10th International Congress on Information and Communication Technology in concurrent with ICT Excellence Awards (ICICT 2025) will be held at London, United Kingdom | February 18 - 21 2025.
Sign up or log in to bookmark your favorites and sync them to your phone or calendar.
Authors - J R Harshavardhan, Anjan Kumar K N, Prasanna Kumar M Abstract - Chronic Kidney Disease (CKD) is a pressing global health concern, where early diagnosis and effective management are vital to prevent progression to end-stage renal failure. This review paper analyzes advancements in the prediction and classification of CKD and related kidney disorders through machine learning (ML) techniques. It explores a spectrum of methodologies, ranging from traditional statistical models to advanced deep learning approaches, assessing their effectiveness in enhancing diagnostic accuracy. A key contribution of this work is the proposal of a novel methodology and block diagram for integrating diverse data sources, including patient demographics, clinical measurements, and medical images, to improve predictive outcomes. The proposed system leverages Convolutional Neural Networks (CNNs) for image analysis and employs ensemble methods for feature integration, aiming to optimize predictive performance. The review also addresses significant limitations, such as data quality and feature selection challenges, while emphasizing the advantages of early detection and personalized treatment through advanced ML models. By identifying research gaps and suggesting future directions, this paper aims to foster the development of more effective algorithms and real-time monitoring systems for CKD and kidney disorder management, ultimately contributing to improved patient outcomes.
Authors - Philane Tshabalala, Rangith B. Kuriakose Abstract - The Fourth Industrial Revolution has had a significant and far-reaching impact on the manufacturing industry. A substantial transformation has taken place within the manufacturing industry, with a notable shift from the conventional approach of mass production to a more bespoke model driven by the global market's demand for enhanced product diversity. This requires the redesign of assembly lines to enable the production of multiple product variants, thereby increasing their complexity. In order to effectively manage the increased complexity and avoid potential bottlenecks caused by longer cycle times, it is essential to implement a virtual system capable of real-time monitoring and fault detection. The current methods for reducing cycle time are deficient in their lack of utilization of real-time data inputs. This article presents a case study of a water bottling plant that employs a mixed-model stochastic assembly line. Two virtual systems, a digital shadow and a digital twin, were developed using MATLAB and SIMULINK as potential solutions. The two systems processed the identical input data in order to calculate cycle times. The results of the study indicate that the application of real-time data and digital twins can lead to a significant reduction in cycle times in a mixed-model assembly line, with an average improvement of 19% in comparison to the digital shadow.
Authors - Hiep. L. Thi Abstract - This paper explores the critical issue of stability in Unmanned Aerial Vehicle (UAV) control systems, particularly under varying environmental conditions and mission requirements. We discuss current challenges, including adaptive control, autonomous missions, urban navigation, and sensor integration. The paper also highlights recent advances in ensuring robust stability and outlines future research directions for improving UAV performance in complex and dynamic environments.
Authors - Abdul Wahab Samad, Noerlina AnggIvanraeni, Khairul Ismed, Ivan Lilin Suryono, Zahera Mega Utama Abstract - Cooperatives are a vital part of Indonesia's economy, and their growth and development have changed several times over the country's history. One of the cornerstones of any functional economy is the cooperative. Much headway was made towards assisting farmers during the New Order through the formation of Village Unit Cooperatives, often called Koperasi Unit Desa (KUD). Conversely, these cooperatives are encountering roadblocks and challenges in their development at the moment. In order to weigh the pros and cons of cooperatives, it is necessary to set up a cooperative framework that considers the cooperative movement and backs regulatory standards. Building this structure is a prerequisite to achieving this goal. That cooperative goods will be available for purchase and supported adequately in the future is ensured by embracing this paradigm. One of the quantitative research methodologies used for this examination was the Smart Partial Least Square (Smart PLS) analysis. An investigation was conducted to assess the scope of the opportunities and constraints that the cooperative market faces in its pursuit of integration into the Indonesian economy. The data found by the academic community at the Institute of Business and Informatics in 1957 shows that the p-value is less than 0.05, which means that there is a substantial association with a number higher than 0.7. This opens up a lot of possibilities for the development and expansion of cooperatives in Indonesia. It is possible that these cooperatives may form the bedrock of the country's future economic success
Authors - Paula Cristina De Almeida Marques, Paulo Alexandre Teixeira Faria de Oliveira Abstract - This further underscore the need to have crisis resilience capabilities in a continuously evolving healthcare environment; especially in the wake of global crises such as COVID-19. This paper explores the impact of intelligent systems in the healthcare system. How to make resilient in crisis, and limits that analysis by comparing with Balanced Scorecard (BSC). When a hospital implements AI and ML technologies, it can dramatically enhance crisis surveillance, reduce the time needed for escalation predictions, and facilitate timely interventions accompanied by quick reactions to unexpected events. Based on multiple case studies, the literature review suggests that intelligent systems can greatly assist in resource optimization, operational efficiency improvement, and crisis decision making. Similarly, to how these perspectives are used to evaluate intelligent systems, BSC analyses them through four financial perspectives: customer; internal processes and growth and learning. We uncovered more than a billion euros respective and on average in value that could be gained fleet of 5G-enabled smart bicycles, specifically contribute to operational efficiency and clinical effectiveness in times of crisis by integrating smart systems. In addition to highlighting the importance of support from upper management an ongoing tailoring of smart systems to assist in the accomplishment of economic alignment to the strategic goals of healthcare organizations The Balanced — So, this study sets out that intelligent systems in health care with the Balanced Scorecard would provide a rapid response health system able to respond appropriately towards forthcoming crises. But there could be for policymakers and health care managers, provide incentives for the strategic integration of these technologies to support crisis management abilities, as well as more general benefits for human health.
Authors - Asmae CHAKIR, Mohamed TABAA Abstract - Throughout the world, the transportation and residential sectors are the most energy intensive. This continues to increase especially with the steady urban development. Consequently, the electricity consumption will increase especially in the above-mentioned sectors. To satisfy this demand, an increase of the electrical production is necessary in an environmentally friendly way. For this purpose, non-conventional or renewable generation is needed. But to overcome the intermittency, the concept of complementary sources hybridization has been launched. In this context, we considered the PV-Wind-Battery hybrid system in small scale that will supply a house already connected to the grid. This will remedy to the issue of increasing consumption in the residential sector. Regarding the transportation sector, a strategy to switch to electric transportation means has been initiated as well. To achieve this, we have hybridized our system with the existence of an electric vehicle used by the building's inhabitants as a means of transportation. On this paper, we proposed to manage the energy of this system according to three management sides, namely: source side, storage side and load management side. This combination allowed an optimization of the energy produced by the renewable system and a management of energy storage preference depending on the home's energetic states. Besides, the management system on the load side which helps in the minimization of the energy consumed trough the electricity utility during the periods of energy deficit to a consumption to satisfy just critical loads, especially with the presence of the mobile battery supplying the electric vehicle via the vehicle to home and home to vehicle strategy.
Authors - Ayoung YANG, Atsushi ISHIBASHI, Ryota IMAI, Tsuyoshi MIYASHITA, Tadasuke FURUYA Abstract - As interest in autonomous ship research grows and challenges from natural disasters increase, the accurate assessment of marine environments is becoming increasingly important. However, current marine environment assessments are primarily focused on evaluating marine resources and environmental conservation, with limited applicability to vessel navigation. This study proposes the creation of a 3D map that integrates both underwater and above-water data, specifically targeting key areas of vessel navigation. The above-water data were collected using LiDAR(Light Detection and Ranging), while the underwater data were mapped using multibeam sonar. This map offers a level of realism that is not achievable with traditional nautical charts, enhancing maritime safety and supporting the operation of autonomous ships through a new format of data.
Authors - Selwa ELFIRDOUSSI, Hind KABAILI, Ghita SEKKAT Abstract - The COVID-19 pandemic disrupted many sectors, including education. The confinement of administrative bodies, teachers, and students confronted us with an unavoidable reality: the need for distance learning. Once schools reopened, several countries and institutions began adopting blended learning models, combining both distance and face-to-face modes. This sudden shift revived research in the field of education, specifically what is known as "Educational Data Mining," a discipline aimed at developing new tools for extracting and utilizing educational data. This paper presents a Machine Learning Model aims to predict student performance in blended learning by understanding the impact of various social, economic, personal, and other factors on student performance, and to identify students at risk of failure.
Authors - Phuong Thao Nguyen Abstract - Artificial Intelligence (AI) plays a transformative role in modern auditing by revolutionizing traditional methodologies and enhancing the overall audit process. The integration of AI technologies in auditing allows for the analysis of vast amounts of financial data, enabling auditors to identify anomalies, trends, and potential errors with unprecedented speed and precision. The significance of AI in identifying financial errors is paramount, as it enhances the detection of discrepancies that may go unnoticed through conventional auditing practices. By leveraging advanced algorithms and machine learning techniques, AI can recognize patterns and flag unusual transactions, thereby significantly reducing the risk of financial misstatements. Moreover, AI enhances the accuracy, efficiency, and compliance of financial audits. Automated data processing and real-time analytics minimize manual intervention, allowing auditors to focus on higher-level analysis and judgment-based tasks. AI tools also facilitate continuous auditing, enabling organizations to maintain compliance with regulatory standards and improve overall financial reporting. This paper provides an overview of the innovative ways AI is reshaping the auditing landscape, emphasizing its potential to elevate the quality and reliability of financial audits while streamlining processes and reducing costs.
Authors - Asmaa Abdul-Razzaq Al-Qaisi, Maryam Yaseen Abdullah, Enas Muzaffer Jamel, Raghad K. Abdulhassan Abstract - New technologies, particularly in recent years, are revolutionising the way the world of cultural heritage, as well as museum and exhibition spaces, is understood. In this context, virtual reality (VR), in particular, is seen as a valuable tool to enrich and enhance traditional visits, using virtual elements to make visitors' experiences more engaging and interactive. Furthermore, as arousing emotions is a fundamental aspect in the creation of museum itineraries, VR techniques are flanked by physiological techniques such as electroencephalography (EEG) that allow for a comprehensive analysis of visitors' feelings. Using EEG-based indicators, this paper aims to analyse the emotional state of a sample of visitors engaged in a first physical, then virtual experience. Interaction, in this case, took place with five specially chosen objects belonging to the collection of the museum of handicrafts of Valle d’Aosta region in order to classify the different levels of involvement. The results suggest that EEG analysis contributed significantly to the understanding of emotional and cognitive processes in traditional and immersive experiences, highlighting the potential of VR technologies in enhancing participants' cognitive engagement.
Authors - Kannary Keth, Samia Ben Rajeb, Virak Han Abstract - This paper presents a comprehensive literature review of research articles on Building Information Modeling in the past decade in thirteen Asian countries, including Cambodia, Thailand, Vietnam, Lao, Indonesia, Malaysia, Philippines, Singapore, Brunei, and Myanmar. Based on a Scopus search using keywords such as Building Information Modeling /Modelling /Model /Management /BIM, barrier/challenge, and the names of the 13 countries, the review identified 81 journal articles. Thirty-two articles were selected to extract the barrier statements. Only literature from four countries, China, Vietnam, Indonesia, and Malaysia, was found and selected. The semantic analysis by NVivo software included word frequency based on the literature review. As a result, 45 main barriers with six classifications: Cost, Technology, People, Environment, Organization, and Education were identified. Furthermore, the classification with high potential factors to influence the adoption of BIM in those countries is the environment, which demonstrates the external concerns, including standards, legality, guidelines, and regulations. Moreover, the main concern in China is a need for more willingness and awareness of BIM; in Vietnam, there is a lack of national standards; in Indonesia and Malaysia, there is concern about high costs. However, the study’s limitations include limited literature sources, exclusion of non-English sources, exclusion of article citations, and absence of expert validation.
Authors - Ivan Ursul Abstract - This paper presents a comprehensive approach to real-time fall detection using advanced Transformer-based architectures tailored for deployment on resource-constrained devices. Our dataset, collected over four months using the WitMotion BWT61CL IMU and complemented by smartphone video recordings, provides a rich, multi-modal source for modelling fall and non-fall events in diverse environments. Our work focuses on the deployment and performance evaluation of three Transformer-based models—Standard Transformer, Performer, and Linformer— each optimized for latency and accuracy in processing timeseries accelerometer data. Rigorous data preprocessing, including noise filtering and feature extraction, was applied to enhance signal quality. We evaluate the models on a dataset comprising 403 samples, achieving a peak accuracy of 98% with the Standard Transformer, and competitive results of 96% with the Performer and Linformer. The Performer model emerges as the most efficient latency, achieving an average response time of 34ms, while the Standard Transformer and Linformer require 350ms and 110ms, respectively. This efficiency, combined with high sensitivity and specificity, underscores the Performer model’s suitability for real-time embedded systems. Our findings demonstrate that advanced Transformer models, with optimized hyperparameters and efficient architectures, can deliver accurate, low-latency fall detection solutions, paving the way for enhanced safety in applications requiring real-time monitoring on compact hardware.
Authors - Varsha Naik, Rajeswari K, Kshitij Jadhav, Aniket Rahalkar Abstract - This study examines cross-lingual natural language processing (NLP) techniques to address the challenges of developing conversational AI systems for low-resource languages. These languages often lack extensive linguistic re- sources such as large-scale corpora, annotated datasets, and language-specific tools, making it difficult to capture the linguistic distinctions and contextual meaning essential for high-quality dialogue systems. This language gap restricts accessibility and inclusivity, preventing speakers of these underrepresented languages from fully benefiting from advancements in technology. The study compares various factors that affect model performance, including transformer model architecture, cross-lingual embeddings, fine-tuning strategies, and transfer learning approaches. Despite these challenges, the research shows that cross-lingual models offer promising solutions, especially when utilizing techniques like transfer learning and multilingual pre-training. By transferring knowledge from high-resource languages, these models can compensate for the scarcity of data in low-resource languages, enabling the development of more accurate, culturally sensitive, and inclusive AI systems. The findings highlight the importance of bridging linguistic divides to foster greater language diversity, accessibility, and technological inclusivity, ultimately supporting cultural preservation and revitalization.
Authors - Elrasheed Ismail Mohommoud Zayid, Ahmad Mohammad Aldaleel, Omar Abdullah Omar Alshehri Abstract - Machine learning classifiers are the first candidate methodology that could be used to assess the digital innovation across a set of teachers. This study aims to collect, build, represent, and discuss a reliable digital innovation skills (DIS) dataset by recruiting teachers chosen from the teachers who work in Bisha Province, Saudi Arabia. The study processed a rich data sample and made it accessible and shareable for the researchers' open use. DIS assessment addressed the problems and helped design a suitable innovation training module for the local community teachers. The total dataset comprises 400 conveniently collected data points, and each data point represents a complete record of teachers among the DSTs of Bisha Province. The research fields are prepared and set as fifty questionnaire questions, which distributed across the DSTs community in the area using social networks. Each question represents a single input or output feature for the classification model. Before running the ML models, the input variables are encoded serially from F0 to F49, and based on an explanatory test performed using LazyPredictools, only the positively contributing features are used. The extensive dataset, which is kept in the Mendeley Data repository, has a great deal of possibilities for reuse in sensitivity analysis, policymaking, and additional study. The decision tree, extra tree, and extreme gradient boosting (XGB) classifiers are examples of the recruited algorithms for evaluating DISs. The authors believe that this a wealthy kind of innovative respiratory dataset with its classification features will become a valuable mining source for interested researchers.
Authors - Malgorzata Pankowska Abstract - Business information system (BIS) consultants are working on solving problems of client companies, providing them with high-quality services, helping them quickly respond to changes in their ecosystems, and to the changes initiated by new technologies. Client is usually the most important actor in the consulting process. Therefore, the consultants are to be well educated to ensure the best satisfying solutions. This study focuses on business information system analysts’ competences development to enable them participation in the consulting projects. In this study, the thematic review of literature was applied, the author’s framework of consultants’ competencies for business information system strategic analysis has been provided, and finally, the author formulate a recommendation on business analysis course for students of computer science at university. The findings indicate that both the students’ motivation, knowledge, experience, as well as a strong theoretical background and a methodological support from cooperative business units influence innovativeness and creativity of BIS consultants.
Authors - Martin Mayembe, Jackson Phiri Abstract - Religious organizations, particularly church organisations, play a significant role in the lives of many people globally. These organisations require efficient management of various operations such as management of members, finances, events, and communications to fulfil their mission effectively. Existing church management systems are often built using traditional monolithic architectures, which come with inherent challenges. These challenges include platform dependence, limited scalability, and high upfront investment, making it difficult for many church organizations to develop, maintain, and scale their systems effectively and efficiently. This method of development is often referred to as the Spaghetti model. This study explores the application of the Micro-services Architecture in Church Management Systems, with the use of a service bus to enable communication between the services, to achieve modularity and scalability. To demonstrate the effectiveness of this design, a prototype is developed, focusing on two key modules: the Church Member Management System and the Financial Management System These modules work in tandem to manage member and associated member contribution data to provide access to up-to-date vital information.
Authors - Williams A. Ayara, Adenike O. Boyo, Mustapha O. Adewusi, Razaq O. Kesinro, Mojisola R. Usikalu, Kehinde D. Oyeyemi Abstract - The search for enhancing green electricity generation and the constant increase in the price of crude oil and its products propelled the choice of this research. Hence, a photovoltaic fuel-less power generating system using locally available materials. The input and output characteristics are analyzed to determine the efficiency, and the power generated by the photovoltaic-powered fuel-less generator is used to power an external load. The photovoltaic used is oriented to face in a direction with optimum tilt for maximum yield (to face southward) of solar power. This orientation and angle of tilt were determined using the Garmin Oregon450 GPS in conjunction with a Seaward Solar Survey 200R meter. Thus, the photovoltaic fuel-less generator was successfully developed. The driving component of this power-generating system is the 1 HP Direct Current (DC) motor, powered by two (2) 250 W mono-crystalline solar panels via a 12 V battery connected to a 30 A charge controller to maintain the charge level of the battery which helps to spin the 650 W Alternating Current (AC) alternator to deliver electricity. The device efficiently delivered power by lighting three (3) incandescent bulbs and a standing fan with total power between 100 – 220 W, and an efficiency of 70 -75%. This generator is eco-friendly since it does not emit any contaminants to the environment.
Authors - Sarah Anis, Mohamed Mabrouk, Mostafa Aref Abstract - This research paper investigates the application of sentiment analysis in the fintech sector, focusing on stock market prediction through a transformer-based model, specifically FinBERT. By comparing its performance against established models like CNN, LSTM, and BERT across different datasets, the study demonstrates that FinBERT achieves superior accuracy in classifying sentiments from financial reviews. The findings emphasize the significance of specialized models tailored to specific domains for improving sentiment analysis within the financial sector, providing useful information for those involved in the fintech field.
Authors - Rotimi Williams Bello, Pius A. Owolawi, Chunling Tu, Etienne A. van Wyk Abstract - One of the mainstream methods for user identification has been by face. However, the vulnerability of face-swapping applications to security issues when swapping the faces between two different facial images, has undermined the genuine aims of the technology, thereby threatening the security of certain applications and individual users when such action is performed without caution. To address this, we propose the development of scalable and safe cloud architecture for a face-swapping application that lets users upload two photos and get a face-swapped output. This is achieved by: (1) creating a secure virtual private cloud (VPC) to hold all application resources, (2) using a Web Application Firewall (WAF) to filter and safeguard requests, (3) putting application programming interface (API) Gateway into place to provide regulated access to the application's API, (4) processing and overseeing face-swapping operations with Lambda functions, (5) using VPC Endpoint to store input and output photos in Simple Storage Service (S3) buckets for private access, and (6) configuring a Simple Notification Service (SNS) to inform users of the progress and completion of their requests. A face swapping dataset derived from an open benchmark dataset was utilized for training and testing the proposed system. The experiment produced an effective solution with a 93% detection accuracy. The implications of this solution are: (1) the provision of security and private access to Amazon Web Services (AWS) by VPC Endpoints and WAF, (2) elimination of Network Address Translation (NAT) Gateway costs by utilizing VPC Endpoints for private S3 access, (3) offering of a scalable processing environment by Lambda functions without the need for server management, (4) delivering of real-time notifications by SNS to users regarding their request status, and (5) optimization of S3 storage ensures quick and efficient access to images.
Authors - Duong Bui, Cuong Nguyen Abstract - Purpose - We are currently experiencing the era of digital transformation. This leads to concepts like digital leadership, continuous learning, and digital culture. The objective of this study is to investigate the influence of various dimensions of digital leadership (DL) on enhancing responsible innovation (RI), with a mediating role of continuous learning (CL) and the management of digital culture (DC). Design/methodology/approach – This study was employed a mixed-methods research design. Data were collected using a self-administered questionnaire distributed to a sample of 250 employees from small and medium-sized enterprises in Vietnam, selected through convenience sampling. Findings - Structural equation modeling was utilized for path analysis in the study. The findings indicated a positive and significant impact of digital leadership (DL) on responsible innovation (RI), mediated through the roles of continuous learning (CL) and digital culture (DC). Practical implications – This study has highlighted the significance of the impact of DL to create CL and DC in Vietnam. The study also confirmed the relationship between DL and RI. It adds to the evidence on digital leadership in Vietnam. Originality/value – Empirical evidence was provided by this study to support the role of DC in fostering RI. Furthermore, how DL strengthens its influence on CL and DC within organizations was demonstrated. By doing so, a critical gap in understanding the impact of DL on RI, CL, and DC in the context of Vietnam is addressed by this research.
Authors - Suresh Rasappan, S. Ahamed Nishath, Francis Saviour Devaraj Abstract - This study proposes a hybrid CNN-ANN architecture for lung cancer image classification on the LC105K dataset. Enhanced feature extraction and representation techniques improve classification accuracy. The model leverages CNN and ANN strengths, demonstrating superior performance compared to existing methods. Results show significant accuracy, precision, and recall improvements, offering a promising solution for computer-aided diagnosis.
Authors - Abdellah Tahenni, Abdelkader Belkhir Abstract - This study provides the privacy concerns of AI predictive algorithms for E-health systems. A significant disadvantage is that these algorithms can infer delicate private health data of people, particularly high profile figures, from big datasets. This might be infringing privacy and result in discrimination or safety threats. The paper additionally analyzes the danger of AI prediction algorithms escalating wider privacy violation risks for patients and providers like accidental disclosure of personal details or unauthorized use of system vulnerabilities for information theft via AI models. The mixed-methods methodology encompasses evaluation of AI algorithm abilities, privacy breach case studies, expert interviews, healthcare provider surveys and eHealth method penetration tests. The results plot vulnerabilities, risk levels and technical, cultural and regulatory variables related to these privacy risks. To lessen those risks, a framework is suggested that has specialized safeguards including AI auditing and differing privacy, governance (data security policies and ethical AI guidelines), organizational (devoted privacy roles and staff training) along with ethical considerations balance innovation with privacy protection. Lastly, the study suggests multi-stakeholder, strategic and collaborative interaction among healthcare, policymakers, AI designers and patient advocates to mitigate AI driven privacy issues in eHealth systems through serious scrutiny and suggestions guided by this vision.
Authors - Kevin Tanuwijaya, Elfindah Princes Abstract - Indonesia's digital economy is rapidly expanding, fueled by technological advancements and government support for e-commerce. E-commerce has become a cornerstone of the nation's economy, significantly contributing to Gross Merchandise Value (GMV). However, Small and Medium-Sized Enterprises (SMSEs), crucial to Indonesia's economic landscape, face challenges in building lasting customer loyalty. This study investigates the impact of affiliate marketing and gamification on SMSE sustainability, focusing on economic, social, and environmental dimensions. Data were collected from a purposive sample of 100 respondents in Jakarta was analyzed using Structural Equation Modeling with Partial Least Squares (SEM-PLS). The results demonstrate that both affiliate marketing and gamification directly enhance customer loyalty. Furthermore, customer loyalty was found to have a significant positive impact on SMSE sustainability. Crucially, the study reveals a mediating effect of customer loyalty, bridging the gap between affiliate marketing and gamification strategies and their ultimate impact on business sustainability. This research contributes valuable insights into the sustainable business literature by empirically examining its effects on key sustainability variables. The study concludes with a discussion of theoretical implications, practical recommendations for SMSEs, and avenues for future research.
Authors - Nguyen Quoc Cuong, Huynh Gia Nghi, Mai Thi Bich Ngoc Abstract - Live streaming has transformed online purchasing, especially for tech-savvy Generation Z, who remain cautious in their purchasing decisions. This study explores the motivational factors driving live streaming-enabled purchasing decision in Vietnam. Applying CB-SEM in the Theory of Planned Behavior, this papers analyzes relationships among 07 variables: information quality, streamer attractiveness, interaction quality, trustworthiness, streamer expertise, online purchase intention, and online purchase decision. Samples consist of 233 Gen Z residents in Ho Chi Minh City (April–June 2024) was analyzed using SPSS and AMOS.. The findings indicate that all examined variables positively impact Gen Z's live stream purchase decisions, helping to advance scholarly understanding and offering insights for businesses to effectively integrate live streaming into their omnichannel strategies.
Authors - Deborah Prasetya Kusuma, Honey Paramitha Soetioso, Nurul Sukma Lestari Abstract - The aim is to examine how employee engagement influences performance, considering the roles of technology and work-life balance. Furthermore, this research also evaluates job engagement as a mediating variable between digital engagement and work-life balance on job performance. This study utilizes quantitative methods, gathering data through both online and in-person questionnaire surveys. The data analyzed using partial least squares structural equation modeling (PLS SEM) and Smart PLS software. The participants are Generation Z hotel employees in Jakarta, such as contract or permanent staff, daily workers, and part-timers who are influenced by technology, referred to digital engagement. A total of 240 respondents successfully completed the survey. The results are digital engagement has influence on job performance, work life balance has not significant influence on job performance, digital engagement, work-life balance, mediated by job engagement has influence on job performance. This research presents a novel conceptual framework for analyzing hotel performance. It also provides valuable insights for hotel management to develop strategies that enhance generation z employees’ performance by improving digital engagement and work-life balance while simultaneously supporting the hotel’s sustainability. For further research can examine variables that were not included in this study, such as digital addiction, job stress, management support, job environment, and motivation with a broader reach local hotel or comparing even until international.
Authors - Rayner Henry Pailus, Rayner Alfred Abstract - Pose face recognition systems often struggle with the variability of illumination and face poses, especially when images are captured in uncontrolled environments. This paper addresses these challenges by proposing a novel face recognition approach: Multiple Adaptive Derivative Face Recognition (MADFR). Our method focuses on optimizing face recognition at every processing level to enhance overall accuracy. By incorporating multiple illumination training samples and diverse training data, including both controlled and wild images, our approach improves the robustness of face recognition models. Our analysis highlights the limitations of existing models like FaceNet, particularly in handling images with multiple face poses and varying background illuminations. We propose pose estimation landmarking and localization with multiple landmarks, which significantly enhances discriminant features. The effectiveness of our approach is demonstrated through extensive experiments on three datasets: LFW, Pointing 04, and Carl Dataset. Our results show that the proposed MADFR system, combined with the ensemble method MADBOOST, consistently outperforms other models. Specifically, MFRF 10 emerged as the top-performing model across all datasets, exhibiting high accuracy and low error rates. This research makes a significant contribution to the eld of face recognition by providing a robust solution that effectively handles the complexities of real-world scenarios. In conclusion, the MADFR system, with its optimized processing and decision-making capabilities, demonstrates substantial improvements in face recognition accuracy, paving the way for more reliable and effective face recognition technologies.
Authors - Sayaka Matsumoto, Kunihiko Takamatsu, Shotaro Imai, Tsunenori Inakura, Masao Mori Abstract - In the context of higher education, Institutional Research (IR) has increasingly emphasized the use of data-driven tools such as student surveys to enhance educational practices and university operations. This study addresses challenges in managing and improving student surveys through advanced visualization techniques. We propose a third visualization method—a stacked bar graph—alongside two existing methods, the heatmap and bar graph with line overlay. This third method visually represents the progression of respondent dropout across questions, offering a detailed view of response continuity. The three visualization methods were used to compare pre- and post-improvement survey data, highlighting key factors such as question design and response behavior. The results indicate that reducing the number of questions and providing clear instructions significantly improve response rates, especially in the later sections of the surveys. The third visualization method effectively highlights these improvements by enabling precise monitoring of dropout trends and response continuity. This study situates its contributions within the interdisciplinary framework of Eduinformatics, integrating education and informatics to optimize educational processes. The proposed visualization methods offer practical tools for evaluating the quality of student surveys and ensuring the validity of collected data. While primarily aimed at student surveys, these methods have broader applicability to other survey-based research contexts.
Authors - Asmaa Berdigh, Kenza Oufaska, Khalid El Yassini Abstract - This study proposes a gradual transition from cabled to wireless communication in vehicles as a means of reducing weight and meeting regulatory requirements related to CO2 emissions, maintenance costs, and time to market. However, the study recognizes that different network domains and compartments in the vehicle have varying requirements and constraints. Therefore, a hybrid architecture between classical wired and wireless networks using Ultra-Wideband (UWB) was proposed as a starting point for testing the feasibility and obtaining feedback. We selected the Headlamp Control Module (HCM) as an application domain since it represents a reduced network consisting of a microcontroller unit (MCU) that operates as a slave to another electronic control unit (ECU) and sensors. This allowed the study to apply the proposed approach to a representative unit scenario. The study outlines the system architectural description for the selected system, the HCM. It describes the Controller Area Network (CAN) and UWB communication and analyzes the requirements that must be fulfilled to interchange both communication technologies. This paper proposes a CAN-UWB gateway system architecture and simulates it to evaluate its ability to meet communication requirements.
Authors - Eyad Mamdouh, Mohamed Gabr, Marvy Badr Monir Mansour, Amr Aboshousha, Wassim Alexan, Dina Reda El-Damak Abstract - This study presents an encryption algorithm for picture cubes that is based on complex differential equation-derived hyperchaotic systems. In order to enable efficient multidimensional encryption, the sensitivity to beginning conditions—a key component of chaos theory—has been extended into the hyperchaotic realm. The combination of DNA coding sequences with Linear Feedback Shift Registers (LFSRs) has increased the complexity of the method. The utilization of LFSRs provides secure pseudo-random sequences, whereas DNA coding adds more cryptographic depth. This combination has produced a strong encryption system that guarantees data security and resistance to sophisticated cryptanalysis attacks. The suggested encryption method has proven to be suitable for protecting volumetric picture data due to its superior performance in entropy, key sensitivity, and resilience to statistical attacks.
Authors - Berliana Tadjudin, Elencia, Davy Jivan Parmono, Tiurida Lily Anita Abstract - There are factors that indirectly influence consumer purchasing decisions in the restaurant industry. As consumer awareness toward environmental issues grows, the implementation of eco-friendly packaging, environmentally friendly visual appeal and adopting sustainable business model are a growing trend in the restaurant industry. In other hand, elements such as the aesthetics of the menu, food packaging, the design of the restaurant room, and the general brand awareness are also one of the factors that play an important role in influencing purchasing decisions, which could also be a factor toward consumer trust in the restaurants and loyalty toward the business. With both ideas in mind, this research was conducted to answer and analyze the impact of various elements on consumer buying decisions toward a restaurant adapting sustainability model. The research is conducted in Greater Jakarta Region and manages to gather 250 samples of respondents which are analyzed statistically, to investigate the validity of the hypothesis. The data gathered from the analysis shows that there are significant relationships between the variables.
Authors - Etian Ngobeni, Sara Grobbelaar, Christopher Mejia-Arguata Abstract - Infrastructure maturity models largely guide an organization towards adopting advanced technologies. However, the knowledge on how such models can be developed for wholesale food markets is still lagging. This study fills the gap by using a pragmatic approach and the application of design science research methodology to develop a roadmap to developing a maturity model for infrastructure in wholesale food markets. This paper proposes a three-phase comprehensive framework for developing a maturity model.
Authors - Senthil Kumar Subramani Anandan, Lorenzo Garbagna, Lakshmi Babu Saheer, Mahdi Maktar Dar Oghaz Abstract - Air quality monitoring systems have become an important part of urban areas due to recent attempts to monitor pollution levels to tackle problems such as climate change and population health risks. In recent years, research has been conducted of the utilisation of lowcost pollution concentration sensors to improve and expand on current air monitoring systems, as well as creating mobile systems that could be deployed in different scenarios. Although, the spread of Internet of Things (IoT) devices for monitoring systems brought the need of calibration between multiple different devices that could be found working inside the same network. This project explores the utilisation of Machine Learning and Deep Learning models to calibrate custom and Aeroqual sensors for PM2.5 and PM10 monitoring to an existing network from the city council in Cambridge, UK. For PM2.5, the collection with the custom sensor provided the highest accuracy when calibrated to the council one: Keras Regressor achieved an RMSE of 1.6240 and R2 of 0.8831, while with the data from Aeroqual a GRU Regressor achieved an RMSE of 1.9263 and R2 of 0.4867. On the other hand, collection with Aeroqual on PM10 concentration levels achieved an RMSE of 2.2087 and R2 of 0.6428 utilising RNN Regressor, while an MLP with Attention achieved a lower accuracy, with an RMSE of 4.9582 and R2 of 0.3297.
Authors - Ferlyn P. Calanda Abstract - The main goal of this project was to develop a Poultry Farm Monitoring and Control System using a web application platform. This system was designed to assist farmers by providing real-time data on temperature, humidity, ammonia levels and the overall environmental conditions within the poultry houses. As a result, farmers were able to access this information and make informed decisions to maintain animal welfare and productivity. The study employed a combination of descriptive and developmental research methods. A total of thirty (30) respondents including farmers, agriculturists, veterinarians, and faculty members from the agriculture department, took part in the study. The number of respondents was based on the suggestion of Jakob Nielsen [2012], which states that for quantitative studies, usability tests can be deployed on at least twenty (20) users to get statistically significant numbers. These respondents were able to remotely monitor the data and use it to inform decision-making processes.
Authors - J. Coetzer, R B Kuriakose, H J Vermaak Abstract - As manufacturing and business sectors adopted Industry 4.0, the Fifth Industrial Revolution (Industry 5.0) emerged. Unlike its predecessor, Industry 5.0 extends its focus beyond economic growth and job creation, recognizing the manufacturing sector’s potential to support to broader societal goals. The continuous technological advancements and system improvements of Industry 5.0 have sparked a new area of research: enhancing human-machine interaction in commercial and industrial manufacturing environments by fostering better collaboration between humans and machines. There have been limited studies on how to establish a CDM process that takes into account the worker's recognition and ability to adapt to this development. The aim of the paper is to explore if existing protocols for Human-Machine Collaboration (HMC) are present in the manufacturing sector. If such protocols do not exist, the paper seeks to develop a universal protocol suitable for implementation in an Industry 5.0 context. An entirely mechanized water bottling plant will be serve as a case study to examine the effects of HMC. The study aims create a protocol that supports CDM within an Industry 5.0 environment. To support this goal, a single-case experiment has been conducted to test the theory of HMC that will lead to optimal production time of an automated system in an Industry 5.0 context. The paper details the background that motivated the research, methodology used and showcases steps taken in creating a protocol for CDM before concluding with the investigation of preliminary results, that show an up to an average of 24% reduction in production time.
Authors - Vusumzi Funda, Bingwen Yan Abstract - Knowledge is a strategic asset and a critical source of competitive advantage for organisations. Consequently, organisations employ various knowledge management (KM) enablers to acquire, store, secure, retrieve, share and utilize knowledge, all of which are crucial for enhancing organizational performance. Information and Communication Technologies (ICTs) play a pivotal role in facilitating these processes. This study aimed to evaluate the effectiveness of ICT usage in KM within the context of South Africa, with a specific focus on identifying barriers to ICT utilization. A quantitative method research approach was adopted using surveys. The findings revealed that the selected university lacked a comprehensive guideline on ICT usage, which hindered effective KM. The study concluded that while KM is essential at the University, significant efforts are needed to improve its practices. Additionally, a comparative methodology was proposed to analyse disparities in ICT utilization across different institutions. This study contributes valuable insights into KM and offers practical implications for policy review, potentially influencing management and other stakeholders to initiate necessary reforms.
Authors - Maria Sahakyan, Meri Badalyan, Lusine Karapetya Abstract - The article is devoted to the study of the essence and characteristics of discrimination in the IT workplace. Obviously, the field of information technology is one of the priority areas for the development of the economy of the Republic of Armenia. This area is developing quite rapidly, and the average salary in IT companies is higher than the average salary in other spheres in Armenia. On the one hand, we still face the stereotype that a successful IT professional is a man. On the other hand, women in Armenia are starting to play an increasingly important role in coding, product development, web design, and other IT areas. The average share of women employed in IT in the world doesn't exceed 20% even though the tech world aspires to achieve gender balance and diversity. According to the data of 2022, more than 43% employees of the IT sector in Armenia are women, which is a quite high index at the global level. But still women in the IT sector earn on average about 1.5 times less than men. Despite the efforts of different engaged bodies to diminish the discrimination in the work-place, this is still a serious issue.
Authors - Lillian Mzyece, Jackson Phiri, Mayumbo Nyirenda Abstract - Accurate rainfall forecasts are critical for various sectors, yet traditional methods struggle due to evolving and non-linear weather patterns. This study evaluates four machine learning algorithms—Support Vector Machines (SVM), Random Forest (RF), Neural Prophet (NP), and Long Short-Term Memory (LSTM)—to determine the most effective algorithm for rainfall forecasting in Zambia. Results show that Neural Prophet outperformed others, achieving the lowest RMSE (4.67), MAE (16.75), and MAPE (13.40%). Its autoregressive capabilities, interpretability, and reduced parameter complexity make Neural Prophet the preferred choice for forecasting rainfall trends in Zambia.
Authors - Nailah Al-Madi Abstract - The diagnosis of appendicitis is a challenge especially for children, as its symptoms overlap other diseases and children are unable to express their pain well. The misdiagnosis rate ranges from 28% to 57% in children. Machine learning is efficient in building models that can help predict diseases. XGBoost is one of the best machine learning models since it is based on ensemble learning approach. XGBoost has hyper-parameters that should be tuned well in order to achieve high performance. These parameters could be optimized to find the optimal or near optimal performance of XGBoost. In this paper, an Optimized- XGBoost model is proposed, which uses Genetic Algorithm to optimize seven parameters of XGBoost to achieve high performance. This Optimized-XGBoost is used to predict three class labels of pediatric Appendicitis, including diagnosis (appendicitis or no appendicitis), Severity (complicated or not complicated), and management(conservative or surgical). The experiments were implemented on Pediatric Appendicitis with 38 features and 780 records, and compared optimized-XGBoost with original XGBoost, and other well-known classifiers, such as DT, SVM, NB, KNN, RF, and Adaboost. Results show that optimized-XGBoost achieved highest results for accuracy, precision, recall and F1-Score. For example, the F1 score results for the prediction of severity is 96.15%, for the prediction of diagnosis is 99.36%, and for treatment is 99.36%.
Authors - Andre Viviers, Bertram Haskins, Reinhardt A Botha Abstract - Tracking gastropod chemical trails is time-consuming and error-prone. This paper argues that computer vision provides a viable alternative. Using selected image manipulation and segmentation techniques, an unlabeled dataset was generated. A simple K-Means clustering algorithm and manual labelling created a labelled dataset. Thereafter, a best-effort model was trained to detect gastropods within images using this dataset. Using the model, a prototype was created to locate gastropods in a video feed and draw trace lines based on their movement. Five evaluation runs serve to gauge the prototype’s effectiveness. Videos with varying properties from the original dataset were purposefully chosen for each run. The prototype’s trace lines were compared to the original dataset’s human-drawn pathways. The versatility of the prototype is demonstrated in the final evaluation by generating fine-grained trace lines post-processing. This enables the plot to be adjusted to different parameters based on the characteristics that the resulting plot should have. This research demonstrated that a gastropod tracking solution based on computer vision can alleviate human effort.
Authors - Maya Dimitrova, Nina Valchkova Abstract - The paper presents the concept of a ‘cyber-physical nurse’ from a feasibility perspective for wider inclusion in healthcare, in particular in relation to empathic communication with the patient. The results of a pilot study on user perception of two robotic and one human faces are presented and discussed in this context. Users attributed positive features to neutral agents’ facial expressions, but not negative, which increases the feasibility of introducing social robots in healthcare. Some guidelines for cyber-physical nurse design are discussed, addressing challenges to its possible implementation in hospitals, rehabilitation centers, and home care settings.
Authors - Tagnon Adechina Geoffroy Zannou, Semevo Arnaud Roland Martial Ahouandjinou, Manhougbe Probus Aymard Farel Kiki, Adote Francois-Xavier Ametepe Abstract - Sensor-based gas analysis has been the subject of much research, particularly in the development of electronic nose (e-nose) systems. E-noses are based on chemical sensors to detect and analyze volatile organic compounds, and thus play an important role in a variety of fields. In this paper, based on three research strings, we have performed a bibliometric analysis to examine current trends and scientific contributions in the field of sensors for detecting odors and volatile organic compounds (VOCs), their use in electronic nose systems, work to improve their performance and their optimization. Using the Scopus database and English-language documents published between 2014 and 2024, we identify the most prolific authors, countries and journals in these fields. After that, a short literature review provides a detailed overview of the strategies to improve e-noses selectivity and reduce their drift. The results of the bibliometric analysis show a growing intercontinental interest, with strong scientific activity in China, the United States, India and Italy, with a particularly strong focus on performance improvement and sensor optimization. The short survey reveals the existence of a wide range of gas sensors with their advantages and disadvantages, significant advances in improving the performance of sensors and electronic noses, as well as new challenges that deserve attention.
Authors - Adibah Alawiah Osman, Azwan Abdullah, Sharul Shahida Shakrein Safian, Nor Zawani Ibrahim, Nik Rozila Nik Mohd Masdek, Norhasimah Shaharuddin, Nur Athirah Sumardi Abstract - The process of using various data methods within one study to con-firm that the results are firmly supported by the predictions made is called triangulation. Several methodological debates have highlighted the limitations of quantitative research compared to qualitative research. This paper hunts to explore the triangulation research approach in the background of Islamic marketing at fully established Islamic banks in Malaysia. Islamic marketing of Islamic banks is defined as the application of Islamic banking knowledge, Islamic advertising ethics, and the augmentation of learning and instruction by Islamic bank employees in this study. The present research clarifies the basis links between the quantitative data of Islamic bank’s staffs at fully established Islamic banks and the qualitative insights of Islamic financial experts. The amalgamation of both qualitative and quantitative approaches in data collection and evaluation significantly improves the quality of the research outcomes. Further studies ought to explore the application of the triangulation method in other domains.
Authors - Carlo Giuseppe Pirrone Abstract - This study explores urban accessibility for the elderly, focusing on the importance of integrating objective and subjective measures for a comprehensive assessment. Objective measures, such as cumulative opportunity measures (CUM) or measurable travel times, quantify spatial data while often neglecting personal experiences and user perceptions. Subjective measures, obtained through surveys, become crucial in defining the ease of access to services, including satisfaction levels derived from the journey, barriers due to individual factors (age, health, disability), as well as comfort and safety. A combined methodology would promote a new interpretation of urban accessibility. A case study conducted in Rende, Italy, illustrates a practical application by mapping healthcare services and public transport to assess pedestrian accessibility. A pilot survey gathered elderly residents' perceptions of distance, travel time, and service satisfaction. Preliminary results indicate a reluctance to walk, overestimated perceived distances and a strong reliance on private vehicles, highlighting the need for infrastructures and services to provide a better connection of the elderly to healthcare services. Ongoing research will further refine the study by adapting objective measures to local perceptions to develop a specific accessibility indicator for the area.
Authors - Dilshan De Silva, Dulaj Dawlagala Abstract - The research demonstrates a reliable and efficient IoT solution aimed good at improving the safety of campers and hikers in outdoor settings. It consists of one primary device and a set of other peripherals, which employ LoRa communication, GPS positioning, and environmental parameters for location-based services. The primary device system consists of an ESP32 microcontroller fitted with a LoRa 433 MHz module and NEO-7MGPS powered using SYN-ACK protocol that allows the device to constantly communicate with the subordinate devices. The subordinate devices which are also based on ESP32 has LoRa modules and OLED screen for the purposes of receiving and providing information about the geofences and locational alerts. A significant strength of this system is that it is able to function in remote areas by bringing all the devices together into a mesh network so that data and devices can be synchronized without relying on the internet for connection purposes. Both primary and subordinate devices have the ability to connect to the internet wherever possible, update messages, synchronize, and transfer messages efficiently. Failure is further minimized for effective communication and precise positioning which are important in the management of outdoor safety hazards. The first prototype tests have shown the ability of the system to solve problems such as real-time interaction, data integration, and functioning in difficult environments. To npm and deploy the research further developed IoT systems for outdoor applications, effective outdoor deployment strategies were developed. As the next step, the system will be tested on a larger scale to assess its scalability, and user-centered interfaces will be redesigned to accommodate real-world scenarios.
Authors - Jude Osakwe, Sinte Mutelo, Nelson Osakwe Abstract - This study aimed to investigate the interrelationship between data governance and compliance with privacy regulations. A systematic literature review was conducted to synthesise the existing research on data governance's impact on compliance with privacy regulations. The study found that data governance has a positive association with compliance, with integrated data governance methods and processes supporting decision-making, and stakeholders' involvement guaranteeing transparent processes. The findings also suggested that the impact of data governance on privacy regulations compliance needs a certain maturity level and top management support. Key recommendations for organisations are outlined to enhance their governance frameworks, promote transparency, and align resources effectively in order to bolster compliance with privacy regulations. The study concludes by addressing identified research gaps and offering directions for future studies aimed at exploring the evolving landscape of data governance and privacy compliance.
Authors - Nabeela Kausar, Ramiza Ashraf, Saeed Nawaz Khan Abstract - Skin cutaneous melanoma is one of the most aggressive forms of skin cancer, with various prognostic factors that can significantly impact patients’ survival outcomes. Survival analysis helps in identifying key factors influencing patient outcomes and guides in clinical decision-making. In literature, statistical methods have been used for the survival analysis of skin cancer patients but these methods have limitations. To address the limitations of traditional statistical methods in survival analysis, researchers have developed a range of machine learning (ML) based survival analysis techniques. These ML techniques offer advanced capabilities for modeling complex relationships and improving prediction accuracy. But "black box" nature of ML models poses a challenge, especially in fields like healthcare where understanding the rationale behind predictions is crucial. It this work, Explainable AI (XAI) based survival analysis has been carried out using XGboost model and clinical features of skin cutaneous melanoma patients. XAI models explain their prediction by showing the important features involved in the prediction to demonstrate their reliability to be used by the clinicians. To validate the performance of XAI model, in this work, multivariate regression based Cox Proportional Hazard (CPH) model has been developed which shows the relationship of patients’ clinical features and survival time. The pro-posed XAI based model has C-index value of 84.3% and shows that age, pathology T stage, and pathology N stage are key factors influencing the survival of skin cutaneous melanoma patients. The CPH model further validates the strong association between these features and patient survival.
Authors - Mulima Chibuye, Jackson Phiri Abstract - Agricultural systems have been modeled and prediction of yields used in the space since the beginning of agriculture ,improvements in the crop science and better tools made the task much easier through the ages, from using the position of the sun to determining that certain weeds signify a good harvest to actually determining what factors precede observable phenomena, the space has be-come so advanced such that we are able to build better prediction models and the promise of quantum computation that can model much more complex systems and interactions among the individual parameters within the system promise to make us predict yields of crops with much better accuracy than has ever been deemed feasible. With the technology that we have available now, we can apply properties of physical systems on classical computers such as mimicking chaos theory to add randomness to our predictions as that is the way nature works. That randomness is due to how initial conditions might potentially fluctuate and we would normally call it random because we are missing certain parameters that if we collect, would greatly improve how we predict physical chaotic systems. The aim of this work is to explore how we can incorporate chaos in agricultural systems by making use of a hybrid approach to known systems like dense neural networks and more recent methods such as Echo State Networks.
Authors - Cynthia Sherin B, Poovammal E Abstract - Vehicle detection and classification has a key role in evolution of intelligent transportation system. Accuracy in the detection enhances the efficiency of intelligent traffic monitoring systems. The paper shows a comparative study on the performance of YOLOv8 and YOLOv10 detection models on the novel Vehicle Identification aNd Classification (VINC) dataset introduced. They detect multi-class vehicles such as cars, trucks, buses, bicycles and bikes. The achievements of each model are assessed using precision, recall, F1 score and confusion matrices. The experimental results demonstrates the supremacy of YOLOv10 in detecting very small and more complex vehicle structures in the traffic scenario than YOLOv8. Alternatively, YOLOv8 also exhibited equivalent detection accuracy in detecting large vehicles like buses and trucks, by capturing the minute variations in the processed features. The detection models achieve precision of 97.2% and 93.6% for YOLOv10 and YOLOv8 respectively. YOLOv10 achieves high recall rate and F1 score of 92.4% and 81.4% respectively. Thus, the detection performance of these vehicles expresses the robust characteristics of both the YOLO versions. This research paper delineates the merits and drawbacks of these two versions on real-time circumstances, thereby creating faster and precise detection models.
Authors - Ansh Soni, Krish Modi, Aneri Shah, Nishant Doshi Abstract - A successful and efficient transportation system depends on the credibility of engines and machinery. With the help of NASA Turbofan Jet Engine dataset, this paper focuses on the predictive maintenance framework to boost transport efficiency by leveraging sensor data. With the help of machine learning algorithms, we predict the Remaining Useful Life (RUL) of engine components based on training the model with appropriate algorithms that prompt scheduled services and maintenance to reduce downtime. Feature engineering techniques and predictions of RUL, Health Index(HI), and degradation score- the proposed model provides a methodology for enhancing system dependability and minimizing maintenance costs. This study provides valuable insights into current transportation setbacks.
Authors - Dario Lombardi Abstract - This study investigates the impact of Serious Games (SGs) and ChatGPT on nursing education, focusing on usability, learning outcomes, engagement, skill transfer, and future usage intentions. Using a multi-phase design aligned with the ADDIE instructional model, the study explores how these tools facilitate learning through experiential and cognitive pathways. In the first phase, students designed instructional interventions using the ADDIE model, while the second phase introduced ChatGPT as an AI-driven support tool. Findings reveal that SGs promote experiential learning by enhancing clinical skills, emergency response, and procedure retention. Usability metrics were high, with 79% of participants rating interface intuitiveness positively. Conversely, ChatGPT supported cognitive scaffolding, enabling faster and more effective instructional design. Students reported a significant increase in familiarity with AI, with 68.4% moving from "low" to "medium" familiarity. Engagement and motivation were strong for both tools, with 84.2% of participants intending to continue using ChatGPT. Despite its small sample size (n=19), this study highlights the potential for hybrid models that integrate SGs and AI to improve nursing education. It calls for the incorporation of these tools into curricula, emphasizing experiential learning (SGs) and cognitive support (AI), thereby addressing both procedural and conceptual learning needs.
Authors - Ravichandran S, R Kasturi Rangan, Manjesh R, S Karthik, T N Hemanth Abstract - The page-level recognition and reordering of handwritten documents is important in digitizing and archiving systems. These systems focuses on solving the two problems of converting relevant parts of a handwriting document into recognizable formats for machines as well as correctly sequencing pages in order to preserve context. Building upon the state-of-the-art in Optical Character Recognition (OCR) and Document Layout Analysis (DLA), The paper suggests that these methods are effective for page-level text recognition that combines automatic reading order detection with advanced OCR modeling. This study evaluates the impact of a hybrid architecture combining Vision Transformers (ViT) for powerful feature extraction, and transformer-based Language Models (LMs) to provide context during text decoding. We then pose the task of reordering as a sorting problem and use a pairwise order-relation operator trained from annotated data to generalize to various layouts of input documents. The phenomenon under study reveals significant trends in the state-of-the-art performance on standard datasets with significant recognition accuracy gain and reordering precision. It opens up the efficient processing of handwritten documents in applications that range from preserving historical writing samples to today’s administrational scanned handwritten documents.
Authors - Khanyisani I Ndlovu, Timothy T Adeliyi, Alveen Singh Abstract - Integrating Information and Communication Technology (ICT) in educational settings has become fundamental to modern pedagogy. Despite its significant contributions, ICT's adoption, integration, and usability pose challenges for school students in developing countries, particularly in Sub-Saharan Africa. This study aims to identify and analyse the diverse factors influencing the widespread adoption of ICT among students. A comprehensive systematic literature review revealed thirty-eight factors from eighty-four articles that either facilitate or hinder ICT integration in students' academic activities. Using Principal Component Analysis (PCA) a statistical method known for reducing dimensionality and uncovering patterns in complex datasets. The study extracts the most critical factors impacting ICT adoption. The findings indicate that in addition to over-digitalization, cognitive barriers, health issues, time constraints, funding limitations, and a lack of modern software are significant factors affecting students' engagement with technology. The implications of this study are relevant to policymakers, educators, and academic institutions, providing a data-driven basis for strategies aimed at improving ICT adoption
Authors - Pesta Evaria Simbolon, Himsar Silaban, Khasan Effendi, T. Herry Racmatsyah Abstract - Currently, the professionalism of expert staff at the House of Representatives (DPR RI) is influenced by various interconnected factors such as work management, coordination, compensation, qualifications, and competence. This study aims to identify the key factors affecting the professionalism of expert staff at DPR RI and provide recommendations to improve their performance. A qualitative research method was employed using thematic analysis, grounded theory, and triangulation through NVIVO 14 to analyze interview data and relevant documents. The results indicate that work management and coordination, competitive compensation, staff qualifications and competencies, rigorous recruitment and selection processes, and objective performance evaluations are the primary factors influencing professionalism. Furthermore, professional development and clear career paths enhance staff loyalty and performance, while benchmarking against industry standards offers insights into best practices that can be adopted. Addressing challenges and barriers in the workplace and ensuring a clear organizational structure help define roles and responsibilities. High-quality support from expert staff and satisfaction with compensation has a direct impact on the effectiveness of DPR RI. Thus, DPR RI must focus on and improve these factors to ensure the optimal efficiency and effectiveness of expert staff, ultimately supporting the overall performance and effectiveness of DPR RI.
Authors - Ilnar Yarullin, Ramis Nasibullov, Almaz Galimov, Shamil Sheymardanov Abstract - This paper is important because it highlights the need to improve how we help students with their internships. This need arises from higher expectations for the quality of training future teachers receive and the limitations of traditional methods of internship support. The article explains the idea and functioning of a digital platform designed to assist students with their internships. The aim of this platform is to improve the quality of their professional training by enhancing communication among everyone involved in the educational process. The software described provides options for creating flexible schedules that consider different types of internships, such as in-person, remote, and hybrid. This flexibility is especially important when working with various groups of students. In addition to assigning mentors and supervisors, both teachers and students can outline the goals and objectives of the internship. This helps to avoid misunderstandings and ensures that everyone is clear about what needs to be accomplished at each stage of the internship. The platform is connected to the university's corporate system, teaching websites, and electronic publications. As a result, teachers, students, and administrators can share information more easily.
Authors - Pablo Salamea, Remigio Hurtado, Rodolfo Bojorque Abstract - Recent advancements in deep learning have enabled the development of convolutional neural network (CNN) architectures, which have proven to be valuable tools in computer-aided diagnosis (CAD) systems. These systems assist radiologists in identifying regions of interest associated with pathologies in chest X-ray images, a diagnostic tool recognized as essential by the World Health Organization (WHO). The WHO highlights that chest X-rays are an accessible and cost-effective method, crucial for evaluating respiratory and thoracic diseases, particularly in resource-limited settings and during global health emergencies. In this study, the Vindr-CXR dataset was used, known for providing labeled chest X-ray images suitable for multi-label classification tasks. The process began with data preparation, where images and labels were grouped in a binary format and split into training and validation sets. Subsequently, pre-trained neural network architectures, such as VGG16, InceptionV3, ResNet50, and EfficientNetB0, were utilized with weights initialized from ImageNet. The initial layers of these architectures were frozen, and dense layers with sigmoid activation were added for multilabel classification. During training, the binary crossentropy loss function and the Adam optimizer were employed. The models were trained for a fixed number of epochs, with validation conducted at the end of each epoch to evaluate metrics such as accuracy and loss. Finally, predictions were generated on the validation set, and key metrics such as the ROC curve, precision, recall, and F1-Score were calculated. The models achieved a promising performance, with an accuracy of 0.72 in detecting thoracic pathologies. These findings highlight the potential of deep learning to enhance diagnostic precision and support clinical decision-making, reaffirming the critical role of chest X-rays
Authors - Pei-Jung Lin, Meng-Chian Wu,Jen-Wei Chang Abstract - To compare the effects of music and meditation on brainwave patterns and attention, this study designed a series of EEG-based experiments. Participants were instructed to either listen to music or engage in meditation, while their attention levels were assessed using a Rapid Serial Visual Presentation (RSVP) paradigm to validate brainwave differences under varying attentional states. EEG data were collected to analyze changes in attention during exposure to different types of music. Subsequently, mathematical computations were applied to quantify and summarize the pre- and post-intervention differences. The experimental results revealed significant differences in the impact of various music genres on attention. Listening to classical music effectively enhanced attention, whereas listening to popular music demonstrated a notable effect on emotional relaxation. Deep meditation yielded the greatest improvement in concentration, and its brainwave patterns closely resembled those observed when listening to classical music. An analysis of Arousal and Valence metrics indicated that meditation led to positive emotional changes. These findings suggest that both music and meditation can influence attention and emotional states.
Authors - John Khoo, Rayner Alfred, Khalifa Chekima, Rayner Pailus, Chin Kim On, Ervin Gubin Moung, Raymond Alfred, Oliver Valentine Eboy, Normah Awang Besar Raffie, Ashraf Osman Ibrahim, Nosius Luaran Abstract - Carbon stock serves as a crucial metric for assessing the quantity of carbon stored within terrestrial and aquatic ecosystems, exerting signi cant in uence on global carbon dynamics and climate change mitigation eorts. Eective management of carbon stocks is vital for regulating atmospheric carbon dioxide (CO2) levels and mitigating the adverse impacts of climate change. The study delves into the estimation of carbon stocks, particularly focusing on above-ground biomass (AGB) as a key component of carbon storage in forests. In addition, explores methods for estimating above-ground biomass (AGB) of carbon storage in forests. Traditional eld-based approaches, statistical methods like regression, and machine learning techniques such as deep learning oer varied strategies for AGB estimation. These methods leverage a variety of data to enhance accuracy and scalability. Through empirical examples, the study presents their eectiveness in informing conservation strategies and fostering sustainable development amidst environmental challenges.
Authors - Juan Dominguez, Carlos Carranco, Remigio Hurtado, Rodolfo Bojorque Abstract - Driver fatigue is one of the leading causes of road accidents worldwide, affecting concentration, reaction time, and vehicle control. Sleep deprivation, long driving hours, and monotonous conditions increase the risk, particularly among professional drivers and shift workers. Identifying early signs of fatigue is essential for improving road safety and preventing accidents. This study introduces a structured framework for detecting fatigue based on EEG and EOG signal analysis. Using the SEED-VIG dataset, the methodology integrates multiple stages, including data processing, feature selection, model training, and performance optimization. Various machine learning models were tested, with particular emphasis on Random Forest, LSTM networks, and ensemble techniques such as Gradient Boosting, XGBoost, and LightGBM. Additionally, explainability techniques like SHAP and LIME were applied to highlight critical fatigue indicators, such as variations in blink frequency, saccadic movements, and brainwave activity in the theta and delta frequency bands. Among the tested models, the optimized Random Forest approach yielded the highest accuracy, with an RMSE of 0.0257. These findings contribute to the advancement of fatigue monitoring technologies, offering practical solutions for real-time driver assessment and accident prevention.
Authors - Madhwendra Nath, Subodh Srivastava Abstract - Denoising of the heart sound signal is crucial part of the heart sound signal analysis, as it reduces the interfering noise such as respiration noise, gastric noise, speech, motion artifacts, and power-line interference from the signal. The In-band noise in a phonocardiogram (PCG) signal refers to noise or artifacts that overlap with the frequency range of interest for major heart sounds which is typically 20–100 Hz. To reduce this in-band noise; a Daubechies-wavelets based approach is proposed. The parameters of Dabuchies-wavelets are revamped. To judge the proficiency of the proposed method, a novel performance-metric-index, Noise-area-difference (NAD) has been introduced. It evaluates the Denoising performance. The proposed method is compared with three other existing methods. The comparison results reveal that the proposed method outperforms existing state-of-the-art Denoising of Heart sound signals.
Authors - Welekazi Ntloko, Sara S. (Saartjie) Grobbelaar Abstract - Social franchising is a business model in which a successful social enterprise is replicated in multiple areas, often by providing franchisees with training, support, and resources. Social franchising aims to assist social entrepreneurs to impact a larger number of people with their services by scaling their operations while maintaining their standards of excellence and consistency. Social franchising (SF) is used to scale social business models in new locations, allowing them to expand their impact. This article serves to analyse and review the literature surrounding social franchising. Preliminary results reveal a substantial focus on healthcare in social franchising research, with limited multidisciplinary studies. Challenges include the limited legal frameworks in many jurisdictions, impacting stakeholder certainty. The study aims to contribute insights into the evolving landscape of social franchising, emphasizing the intersection with SBMs and HO for sustainable and impactful outcomes, with potential implications for sustainable economic and social development.
Authors - Kuhlula Mathebula, Noluntu Mpekoa, Khutso Lebea Abstract - This research aims to assess the suitability of a multi-factor authentication (MFA) scheme for protecting a university's Wi-Fi network from threat actors. Given the vulnerabilities of current single-factor authentication methods, which often rely on usernames and passwords, implementing MFA is proposed as a more secure alternative. MFA enhances security by requiring users to pass through multiple authentication mechanisms, such as knowledge-based, possession-based, and biometric methods, making unauthorised access significantly more difficult. The research seeks to determine the most effective combination of authentication factors for a university environment. The research findings may have broader implications for securing educational institutions' networks.
Authors - Amr Abu Alhaj, Omar Safwat, Youssef Ghoneim, Imran Zualkernan, Ali Reza Sajun Abstract - This paper examines the use of pre-trained models like Bidirectional Encoder Representations from Transformers (BERT) and A Robustly Optimized BERT Pretraining Approach (RoBERTa) to create reliable models for detecting fake news from media articles. Traditional Machine Learning (ML) methods frequently have difficulties in accurately identifying the nuances of misinformation due to extensive feature engineering dependencies. The latest advancements in Large Language Models (LLMs) such as BERT and RoBERTa have fundamentally transformed misinformation detection by providing deep context. The research utilizes the LIAR dataset, containing 12.8k manually labeled statements from PolitiFact.com, along with associated metadata and speaker credit scores. The approach combines BERT/RoBERTa embeddings with complementary architectures for binary classification, introducing a credit-score calculation reflecting speakers’ historical truthfulness. Notably, BERT-BiLSTM-CNN-FC and RoBERTa-BiLSTM-CNNFC configurations achieved state-of-the-art F1-scores of 0.76 and 0.74, respectively.
Authors - Ana Martinez-Gamez, Heberto Ferreira-Medina, Bernardo Lopez-Sosa, Sayra Orozco, Mario Morales-Maximo, Carlos A. Garcia, Michel Rivero Abstract - This project aims to develop a methodology for predicting solar radiation in San Francisco Pich´ataro, a community in the municipality of Tingambato, Michoac´an, Mexico. This community lies within the Pur´epecha indigenous zone. The project utilized two databases: one from a solarimetric station in the area and the other from the Solcast platform, which provides access to solar irradiance and other pertinent meteorological variables. Rigorous data cleansing and analysis procedures were implemented to ensure data quality and compatibility. Subsequently, both linear and decision tree regression models were applied to the refined and prepared data to forecast solar radiation.
Authors - Haryadi Sarjono, Safina Alya Zahira, Ine Silviya, Boyke Setiawan Soertin Abstract - This study aims to identify the office layout that best suits Gen Z workers' preferences and enhances productivity and work quality. A qualitative method with a descriptive approach was employed, focusing on Gen Z employees in the Information and Technology Division. Among the 38 employees in this division, ten are Gen Z, and eight of them participated in the study through a questionnaire and partial interviews to delve deeper into their responses. The questionnaire covered six different office layout types and assessed their impact on work productivity and efficiency. Gen Z employees in the Information and Technology Division favored new layouts, particularly the Relax Corner, Desk Facing Outside Window, Mini Bar, and WFO Feel Like WFC. They prefer cozy, flexible office spaces with diverse work environments. The findings suggest that these new office layouts can enhance productivity and work efficiency for Gen Z employees. However, some participants noted that their productivity and efficiency were more influenced by factors like their colleagues and teamwork rather than the office layout itself.
Authors - Rolph Abraham YAO, Ferdinand Tonguim GUINKO Abstract - Software-defined networking (SDN) is a growing concept that allows the separation of the control layer from the data layer, making the network programmable, and having a centralized view and management of the network. The control layer is an important component of the network because it is composed of controllers that play a role in supervising and controlling the entire SDN network. For efficient traffic management in SDN, it is essential to have a high-performance controller. In this paper, a performance analysis of Floodlight, ONOS, OpenDaylight (ODL) and Ryu controllers is analyzed. A custom network topology is created with Mininet. The ping and iperf tools are also used to evaluate the four controllers based on bandwidth utilization, jitter, packet transmission rate, round-trip time (rtt), and throughput. Our analysis reveals that in terms of jitter, bandwidth utilization, and throughput, ONOS has the best performance. Floodlight has better performance in terms of round-trip time (rtt) and ODL provides better performance in terms of transmission rate.
Authors - Swastika Das Abstract - This paper discusses the role of the UMANG platform in achieving the goal of addressing the digital divide in Indian e-governance. The UMANG platform aggregates nearly 2,000 services across sectors--health, education, and finance--onto a singular mobile-first platform for which it strives to make accessible, transparent, and efficient. Under the Digital India initiative, the UMANG platform was launched in 2017. Despite rapid digitalization in India, especially in cities, its rural pockets lag significantly in terms of internet usage penetration, marking only 37.3% in rural areas, respectively. The present research looks into how the same platform is trying to reduce that gap by providing services in 22 Indian languages, Assisted Mode for those without proper digital literacy, and real-time updates in the furtherance of tracking services. Citizen engagement in the right direction, UMANG has streamlined interactions, minimised bureaucratic delays, and created transparency. Problems, however, are still seated there-like limited digital literacy, security of data, and resistance from some government departments. Finally, the study concludes that with continuous integration enhancements in digital security and wider citizen participation, UMANG can transform governance in India, paving the way towards realising the vision of Digital India.
Authors - D. I. De Silva, S.V. Sangkavi, W. M. K. H. Wije-sundara, L. G. A. T. D. Wijerathne, L. H. Jayawardhane Abstract - This study introduces FlexiMind, an innovative mobile application designed to support children aged 6–10 with specific learning disorders, including dyslexia, dysgraphia, and dyscalculia. By integrating evidence-based instructional strategies and leveraging modern technologies, the application delivers an inclusive and interactive learning environment. The app comprises four core modules: Dyslexia Assessment, Tamil Letter Learning, Math Hands, and Word Recognition & Sentence Construction. These modules employ multisensory approaches, including real-time feedback, gesture-based learning, and machine learning algorithms, to enhance cognitive, linguistic, and mathematical skills. Preliminary findings highlight significant improvements in handwriting accuracy, letter recognition, phonemic awareness, and mathematical comprehension among children using FlexiMind. With its focus on Tamil language support and an adaptive design, FlexiMind addresses the unique needs of Tamil-speaking children while offering scalable solutions for broader educational contexts. This study underscores the potential of technology-driven tools in transforming learning experiences for children with specific learning disorders.
Authors - Arjun Mehra, Arti Devi, Ananya Sharma, Sahil Rana, Shivam Kumar, K V Uday, Varun Dutt Abstract - Virtual reality holds enormous potential for disaster preparedness; yet, little is known about how varying landslide risk levels and environmental elements (day vs night) impact people's physiological and psychological responses to these simulated catastrophes. By utilizing behavioral measures (Euclidean distance around collision, number of collisions, and velocity around collision), this study closes this gap by investigating stress and cognitive responses. Eighty volunteers were divided into four groups at random, and each group was exposed to a distinct set of landslide probabilities under various conditions: low likelihood during the day, high probability during the day, and high probability at night. The findings indicate that perceived risk significantly increased behavioral measurements, independent of time of day. These results demonstrate VR's capacity to improve cognitive engagement and equip participants to handle the psychological difficulties that arise in actual crisis scenarios.
Authors - Akriti Agarwal, Harshvardhan Singh Gahlaut, Annie Jain, Shalini L Abstract - Most common complication of Diabetic mellitus is Diabetic Retinopathy: It causes the lesion to occur upon the retina and affects vision if not diagnosed early it triggers blindness. Diabetic retinopathy should be treated by an early diagnosis to avoid irreversible loss of vision. In addition, the manual diagnosis by ophthalmologists is less efficient and can easily miss the smallest detail that, in some cases, may not be visible to naked human eyes compared to the computer-aided systems. This implies proposing an existing supervised learning strategy for detection of DR from retinal fundus images to a hybrid combination of both deep learning InceptionV3 and ResNet and a machine learning model, namely Random Forest and Support Vector Machine. The model architecture incorporates advanced neural networks fused with classifiers which is further tuned and added up with an attention mechanism ensuring robust and one of the most accurate classification model of DR and non-DR cases. The dataset comprises of 30,000 fundus images which is preprocessed and augmented to improve model performance, hence addressing class imbalance. Additionally, a front-end app with Grad-CAM analysis is developed to classify DR and Non-DR images and visualize where the model focuses during classification.
Authors - Nadia Liz Quispe Siancas, Julian Llanto Verde, Wilder Nina Choquehuayta Abstract - Semantic segmentation of buildings using optical satellite images and deep learning techniques is essential for urban planning and monitoring, especially in suburban areas. In this study, we focused on evaluating the performance of six deep learning models: DeepLabV3 MobileNetV3, DeepLabV3 ResNet50, FCN ResNet50, EfficientNet-B0, ResNet101, and UNET. The dataset was collected from the province of Mariscal C´aceres, specifically in the district of Juanju´ı, located in the department of San Mart´ın, situated in the northeast of Peru. Our analysis revealed varying levels of precision for each model: DeepLabV3 MobileNetV3 achieved 74.14%, DeepLabV3 ResNet50 reached 83.35%, FCN ResNet50 attained 83.56%, EfficientNet-B0 yielded 61.37%, ResNet 101 obtained 63.60%, and UNET demonstrated 74.54%. These results provide insights into the effectiveness of different deep learning architectures for semantic segmentation tasks in suburban environments.
Authors - Ambroise D. K. Houedjissin, Arnaud Ahouandjinou, Manhougbe Probus A. F. KIKI, Francois Xavier Ametepe, Kokou M. Assogba Abstract - Image motion deblurring is an important issue in computer vision applications which encounter challenges like motion blur caused by camera shake, fast motion or irregular deformation of agricultural living things during image acquisition. Images acquired by UAV-embedded cameras are often blurred and usually error-prone in precision agriculture. So, image deblurring in applications such as plant phenotyping recognition, crop pests and diseases detection or animal behavior analysis is a great challenge. The main purpose of this paper is to carry out both a bibliometric analysis to assess the current research trends on UAV image motion deblurring with a brief survey of the main image motion deblurring techniques in agriculture. So, we used the Scopus database and 2138 articles were retrieved. This dataset has then been analyzed using a bibliometric tool. According to results, the most impactful authors have 53 and 46 publications respectively. Remote Sensing is the most impactful journal with an h-index of 49 and 285 published articles whereas China is the country with the most impactful production and the most cited document, indicating its considerable influence in this area of research. Results from the short survey indicate that further research is needed to develop more robust and efficient motion deblurring techniques tailored to the specific challenges of UAV imagery in precision agriculture.
Authors - Mariam Basim Al-Najjar, Khalil H. Sayidmarie Abstract - This contribution investigates a proposed Frequency Selective Surfaces (FSS) that can be reconfigured using light-dependent resistor LDR. The unit cell of the FSS comprises a split square ring equipped with a single LDR placed at its gap. The FSS is built on the FR4 substrate of 40X40 mm dimensions, and ring size of 29 x29 mm to serve the WLAN application of 2.45 GHz frequency. When the LDR is adequately illuminated it exhibits a small resistance, and the ring behaves as a closed one, while in the dark condition, the resistance is high and the ring acts as a split ring. Therefore, the FSS works as a bandpass filter when illuminated, and as a bandstop filter without illumination. The LDR doesn’t need biasing wires that usually interfere with the structure of the FSS.
Authors - Moubaric Kabore, Abdoulaye Sere, Vini Yves Bernadin Loyara Abstract - This paper deals with Bayesian approach in Data Research in GIS database through artificial Intelligence (AI) modules, reading the best bayesian probability before returning the data requested, denoted AI4DB. The proposed method combines meshing techniques and the map-reduce algorithm with Bayesian approach to obtain a smart GIS database to reduce the execution time. According to the values of the Bayesian probability, the nearest sites of any position resulting of the user requests, are extracted speedily from the database using the map reduce framework. The execution time is less than the time for the case of the classical method, based only on a parallelism search without a probability. Only a map function with the best bayesian probability for the data in entry, executes entirely its instruction.
Authors - Denis Vasiliev, Rodney Stevens, Lennart Bornmalm Abstract - The idea of smart cities is becoming increasingly popular. Technology alone, however, is not sufficient for addressing the challenges that modern cities face. Pressures stemming from pollution, stress, and changing environmental conditions can ruin the lives of city dwellers, putting enormous pressure on public finance to address or mitigate consequences of the issues. Application of Nature-based Solutions could address multiple societal and environmental issues common to modern cities. Furthermore, the solutions can immensely benefit from integration with modern technologies. In fact, modern technologies can enhance the implementation, monitoring, and scalability of Nature-based Solutions. This makes a strong case for the application of Nature-based Solutions in modern urban environments that aspire to promote technology and become smart cities. Integration of the solutions into smart cities, however, is not a trivial task and requires a holistic approach to city planning and deep understanding of the ways to do so. Justification of the associated costs requires thorough understanding of the benefits, including the values that may be easily overlooked. Thus, in this study, we apply a conceptual research approach to explore how Nature-based Solutions can be integrated into Smart Cities, what are key benefits of the approach, and how this integration can address significant challenges in urban environments.
Authors - Victor Sineglazov, Andrew Sheruda Abstract - In this paper, a new hybrid segmentation method based on SSL (semi-supervised learning) was developed for samples with image sequences, not all of which were labeled. Thus, this method can find application in areas where labeling is expensive or requires a certain specialist, such as in medicine. The developed method was evaluated on a sample of echocardiography images of patients with infective endocarditis in the context of a real-world task of segmenting heart valve anomalies. As a result, the accuracy gain compared to supervised learning is 5% in the IOU metric, while with other SSL methods it is on average 3%.
Authors - Ervin Mikhail G. Garcia, Zara Naomi S. Inocencio, Ronnel Christian B. Langit, Paul James L. Perez, Harold Russell P. Visperas, Mary Jane C. Samonte Abstract - SHair is an innovative and very useful web-based tool that is made to make the process of donating hair easier. Its primary objective is to aid cancer patients in regaining self-confidence. SHair empowers hair donation by providing a user-friendly site that is safe for anybody wishing to give their hair. The main goal of the website is to have a substantial impact on the well-being of cancer patients by facilitating the connection between persons who express the intention to contribute their hair and those who need facial hair transplants. Individuals must possess this quality to foster a comprehensive comprehension of one another and collectives must possess it to increase their resilience. People stress how easy hair renewal is because it can bring donors and patients together, which is good for patients' mental health. SHair also makes sure that the processing and distribution of given hair can happen, which helps with efforts that focus on the happiness and well-being of cancer patients.
Authors - Denis Vasiliev, Rodney Stevens, Lennart Bornmalm Abstract - Implementation of Nature-based Solutions is becoming increasingly widespread. The solutions are intended to simultaneously address environmental, social and economic challenges. This approach is intended to foster sustainable development. However, mere use of nature for addressing specific problems does not necessarily result in simultaneous delivery of value in all three sustainability areas. To make sure that Nature-based Solutions serve both nature and society and deliver maximal benefits, a holistic approach to their implementation is essential. Implementing this approach is, however, not a trivial goal. It requires joint consideration of environmental, social and economic factors at a range of spatial and temporal scales. Furthermore, collaboration among multiple diverse stakeholders in the context of rapidly changing systems is essential. This often involves processing large volumes of data and can be very labor intensive. As a result, the costs of such projects may be overly high, hindering their implementation. The emerging technology of Generative Artificial Intelligence can greatly facilitate the process, bringing down the costs and increasing speed and feasibility of the project implementation. However, lack of awareness and understanding of how such tools can be used in Nature-based Solutions projects may result in missing these opportunities. Thus, this paper explores potential applications of Generative Artificial Intelligence tools in pro-jects involving Nature-based Solutions.
Authors - Vikas Shah, Travis Rice, Aarav Shah, Aarush Shah Abstract - Artificial intelligence (AI) empowered the transformation of decision-making processes for lending services, delivering improved efficiency, scalability, and precision. However, the adoption of AI in loan origination and application processing has introduced significant ethical challenges, including recognizing biases, fairness, transparency, reliability, and accountability. The paper identifies primary challenges in automated lending services (ALS), AI-enabled decision-making, and the deriving of AI governance practices. This paper proposes a deterministic framework (DF) designed to systematically identify and address the ethical dimensions of AI in lending services. The DF spans comprehensive mechanisms encompassing data collection, preprocessing, model development, deployment, monitoring, and governance. Core ethical dimensions of explainability, transparency, and equitable outcomes are recognized within the governance lifecycle stages. The DF continuously integrates novel industry regulatory standards and governance methodologies to identify, measure, and mitigate ethical risks, ensuring operational efficiency and adherence to ethical principles. This research provides a structured approach grounded in deterministic methods, enabling measurable, repeatable, and auditable business processes to enable trust and accountability in AI-driven ALS. An empirical case study focusing on ALS for students and their families is presented to evaluate the DF's applicability and effectiveness. The findings provide actionable insights for financial institutions, policymakers, and technologists seeking to implement ethical AI practices, strengthen risk management, and deliver equitable and accountable lending services to diverse populations.
Authors - Oleksandr Kurbatov, Lasha Antadze, Ameen Soleimani, Kyrylo Riabov, Artem Sdobnov Abstract - This article proposes an extension for privacy-preserving applications to introduce sanctions or prohibition lists. When initiating a particular action, the user can prove, in addition to the application logic, that they are not part of the sanctions lists (one or more) without compromising sensitive data. We will show how this solution can be integrated into applications, using the example of extending Freedom Tool (a voting solution based on biometric passports). We will also consider ways to manage these lists, versioning principles, configuring the filter data set, combining different lists, and using the described method in other privacy-preserving applications.
Authors - Asmaa Berdigh, Kenza Oufaska, Khalid El Yassini Abstract - The inclusion of wireless communication technologies in the car industry has drastically reshaped it over the last two decades. This evolution began with the integration of Bluetooth and Smart Key technology in 1998 and has since progressed to the application of wireless communication in the cell monitoring controller of battery management systems. The objective of this study is to conduct an SMS to evaluate the research investigating wireless communication technologies used in the in-vehicle network. We adopt the Systematic Mapping Study (SMS) approach, a rigorously defined research methodology with roots in the medical and software engineering, using defined criteria to filter out the research contributions stored in both Scopus and GoogleScholar databases over the last twenty years. We synthesize the resulting data and produce this article. This work aims to organize information from studies published within this disciplinary field over the past two decades, presenting them in a systematic map form, and discussing the results and their implications for future research, concluding by a visual display of which automotive domains have the largest wireless communication. The SMS provides a clear and comprehensive picture drawn from precise questions. The derived outcomes could hold significance for both researchers and industry professionals considering the integration of wireless communication technologies within in-vehicle networks. Despite the substantial body of research identified over the past 20 years on wireless technologies, only a limited number of studies have specifically focused on the In-Vehicle Networks.
Authors - Esther Endjala, Hanifa Abdullah, Mathias Mujinga Abstract - This paper explores the theoretical and strategic foundations for cultivating a cybersecurity culture within telecommunications institutions. Drawing on established behavioral theories Social Cognitive Theory (SCT), Protection Motivation Theory (PMT), Theory of Planned Behavior (TPB), and Technology Acceptance Model (TAM) it examines the opportunities for enhancing cybersecurity awareness and transforming employee behaviors into a resilient human firewall. The paper synthesizes existing literature to highlight the role of leadership, employee engagement, training, collaboration, and recognition in fostering a cybersecurity culture. The review further identifies gaps and limitations in the current approaches, proposing a conceptual foundation for developing an effective cybersecurity culture framework tailored to telecommunications institutions. Appropriate cybersecurity culture is essential in developing the entity and helps protect organizational assets such as data, networks, and systems when technical defenses are quite significant. The section takes into consideration the theoretical aspect of cybersecurity culture and comes out with a derived underlying framework that incorporates aspects like the Social Cognitive Theory, Protection Motivation Theory, Theory of Planned Behavior, and Technology Acceptance Model. Creating a strong cybersecurity culture faces several significant challenges, including resistance to change, limited resources, and regulatory hurdles. The proposed framework emphasizes the importance of top management commitment, employee involvement, ongoing training, and interdepartmental collaboration as vital components for cultivating this culture. Organizations should address these challenges to successfully establish an effective cybersecurity culture. By integrating these elements, cybersecurity can become a fundamental organizational value, enhancing awareness, compliance, and employee engagement. This paper establishes the groundwork for further research on cybersecurity culture and outlines key steps to strengthen organizational resilience and ensure a safe digital environment.
Authors - Amna Altaf, Zeashan Khan, Adeel Mehmood, Jamshed Iqbal Abstract - Advancements in Artificial intelligence (AI) and robotics call for prioritising research in education and pedagogy in these domains including teachers’ training to practice emerging learning and teaching strategies. This paper explores the model of teachers’ training by using CDIO (Conceiving, Designing, Implementing and Operation) framework as a guide and a robotic platform as an example in AI education. In the pilot study, nine workshop sessions were designed and organised for a group of five teachers introducing them to robotics-led delivery of AI content using a mobile robot ‘Duckiebot’. The prominent workshop contents include robot vision, object detection, state estimation and localisation, task planning and reinforcement learning. Preliminary results in the form of feedback from the workshop participants demonstrated that the teaching model presented in this study made a promising contribution in terms of improving teachers’ intellectual and pedagogical skills as well as their confidence in achieving learning outcomes. The presented CDI-based robotics-led AI teaching model adds to the dialogue on innovative AI and engineering education methods. It is anticipated that wider dissemination of the findings in this research will lay the groundwork for a larger educational impact.
Authors - Swayamjit Saha, Garga Chatterjee, Kuntal Ghosh Abstract - Visualizing data plays a pivotal role in portraying important scientific information. Hence, visualization techniques aid in displaying relevant graphical interpretations from the varied structures of data, which is found otherwise. In this paper, we explore the COVID-19 pandemic influence trends in the subcontinent of India in the context of how far the infection rate spiked in the year 2021 and how the public health division of the country India has helped to curb the spread of the novel virus by installing vaccination centers and administering vaccine doses to the population across the diaspora of the country. The paper contributes to the empirical study of understanding the impact caused by the novel virus to the country by doing extensive explanatory data analysis of the data collected from MoHFW, India. Our work contributes to the understanding that data visualization is prime in understanding public health problems and beyond and taking necessary measures to curb the existing pandemic.
Authors - Louay Al Nuaimy, Hazem Migdady, Mahammad Mastan Abstract - Accurate time series forecasting is vital in areas such as finance, weather prediction, and energy management. Traditional forecasting methods often struggle to effectively model the intricate patterns and nonlinearities present in real-world data. This study proposes the feedback-matching neural network (FMNN), a deep learning model that evolves from the feedback-matching algorithm (FMA). By embedding the core concepts of FMA into a neural network structure, the FMNN can recognize and match historical patterns in time series data, leading to more accurate predictions. Extensive experiments reveal that the FMNN outperforms several conventional statistical models and modern neural networks in terms of forecasting accuracy, as evaluated by the weighted absolute percentage error (WAPE). The FMNN enhances prediction accuracy by offering a sophisticated method for identifying and leveraging repeating trends within the data.
Authors - Alexandre Evain, Redouane Khemmar, Mathieu Orzalesi, Sofiane Ahmedali Abstract - This paper presents MYv7 (Mono-YOLOv7), an adaptation of the YOLOv7 architecture tailored specifically for 3D monocular object detection. Rather than competing with specialized 3D methods, we demonstrate the efficacy of enhancing 3D monocular detection using improved 2D object detection algorithms. We showcase how improvements in 2D algorithms can enhance 3D predictions, presenting MYv7’s twofold advantage over a YOLOv5-based method: increased speed and accuracy. These gains are crucial for efficient operation on embedded systems with limited computational resources. Our results highlight the potential of using advancements in 2D detection methods to significantly improve 3D monocular object recognition, opening new avenues for real-world applications.
Authors - Ali Belgacem, Abbas BRADAI Abstract - This summary research paper provides a comprehensive overview of Vehicle-to-Everything (V2X) communications, including various communication types and the roles of base stations. It covers resource allocation techniques and beamforming for high-quality connectivity and addresses energy efficiency optimization metrics. The paper also discusses artificial intelligence methods and their integration to optimize these systems and enhance performance. This research serves as a valuable guide for those aiming to contribute to advancements in 6G technologies for efficient vehicular communications.
Authors - Iaroslav Omelianenko Abstract - Neuroevolution algorithms need to evaluate at the end of each epoch the fitness scores of each organism in a population of solvers within the problem space where a solution is sought. This evaluation often involves running complex environmental simulations, which can significantly slow down the training speed if done sequentially. This work proposes a solution that utilizes the inherent capabilities of the Go programming language to run complex simulations in local parallel processes (routines). The efficiency of this proposed solution is compared to sequential evaluation using two classic reinforcement learning experiments, specifically single and double pole balancing. Direct comparisons indicate that the proposed solution is up to five times faster than the sequential approach when complex environmental simulations are required for objective function evaluation.
Authors - Kayode Oyetade, Anneke Harmse, Tranos Zuva Abstract - The introduction of AI in education has the potential to address educational inequalities and improve outcomes, but it also raises concerns about cultural responsiveness and biases in AI systems. To ensure equitable outcomes, strategies are needed to address these concerns. However, there is a limited understanding of effective approaches for promoting cultural sensitivity and equity in AI-powered educational content, highlighting a significant gap in existing literature. Using literature review methodology, this study aims to explore strategies to enhance cultural sensitivity and mitigate biases in AI-powered educational content, focusing on the intersection of technology and cultural diversity. By addressing concerns related to bias in AI algorithms, our findings highlight the importance of cultural inclusivity in AI-driven educational tools and advocates for proactive measures to embed cultural responsiveness into AI development processes. This review contributes to the discussion on responsibly integrating AI in education, promoting educational environments that value and reflect diverse cultural identities, and promoting a more inclusive educational experience globally.
Authors - Eduardo Puraivan, Patricio Tapia, Miguel Rodriguez, Steffanie Kloss, Connie Cofre-Morales, Pablo Ormeno-Arriagada, Karina Huencho-Iturra Abstract - This study provides empirical evidence on the effectiveness of large language models (LLMs), particularly ChatGPT, for automating the identification and analysis of cognitive demand levels in reading comprehension assessment tasks, using Barret’s Taxonomy. The manual classification of these tasks, even for experienced teachers, poses challenges due to their complexity and the time required. To address this issue, a three-step methodology was developed: selection of reading comprehension activities, automatic classification by ChatGPT, and comparison with the classifications from a group of experts. The experiment included 25 questions based on four readings extracted from a fourth-grade teacher’s guide for primary education. The results showed variability in the agreement between ChatGPT’s classifications and those of the experts: 77% in Activity 1, 50% in Activity 2, 52% in Activity 3, and 67% in Activity 4. At the question level, agreements ranged from 0% to 100%, highlighting discrepancies even among the evaluators, which underscores the inherent subjectivity of the task. Despite these divergences, the results emphasize the potential of LLMs to streamline the classification of educational activities on a large scale and the need to continue refining these models to enhance their performance in more complex pedagogical tasks.
Authors - Larissa de Lima, Priscila Capriles, Nathan Oliveira Abstract - This paper explores the use of machine learning (ML) with various physical, chemical, and biological parameter combinations to predict water quality, focusing on the Water Quality Index (WQI). We assess the performance of several regression algorithms across five different data combinations and examine the impact of inference and class balancing techniques on model outcomes. Our analysis reveals that LightGBM achieved the highest accuracy in WQI regression at 93%. This research introduces a novel approach to calculatingWQI by automating the traditional manual and complex parameter collection and calculation process. By streamlining water quality monitoring, our ML-based method offers a more efficient and innovative solution. Additionally, the study provides practical insights into handling data scarcity and using statistical inference for skewed sampling distributions.
Authors - Atiqur Rehman, Karim Elia Fraoua, Amos David Abstract - Blockchain technology has the potential to revolutionize traditional financial systems by offering decentralized, secure, and transparent transaction processing. This research focuses on developing a blockchain-based investment platform that integrates the Practical Byzantine Fault Tolerance (PBFT) consensus algorithm. The platform addresses critical issues faced by traditional investment systems, such as security vulnerabilities, inefficiencies, and the lack of transparency. By incorporating smart contracts, the platform automates key investment processes such as order placement and settlement, significantly reducing reliance on intermediaries. The system is designed to process transactions in real-time, offering high throughput and low latency, ensuring a smooth user experience. Extensive testing, including unit testing, integration testing, and security testing, has been conducted to verify the platform’s performance, scalability, and robustness. Security measures such as end-to-end encryption and multi-factor authentication (MFA) further enhance the platform's reliability. While PBFT ensures fast and secure consensus, the scalability of the algorithm may present challenges as the platform grows. Future work will focus on optimizing the PBFT system, exploring hybrid blockchain models, and integrating the platform with external financial systems to extend its applicability. The research demonstrates that blockchain, when combined with PBFT, can create a secure, efficient, and scalable solution for managing investment transactions.
Authors - Amira Jemaa, Adnan Rashid, Sofiene Tahar Abstract - Explainable Artificial Intelligence (XAI) plays an important role in improving the transparency and reliability of complex machine learning models, especially in critical domains such as cybersecurity. Despite the prevalence of heuristic interpretation methods such as SHAP and LIME, these techniques often lack formal guarantees and may produce inconsistent local explanations. To fulfill this need, few tools have emerged that use formal methods to provide formal explanations. Among these, XReason uses a SAT solver to generate formal instance-level explanation for XGBoost models. In this paper, we extend the XReason tool to support LightGBM models as well as class-level explanations. Additionally, we implement a mechanism to generate and detect adversarial examples in XReason. We evaluate the efficiency and accuracy of our approach on the CICIDS-2017 dataset, a widely used benchmark for detecting network attacks.
Authors - Ayush Verma, Krisha Patel, Hardikkumar Jayswal, Nilesh Dubey, Dipika Damodar Abstract - Insurance fraud significantly undermines the financial stability of the insurance industry, resulting in billions of dollars lost annually due to fraudulent claims across sectors like healthcare, auto, and property insurance. This paper proposes a robust methodology for detecting insurance fraud through the strategic implementation of ensemble machine learning algorithms, specifically XGBoost and Random Forest. By analyzing extensive datasets that include policyholder demographics, claim histories, and risk factors, we develop predictive models that accurately identify fraudulent activities while minimizing false positives. The effectiveness of our approach is supported by a comprehensive literature review highlighting the performance of various machine learning models in fraud detection, as well as our application of preprocessing techniques and feature selection to enhance model accuracy. Our findings indicate that the integration of advanced AI and ML technologies can revolutionize fraud detection in the insurance sector, offering a more secure and efficient environment for both insurers and policyholders.
Authors - Honorato Ccalli Pacco Abstract - Mushrooms are important in human nutrition due to their nutritional value in terms of protein, vitamin and mineral content. The volume of mushroom cultivation is currently increasing. This research focuses in the modeling and simulation of temperature, humidity and irrigation time controlling in mushroom cultivation in a protected environment. Using fuzzy logic in an intelligent system that allows process control and the LabVIEW software that facilitates graphic programming by means of virtual instruments, the irrigation time program was obtained as an output variable or an input variable-dependent response (input variables were temperature and humidity) in the intelligent system. The result was a program that shows how to act in different situations of temperature and humidity in mushroom cultivation in a protected environment. The fuzzy logic program in LabVIEW allowed the simulation of the system in terms of irrigation time in mushroom cultivation in a protected environment to achieve the expected results. In experimental results it can be observed that at low temperatures (15 °C) and low humidity (35%) the irrigation time is an average value (44.03). With the high temperature (35°C) and high humidity (95%) in the protected environment, the irrigation time will be with a low value (22.32). And it could be simulated by varying the input variables.
Authors - Md Asif Ahmed, Md Sadatuzzaman Saagoto, Farhan Mahbub, Protik Barua Abstract - Graphene is emerging as a strong candidate for qubit applications in quantum computing due to its unique properties and recent technological advancements. Graphene, as a two-dimensional material with high carrier mobility and distinct electron behavior, presents potential advantages for qubit applications. However, its zero-band-gap nature poses challenges for stable quantum states, requiring innovative solutions to realize its full potential in quantum computing. This review explores graphene's unique properties and their impact on qubit design, analyzing recent breakthroughs aimed at overcoming its inherent limitations, such as techniques for band-gap modulation and substrate engineering. We delve into various methodologies, including the integration of hexagonal boron nitride (hBN) and electrostatic gating, to enhance graphene's performance for quantum applications. Additionally, we examine the integration of graphene with other 2D materials and hybrid structures to achieve tunable quantum properties, essential for advancing scalable quantum architectures. This comprehensive analysis aims to bridge the material science challenges with the practical demands of qubit technology, providing a roadmap for leveraging graphene in future quantum systems.
Authors - Kobus Kemp, Lynette Drevin, Magda Huisman Abstract - This paper reports on a study that explores and addresses security challenges in the development of enterprise mobile applications (EMAs). Despite the growing prevalence of mobile applications, security considerations are often overlooked or insufficiently addressed in mobile application software development methodologies. This gap highlights the need to incorporate security training into software developer education. The study used a literature review of software development methodologies (SDMs) and security practices, complemented by case studies involving interviews with industry experts on EMA development processes. Using thematic and cross-case analyses, the study produced a framework designed to guide the integration of security measures into EMA development. Findings revealed a limited emphasis on security aspects in current mobile application development practices. Consequently, a partial framework is presented in this paper, detailing key security considerations and countermeasures specific to EMA development. This research contributes to the discipline by offering developers guidelines to enhance security in EMAs, emphasizing the importance of integrating these practices into developer training programs.
Authors - Marisol Roldan-Palacios, Aurelio Lopez-Lopez Abstract - Limited available data becomes a critical problem in specific machine learning tasks, where approaches, such as large language models, turn impractical. Reaching solutions in such situations requires alternative methods, especially whether the object of study contributes to data scarcity while preventing using techniques such as data augmentation. This scenario led us to formulate the research question on how to squeeze hidden information from small data. In this work, we propose a data processing and evaluation technique to increase information extraction from scarce data. Attributes expressed as trajectories are further pair-related by proximity and assessed by customary learning algorithms. The efficacy of the proposed approach is tested and validated in language samples from individuals affected by a brain injury. Direct classification on raw and normalized data from three sets of lexical attributes works as a baseline. Here, we report two learning algorithms out of five explored, showing consistent behavior and demonstrating satisfactory discriminatory capabilities of the approach in most cases, with encouraging percentages of improvement in terms of f1-measure. We are in the process of testing the approach in language data sets of syntactic and fluency features, but other fields can take advantage of the technique.
Authors - Khalaf Elwadya, Khosro Salmani Abstract - The evolution of social media platforms has led to the creation of a dynamic ecosystem, abundant in user-generated content. This, however, has also resulted in raising concerns about data privacy. Beyond potential threats like scammers exploiting freely shared information on social media for spying, financial scams, social media companies can leverage user data to sell targeted advertising. Addressing these issues necessitates heightened user awareness. Hence, this paper first examines the privacy policies of major social media platforms including TikTok, Twitter, Facebook, Instagram, and LinkedIn, providing a comparative analysis of their data storage practices, utilization of user information, account verification requirements, and default privacy settings. Next, we undertake an extensive survey utilizing the data gathered in the initial phase to evaluate user awareness regarding the utilization of their data, highlighting a notable gap between policy stipulations and user expectations. We conclude with four recommendations based on our findings to help social media companies refine their privacy policies, promoting more comprehensible guidelines.
Authors - Muhammad Sufyan Akbar, Guo Jiandong, Muhammad Irfan Khan, Asif Iqbal, Salim Abstract - This paper introduces a deep learning-based approach for point cloud classification, leveraging the PointNet architecture to optimize 3D object recognition. The method effectively addresses the challenges associated with unordered point cloud data, achieving superior classification performance with 92% accuracy, 91% precision and recall, 89% F1-score, and 96% sensitivity and specificity. The proposed model captures spatial features directly from raw point cloud data, demonstrating its potential for real-world applications in 3D object recognition and scene understanding. Comprehensive experiments on benchmark datasets validate the model’s effectiveness in classifying complex 3D structures, highlighting its robustness and efficiency. Future research will focus on advancing feature extraction techniques and refining the model to enhance classification performance under more demanding conditions.
Authors - Timothy T Adeliyi, Funmi Adebesin, Edidiong R Umoh Abstract - Unemployment remains a persistent challenge for both developed and developing countries, leading to the underutilisation of resources. Many Sub-Saharan countries experience high unemployment rates due to weak economic indicators. This study adopts a data-driven approach to investigate women's unemployment in Sub-Saharan Africa, with a focus on the factors contributing to employment disparities and advancing gender equality, for Sustainable Development Goal 5 (SDG 5). Using Multiple Correspondence Analysis (MCA), the research identifies and analyses key factors that contributes to the high unemployment rates among women in the region. The findings reveal significant links between unemployment and factors such as age, region, and wealth index. By shedding light on these disparities, the study offers a comprehensive understanding of the structural barriers faced by women in the labour market. The results emphasise the need for specific policies and interventions to combat gender inequality and boost women's economic participation to achieve SDG 5. This research enriches the broader dialogue on sustainable development and gender equality, providing crucial insights for policymakers and stakeholders working towards more inclusive labour markets in Sub-Saharan Africa.
Authors - Salimah Saeid, Tahani Almabruk, Muetaz Abdulsamad Abstract - The diagnosis of ovarian tumors remains a challenging task due to the inherent variability and complexity of imaging data. This study evaluates the efficacy of transfer learning and fine-tuning techniques in convolutional neural net-works to enhance the classification accuracy of ovarian tumors in ultrasound images. The performance of YOLOv8 and VGG16 models were compared, including a modified VGG16 architecture optimized for this application. YOLOv8 models were evaluated both from scratch and with pre-trained weights, while VGG16 was employed for feature extraction and fine-tuning. The Modified VGG16 outperformed all other models, achieving the highest classification accuracy (%90) and the shortest training time (8.63 hours). Advanced data augmentation strategies and architectural optimizations effectively addressed issues such as class imbalance and overfitting. These results highlight the potential of customized CNN architectures and transfer learning to improve diagnostic accuracy and efficiency, advancing the development of reliable tools for ovarian tumor classification in clinical imaging.
Authors - Mohammad Anwar Rahman, Rafiul Hassan Abstract - Accurate prediction of lithiumion batteries' state of health (SOH) is crucial for preventing catastrophic system failures. This study investigates the application of ensemble modeling to characterize capacity degradation and fore-cast remaining charge-discharge cycles. Leveraging NASA's battery charge/discharge dataset, we developed and compared feed-forward neural network (FNN) and random forest (RF) regression models. To enhance predictive accuracy, we constructed an ensemble model that combines the strengths of both individual models. A key aspect of our methodology was the accurate evaluation of model performance across different battery datasets. Rather than using a single dataset for training and testing, we adopted a cross-validation approach to assess model generalization capabilities. This strategy allowed us to identify the robustness of the models for predicting SOH and estimating remaining battery life. Our findings indicate comparable performance among the FNN, RF, and ensemble models. While all models demonstrated effective capacity degradation prediction, the ensemble model exhibited slightly superior performance in a few scenarios. These findings emphasize the advantages of ensemble modeling in enhancing the accuracy and reliability of lithiumion battery prognostics.
Thursday February 20, 2025 4:15pm - 5:45pm GMT
Virtual Room DLondon, United Kingdom
Authors - Dattatraya Adane, Lakshya Agrawal, Shradha Wangota, Sharvari Inamdar Abstract - In order to overcome issues with traditional voting, such as voter impersonation, booth capturing, and logistical inefficiencies, this study proposes a biometric voting method. The technology guarantees that only authorised individuals can cast ballots while maintaining anonymity by combining fingerprint authentication with secure digital platforms. It features a web-based interface for election managers to manage candidates, track votes, and display real-time results, as well as a mobile app for voter registration and remote voting, improving accessibility. The solution lowers costs while increasing security, transparency, and engagement by utilising technologies like Firebase Firestore, the Mantra MFS100 fingerprint scanner, and QR code integration. This essay examines its design, use, and effects on modernising elections to promote efficiency, inclusivity, and trust.
