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 - Koichi Akashi, Hibiki Ito, Atsuko Yamashita, Katsuhiko Murakami, Sayaka Matsumoto, Kunihiko Takamatsu, Tetsuhiro Gozu Abstract - In recent times, a ground-breaking approach termed abridgement has been advocated for assessing reading comprehension of students in a distinct manner. The operation requires them to shorten the size of the given passage by only deleting the words or characters in it, while not permitting adding, paraphrasing, or swapping any of them. Thanks to its simple operational property, an efficient computational marking scheme has been invented employing the technique of dynamic programming (DP) by the following studies. These endeavors enabled further analyses to proceed, allowing for an ensuing research of reflections about teachings of abridgement collected from students using co-occurrence networks, to give an instance. Furthermore, evolution of this educational approach has led the researchers to suggest its unprecedented application to detect the presence of students who have potential difficulty with learning or specific tasks at an early stage, which is expected to contribute to the reduction of dropout rate in the long run. To make this happen, this research adopted the idea of utilizing large language models (LLMs), specifically Bidirectional Encoder Representations from Transformers (BERT) developed by researchers at Google in 2018, to automatically quantify the confidence levels of their understanding based on the technique of sentiment analysis of collected reflections. Combining grades calculated from DP-based algorithm with LLM newly invited to the research of abridgement, certain criteria have been established to issue warnings to identify those who are experiencing challenges early on.
Authors - Joao Bachiega Jr, Breno Costa, Leonardo R. Carvalho, Aleteia Araujo, Rajkumar Buyya Abstract - The fog computing paradigm allows for the distribution of computing resources and services at the edge of the network, close to end users, complementing cloud computing. Due to the dynamicity of fog computing environments, resource discovery is a key process that aims to find new computational resources that are available to integrate into it. These resources compose fog nodes, devices considering computational capabilities (such as CPU, memory, and disk) and behavioral characteristics (such as availability, scalability, and mobility). Performing an optimized resource discovery with all those attributes is still a challenge. This article proposes an efficient approach to resource discovery in fog computing that considers the computational capability and behavioral characteristics to select fog nodes. The results show that it is at least 33% more efficient than a similar solution found in the literature.
Authors - Kostadin Nevrokopliev, Silvia Gaftandzieva, Svetoslav Enkov Abstract - Every organization needs business intelligence reports and analytics to help it make informed decisions. This creates the need to develop a framework for composing business intelligence reports and analytics. This article describes the structure of a software framework that allows reports to be grouped by given fields and the data to be aggregated. The reports are composed in a way that allows a broader view of the data, which helps managers in their decision-making process. Its flexible and versatile structure allows reports to be customized to fit the specific needs of a given organization. The paper discusses sample reports developed using the framework and shows how they help higher education institutions to manage their activities effectively.
Authors - Quang-Vinh Dang Abstract - Product retrieval in e-commerce systems has traditionally relied on text-based matching between user queries and product descriptions. While recent advances have introduced image-based search capabilities leveraging deep learning techniques, existing systems typically operate in isolation, processing either textual or visual queries independently. However, contemporary user behavior increasingly demonstrates the need for multi-modal search capabilities, particularly as smartphones enable users to seamlessly combine photographic content with textual descriptions in their product searches. This paper presents a novel multimodal retrieval augmented generation (RAG) framework that unifies text and image inputs for enhanced product discovery. Our approach addresses the limitations of conventional single-modality systems by simultaneously processing and correlating both visual and textual features. By leveraging the complementary nature of these modalities, our system achieves more nuanced and contextually aware product matching. Experimental results demonstrate that our multi-modal RAG framework significantly improves search accuracy and relevance compared to traditional single-modality approaches. Furthermore, user studies indicate enhanced satisfaction and reduced search friction, suggesting meaningful improvements to the e-commerce user experience. Our findings contribute to the growing body of research on multi-modal information retrieval and offer practical insights for implementing more sophisticated product search systems in commercial applications.
Authors - Nur Anneliza Abd Latip, Hanita Hanim Ismail, Harwati Hashim, Wardatul Akmam Din Abstract - Textbook role in English language education is imperative in providing curriculum structure, standardising instruction, and maintaining the quality of teaching. Often it is an efficient material for teachers as it is readily available and reliable. Nonetheless, the one-size-fits-all material may not reflect real life language outcome. In reading section of textbook, the passages are simplified, adapted and inauthentic. In a class geared towards high stake reading examination, textbook is needed as it is mirroring language test format, making it a mock test situation. This research exposed students in tackling reading class to texts from periodical literature and explored them using an online whiteboard. The research is not striving to replace textbook, rather put forwards materials that provide learners with opportunity to have an active role in directing their own cognitive resources in reading. The study aims to investigate whether the intervention of using these materials have an effect towards reading achievement. A quasi-experimental design was applied to see quantitative evidence of reading marks. The participants were pre-university students studying at Universiti Malaysia Sabah, one of the public institutions in Malaysia. The findings show that students who are using the periodical literature and online whiteboard revealed significant changes and higher marks of reading achievement compared to the group of students who are only using textbook. The study is hoped to supplement reading class with relevant materials of authentic text and current technology.
Authors - Makoto Hirano, Kayoko Yamamoto Abstract - The purposes of tourism have been becoming diversified in recent years, and a form of travel known as food tourism is becoming increasingly popular. However, little research has been conducted on systems that support food tourism. Against such a backdrop, the present study aims to design, develop, operate and evaluate a food tourism support system that is supported to decide on restaurants for lunch and dinner, tourism spots to visit along the way, and routes to visit these destinations. The system comprises an original tourism plan creation system, web geographic information systems (Web-GIS) and web-augmented realty (Web-AR). In the present study, a location-based Web-AR system is developed. The system was operated for 30 days from December 22, 2023 to January 20, 2024, in Central Yokohama City of Kanagawa Prefecture, Japan. Total number of users was 50 and 20 tourism plans were created during the operation period. Based on the evaluation results, it is clear that the principal functions and the overall system were highly evaluated, regardless of food tourism experience or advance creation of tourism plan. Furthermore, it is evident that there was a high number of visits to the pages for most of the principal functions, and the system was used in a manner consistent with the purpose of the present study.
Authors - Mithil Mistry, Hasti Vakani, Hardikkumar Jayswal, Nilesh Dubey, Mann Patel, Jai Mehtani, Dipika Damodar, Ayush kariya Abstract - This research explores the integration of advanced deep learning techniques for automated pothole and speed bump detection, highlighting various methodologies from recent literature. A systematic review reveals that models utilizing Convolutional Neural Networks (CNNs), including YOLOv3, VGG16, and EfficientNetB0, have achieved impressive accuracy rates in real-time road surface monitoring. In particular, the EfficientNetB0 model was finetuned using a comprehensive dataset comprising 400 annotated images of potholes and speed bumps, collected under diverse environmental conditions. The model achieved a validation accuracy of 91.91%, demonstrating robust performance in identifying road anomalies. Notably, the implementation of advanced data augmentation and regularization techniques, such as dropout and L2 regularization, contributed to preventing overfitting and enhancing generalization across varying contexts. This study underscores the potential of deep learning frameworks in improving road safety and maintenance efficiency, paving the way for future enhancements, including dataset expansion and real-time application integration.
Authors - Ishaan Bhattacharjee, Pranav H P, Harish Satheesh, Disha Jain, Bhaskarjyoti Das Abstract - Satirical content is notoriously difficult to detect, even humans often struggle to discern satire from genuine news. While significant strides have been made in computationally modeling textual satire using supervised learning, the challenge of detecting satire in multimodal content—combining both text and images—remains largely unexplored. In our research, we aim to address this gap by leveraging existing frameworks and tools to detect and differentiate multimodal satire from true news content. Satire builds on two key factors, i.e., knowledge and incongruity. Knowledge has two parts, i.e., local knowledge that is resident in image and text and global contextual knowledge that is not part of the content. Incongruity typically occurs between the first and second parts of the text. In this work, we present a three-step framework. First, we investigate multimodal frameworks such as BLIP, relying on its global knowledge without explicitly modeling the incongruity. Second, we attempt to model incongruity by focusing on the semantic gap between two parts of the text content while using a large language model in knowledge enhancement and next-sentence prediction. Finally, we combine the above two models utilizing local knowledge, global knowledge, and incongruity to offer class-leading performance. The investigations described in this work offer novel insights into the detection of satire in complex, multimodal content.
Authors - James Uys, Gunther Drevin, Lynette Drevin Abstract - Serious games have seen a rise in popularity as an alternative method to deliver information to learners. A problem that is often faced is maintaining learner engagement during the educational process. To address this, it is important to identify the elements which are essential to keeping a learner motivated during the learning experience. This research focused on motivational drivers behind learning as well as prevalent characteristics in serious games. These elements were then integrated into the development life cycle of a serious game. The developed artefact was evaluated using the RETAIN model.
Authors - Lloyd L.K. Modimogale, Jan H. Kroeze, Corne J. van Staden Abstract - The paper presents the results of a quantitative study examining the impact of the Fourth Industrial Revolution (4IR) on the South African coal mining sector, specifically focusing on reskilling. As mechanization and digital technologies increasingly permeate the industry, this study investigates the implications for employment and skill requirements among coal miners. Data on job displacement rates, skill sets, and reskilling initiatives within the coal mining workforce were collected using statistical analysis. The findings indicate a significant decline in demand for traditional low-skilled job roles, highlighting the urgent need for reskilling programs to facilitate workforce adaptation to new technological demands. The study aims to understand how coal miners view the impact of digitalization on the coal mine and the management of the reskilling process. The research highlights the need for proactive measures to mitigate job insecurity and ensure that workers remain relevant in a rapidly changing economic environment, thus contributing to the broader discourse on sustainable labor practices within the mining sector.
Authors - Mafalda Reis, Lidia Oliveira, Catarina Feio Abstract - The main objective of this research is to study the role of online influencers in the information consumption of young people in Portugal. It studies the information consumption habits of young people aged between 18 and 30, as well as their views on the role of influencers in transmitting information on social media and their relationship with the concept of opinion leadership. A literature review was conducted since 2018 to generate a view of the state of the art on the issue under study. The data collection instrument was a questionnaire survey, obtained using an interpretative methodology, through a quantitative analysis of the data. From the analysis of the 322 respondents to the questionnaire, it was concluded that: young people consume more information on social networks; women and students are the ones who follow influencers the most; the relationship between influencers and followers is not one of friendship; young people are mainly interested in health issues and national news; young people have already learned about a current issue because an influencer talked about it; young people consider influencers to be active members of a given online community.
Authors - Kornprom Pikulkaew, Apinantn Sumthumpruek Abstract - Investigating the emotional lives of animals is inherently complicated although the findings are rewarding in terms of conservation, psychology, and sociopsychology. In this paper, we consider the problem of animal emotion detection with the aid of deep learning using dogs' emotions in this study. In this case, four categories of emotions, angrily, joyfully, relaxed, and sadly were classified based on the best CNNs such as ResNet-50, EfficientNet, and MobileNet. Furthermore, by employing data preprocessing, data augmentation techniques, and structural explainability techniques like the Grad-CAM, we could improve how the model made critical decisions. Results confirmed that the model per-formed satisfactorily in detecting the subjects' emotions even though joyful and relaxed states were more pronounced with high levels of accuracy compared to others with emotions like sadness and anger lauded as a notable challenge, especially in discriminating attitudes that seemed too close to one another. The application of Grad-CAM was able to elaborate on the regions of interest incorporated by the model thus enhancing the explainability of the model. This paper is focused on the emergent developments in emotion detection in animals and further recommends for advancement of three-dimensional deep learning techniques, settlement of the dataset, and the introduction of more complicated explainable AI techniques such as Local Interpretable Model Explanations (LIME).
Authors - Aitor Godoy, Ismael Rodriguez, Fernando Rubio Abstract - In this paper we present a series of algorithms to calculate the power of each political party in a parliamentary system. For this purpose, it is necessary to calculate the proportion of parliamentary majorities in which their participation is necessary. The usefulness of the proposed methods is illustrated with a real case study: the Spanish electoral system. For this system, we analyze all the elections that have taken place since the establishment of democracy in the country. For each electoral process, we compare the power that each party would have if the allocation of deputies were proportional to the number of votes, and the real power it has with the current electoral system. The results obtained contradict intuitions that the Spanish population usually has about its own electoral system.
Authors - Edura Halim, Azman Mohamed, Mohamad Syazli Fathi, Zeeshan Aziz Abstract - Roads and highways largely contributes to the growth and development of a country. This paper focuses on enhancing present road safety assessment tools and techniques in line with Safe Roads, one of the pillars of the Safe System. Road Infrastructure Safety Management (RISM) is a comprehensive approach to road safety that involves a set of procedures with systematic identification, assessment, and management of risks associated with road infrastructure. This paper presents a SWOT analysis of tools used in RISM during the design stage including Road Safety Audit (RSA), Road Safety Impact Assessment (RSIA), Road Safety Screening and Appraisal Tools (RSSAT), Star Rating for Designer (SR4D) and Safe System Assessment (SSA). Conceptual framework of Intelligent Road Safety Assessment for Designer (IRSA4D) has been developed to utilized and address the findings on the SWOT analysis of RISM tools. IRSA4D application is aimed to facilitate road designers in providing proactive safety assessment and recommendations for improvement through intelligent static and dynamic assessment. The application is deemed to be valuable in assisting road designers in spite of their level of knowledge and working experiences as well as providing aid in producing the optimum and ‘best’ design during design stage.
Authors - Balendra, Neeraj Sharma, Shiru Sharma Abstract - Brain-Computer Interface (BCI) technology stands at the forefront of interdisciplinary research, merging neuroscience, engineering, and computer science to forge direct communication channels between the human brain and external devices. BCI based devices has tremendous applications in prosthetic device development. The challenges in real-time practical BCI implementation are due to the bulky models, inherent noises, artifacts and complexity of motor imagery (MI) electroencephalogram (EEG) data with inter-subject and intra-subject variabilities. To overcome these challenges, the proposed algorithm introduces a modified EEG Morlet (MEM) wavelet having a better time bandwidth product leading to detailed feature extraction with capability of natural filter for artifacts and noises introduced by eye blinking and muscle movements. Further, the proposed approach utilizes Hilbert transform to extract temporal features of analytical signal, extract their common spatial patterns, calculates the continuous wavelet transform (CWT) coefficients, arrange these coefficients at different scale for each channel, calculates the cross-correlation for each scale and observes the evolution in cross-correlation matrices at different scale with the help of customized long-short term memory (LSTM) neural network to classify MI EEG. The customized LSTM architecture had the size of 1.93MB showing the effectiveness of methodology for MI EEG classification of embedded based devices. The best classification accuracy achieved by MEM wavelet with instantaneous magnitude temporal feature was 83.78% and the comparative analysis with earlier state of the art methods showed an improvement of 1.10% in accuracy.
Authors - Ahmed D. Alharthi Abstract - Traditional proficiency and qualification criteria in crowd-based requirements engineering (CrowdRE) often fall short when identifying the most capable individuals for critical tasks such as elicitation and analysis. While crowd profiles typically account for demographic information like gender and nationality, they frequently overlook personality traits, which can significantly influence task performance. This study addresses this limitation by examining the relationship between personality traits and key requirements engineering (RE) activities within CrowdRE environments. We propose an automated system that incorporates personality profiling into task assignment processes, enhancing the precision of matching individuals to specific RE tasks. By employing data fusion techniques and decision-making algorithms, the system improves the efficiency and effectiveness of task allocation. An empirical investigation is conducted to highlight the impact of personality traits on the success of RE tasks and the need to incorporate these factors into task assignment strategies. The findings contribute to developing intelligent, human-centred collaboration technologies that optimise workflows in crowd-sourced environments. This research underscores the importance of personality traits in improving task performance and collaboration within large-scale ICT systems, aligning with the broader objective of enhancing task allocation in the context of modern collaboration technologies.
Authors - Youssef Baklouti, Tarik Echcherqaoui, Ines Abdeljaoued-Tej Abstract - This release introduces an innovative interactive chatbot designed to engage with sensitive enterprise data. Leveraging Azure Machine Learning Promptflow and Retrieval-Augmented Generation (RAG) architecture, the chatbot facilitates secure data retrieval and generation within the enterprise environment. To assess the model’s performance, we utilized over 10 query examples, providing ground-truth and context data. Evaluation strategies included system-based metrics like the F1-Score, which yielded an average score of 0.59, and AI-evaluating- AI metrics such as Coherence, Groundedness, Similarity, Fluency, and Relevance, scoring 4.50, 4.20, 4.50, 4.10, and 4.40 respectively. While AI-evaluating-AI strategies showed decent scores, the relatively low F1- Score indicates potential for improvement through fine-tuning or selecting a more suitable vector database. Overall, this interactive solution not only enhances internal operations but also demonstrates AI’s potential in automating and streamlining complex processes.
Authors - Azam Syukur Rahmatullah, Nurul Fithriyah Awaliatul Laili, Akbar Nur Aziz Abstract - This study explores the root of social pathologies in the industrial era 4.0, which young and old adolescents in Indonesia carry out. Social pathological behavior that is carried out is quite dangerous to the existence of the nation and state if not handled early. This type of research is qualitative research that is directly studied in the field to find out what causes social pathologies in this industrial era 4.0 and how to solve them. The research approach is phenomenology because it wants to thoroughly explore three (3) informants, experts in the parenting field, taken from the Yogyakarta area of Indonesia, who were interviewed directly by the researcher. The data obtained was then analyzed in depth with phenomenological analysis. The study results show several anomalous social behaviors in the industry 4.0 era caused by parenting in families that are not positive. Hence, they continue until adolescence, adulthood, and even old age. Inconsistency in parenting and failure in parenting cause children to grow into unhealthy individuals and have sick souls so that on their way, they become people who deviate from their behavior. Therefore, healthy and positive parenting must be encouraged early, including in rural and urban areas. Some positive parenting movement programs that should be implemented early on include creating a healthy parenting movement nationally, creating village and city parenting homes nationally, and making instructors and families healthy home companions nationally.
Authors - Nabaa T. Salman, Wasan A. Wali, Mohammed Lami Abstract - Solar energy is an inexhaustible source of carbon-free energy world-wide. However solar radiation determines the amount of electrical energy and current that can be produced by solar panels. In this paper, the dynamic regulation of solar radiation using Polymer Dispersed Liquid Crystal (PDLC) was studied. It regulates solar radiation that is incident on the solar cell’s surface by changing its transparency because of the applied voltage. Thus, researchers were able to obtain a variable range of solar radiation at the same time and then control the power of the solar cell produced according to the user's request. In the outdoor experiment, the behavior of filtrated radiation in daylight performance under different sky circumstances was assessed by examining solar radiation both with and without a PDLC screen. To simulate the PDLC and forecast solar radiation in real time, the researchers utilized an Adaptive Neuro-Fuzzy Inference System (ANFIS). MATLAB program utilized 3.5 W, 25 W, and 100W solar panels. PDLC transparency ranges from 5% to 83%. The results showed that PDLC overall shading on transparent\opaque states are 73% to 37% respectively at the same point where PDLC films may regulate the solar cell's output power at a pace of (39.6%, 39.5%, 42%) of the total cell power for the simulated solar panel respectively.
Authors - Miguel Angel Ruiz-Adarmes Abstract - Knowing the weather conditions at airports is of vital importance for reasons that affect the safety, efficiency, and comfort of flights. Bad weather, such as strong winds or fog, can represent a significant danger to aircraft during takeoffs, landings, and flights. Therefore, learning to predict weather behavior, based on prior information, is important. That is why this research on the prediction of weather conditions at Jorge Ch´avez Airport in Lima is presented. To do this, a set of previous data was used to which the J48, Random Forest, SVM, Bayes Net, and Neural Network algorithms were applied to identify that the Random Forest algorithm obtained the best behavior with Accuracy = 76.8004% for the training and validation process; and Accuracy = 78.5181% for the test process. As a proof of concept, a Java application was implemented.
Authors - Strahil Sokolov, Kaloyan Varlyakov, Dimitar Radev Abstract - In this paper an approach is described for improving the quality of data generated from medical screening processes based on machine learning. The designed workflow uses data acquisition from Titmus equipment, performs data preprocessing, model training and health record evaluation. We are proposing a design of a distributed system to realize this approach in order to bridge the gap between the cloud-native technologies and their usage for patient screening in rural or remote areas. The algorithm shows promising results and is suitable for implementation on Edge-AI , IoT and cloud-based medical support systems.
Authors - Marwa Mostafa Yassin, Nahla A. Belal, Aliaa Youssif Abstract - Papilledema is a medical disorder marked by the enlargement of the optic disc. Optic disk imaging is essential for the diagnosis of papilledema, as neglecting to perform this procedure can lead to fatal outcomes. This research presents a novel approach that combines deep learning with the Harris Hawks Optimization (HHO) algorithm to increase the accuracy of diagnosing and distinguishing papilledema in optical disk images. The proposed technique presented in this study focuses on optimizing the weights of the Convolutional Neural Network (CNN) model. This optimization process improves model training by using the underlying optimization principles. The technique was evaluated using the Kaggle dataset, which was made available for this purpose. The evaluation results showed that the proposed technique achieved an accuracy of 0.997%, surpassing the performance of existing techniques such as VGG16, DenseNet121, EfficientNetB0, and EfficientNetB3. The proposed model demonstrates that state-of-the-art CNN models, when paired with the HHO algorithm, can reliably diagnose real papilledema, pseudo papilledema, and normal optic discs. This could potentially save lives for patients.
Authors - Otuu Obinna Ogbonnia, Joseph Henry Anajemba, Oko-Otu Chukwuemeka N., Deepak Sahoo Abstract - Scholars have investigated the challenges of community policing (CP) in Nigeria through socio-political, economic, and cultural lenses, with none adopting a method that can reveal these challenges comprehensively. This has led to a gap in recognizing key CP problems, thereby resulting in ineffective solutions from the government, and making government services in this context less accessible and responsive to citizens. This study employed Greenhalgh’s meta-narrative approach to unveil community policing challenges that were previously overlooked in Nigerian context. Drawing from a variety of sources such as scholarly articles (ACM digital library, Science Direct), official documents, and media coverage, this study identified lack of robust technology usage, lack of citizens’ participation, citizens’ unwillingness to share information and lack of trust, accountability and transparency as major community policing challenges in Nigeria. This study contributes to a nuanced understanding of the challenges hindering the successful implementation of CP in Nigeria, highlights the implications of these challenges on the overall security landscape, and offers directions to policymakers and relevant government agencies, providing insights to the design of technological solutions for community policing in Nigeria.
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 - 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 - 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 - 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 - Robert Johnson, Jing Jung Zhang, Fu Kuo Manchu, Silvio Simani Abstract - With a focus on fixing the common problems of imbalance and misalignment, this study introduces an artificial intelligence tool based on a state-of-the-art deep learning method that will enhance automatic condition monitoring and fault detection for mechanical processes. The main breakthrough is a trustworthy model for condition monitoring using artificial neural networks that extract feature vectors from signal data using frequency analysis. A high fault detection accuracy rate highlights the research accomplishment, proving its ability to establish new solutions also for predictive maintenance. This research considers the different working conditions of a mechanical process by analysing four separate operational classes, including balanced operation, horizontal vertical misalignments, unbalanced situations, and regular operation. The dataset studied in this work includes a wealth of information and was carefully calibrated for neural network training, which has also the potential to be employed in the development of maintenance procedures for mechanical plants. Finally, this study provides a significant step towards the goals of improved performance and unyielding safety requirements that industries are aiming for.
Authors - Nejjari Nada, Chafi Anas, Kammouri Alami Salaheddine Abstract - The handicraft sector holds crucial importance within the Moroccan economy, serving as a fundamental pillar that significantly contributes to the country's economic balance. This sector not only preserves cultural heritage but also provides employment opportunities and sustains local economies. Our study primarily revolves around an in-depth exploration of the artisanal universe, aiming to derive relevant recommendations to optimize its performance and enhance its competitive edge. By focusing on identifying gaps, challenges, and opportunities within the sector, our goal is to develop concrete improvement suggestions that can catalyze continuous development and growth. Through a comprehensive analysis, we seek to provide actionable insights that can improve efficiency, sustainability, and the overall impact of the handicraft sector on the Moroccan economy. This research aspires to support policymakers, stakeholders, and artisans themselves in fostering a thriving and resilient artisanal industry that contributes robustly to economic and social development.
Authors - Ubayd Bapoo, Clement N Nyirenda Abstract - This study evaluates the performance of Soft Actor Critic (SAC), Greedy Actor Critic (GAC), and Truncated Quantile Critics (TQC) in high-dimensional decision-making tasks using fully observable environments. The focus is on parametrized action (PA) spaces, eliminating the need for recurrent networks, with benchmarks Platformv0 and Goal-v0 testing discrete actions linked to continuous actionparameter spaces. Hyperparameter optimization was performed with Microsoft NNI, ensuring reproducibility by modifying the codebase for GAC and TQC. Results show that Parameterized Action Greedy Actor-Critic (PAGAC) outperformed other algorithms, achieving the fastest training times and highest returns across benchmarks, completing 5,000 episodes in 41:24 for the Platform game and 24:04 for the Robot Soccer Goal game. Its speed and stability provide clear advantages in complex action spaces. Compared to PASAC and PATQC, PAGAC demonstrated superior efficiency and reliability, making it ideal for tasks requiring rapid convergence and robust performance. Future work could explore hybrid strategies combining entropy-regularization with truncation-based methods to enhance stability and expand investigations into generalizability.
Authors - Amalia Mukhlas, Shahrinaz Ismail, Bazilah A. Talip, Jawahir Che Mustapha, Juliana Jaafar Abstract - The pharmaceutical industry’s significant influence on other sectors underscores the urgency of implementing sustainable systems. Technology offers invaluable tools for achieving this goal. This study examines the challenges faced by pharmaceutical websites to function in collaboration and governance, emphasizing the difficulties in providing accessible and relevant information. Using experiential observation, it highlights governance-related inefficiencies in website design. The proposed solutions focus on improving the website usability for transparency, accountability and social involvement in line with sustainable systems practices. The findings disclose the suboptimal design of many pharmaceutical websites, hindering collaboration with external parties, specifically academic and potentially impact the industry’s sustainable efforts.
Authors - Sarah Abdalrahman Al-Shqaqi, Mohammed Zayed, Kamal Al-Sabahi, Adnan Al-Mutawkkil Abstract - The development of the Internet of Things (IoT) in recent years has significantly contributed to a paradigm change in all aspects of life. IoT has rapidly gained traction in a short period of time across a variety of sectors, including business, healthcare, governance, infrastructure management, consumer services, and even defense. IoT has the ability to monitor systems through the delivery of consistent and precise information. In medical services it enables us to make decisions, surrounding technologies will play an essential contribution to providing healthcare to people in remote locations. The health centers gather data from areas where cholera has emerged or is suspected, which is then sent to the ministry of public health and population. The world health organization in Yemen analyzes the data using two systems (Edews and Ewars), but they lack the full capability for early detection of cholera, and do not utilize Internet of Things technology, which plays an important role in solving most health problems, including cholera. To address this issue, we proposed a framework consists of 6 layers and add parameters that helps early detection of cholera disease. In this study, IoT framework was used for early detection of cholera, thereby assisting the ministry of public health and population and the world health organization in making informed decisions by add the intelligent medical server layer. Overall, this framework is applicable to any field, particularly healthcare for cholera.
Authors - Praveen Kumar Sandanamudi, Neha Agrawal, Nikhil Tripathi, Pavan Kumar B N Abstract - Over the past few years, the proliferation of resource-constrained devices and the looming of Internet-of-Things (IoT) for UAV applications has accentuated the need for lightweight cryptographic (LWC) algorithms. These algorithms are designed to be more suitable for UAV application based IoT devices as they are efficient in terms of memory usage, computation, utilization of power, etc. Based on the literature study, the algorithms mostly suitable for the UAV application based resource-constrained devices are identified in this paper. This list also includes ASCON cipher, winner of the NIST’s lightweight cryptography standardization contest. Furthermore, these algorithms have been implemented on a UAV application based Raspberry Pi 3 Model B to analyze their hardware and software performance w.r.t the essential metrics, such as latency, power consumption, throughput, energy consumption, etc., for different payloads. From the experimental results, it has been observed that the SPECK is optimized for software implementations and may offer better performance in certain scenarios, especially on UAV application based resource-constrained devices. ASCON, on the other hand, provides both encryption and authentication in a single pass, potentially reducing latency and overhead. This paper aims to assist researchers in pinpointing the most appropriate LWC algorithm tailored to specific scenarios and requirements.
Authors - Mmapula Rampedi, Funmi Adebesin Abstract - The healthcare sector has generally been reluctant to adopt digital technologies. However, the COVID-19 pandemic pushed the industry to accelerate its digital transformation. Digital twins, a virtual replica of human organs or the entire human body, is revolutionizing healthcare and the management of healthcare resources. Digital twins can improve the accuracy of patients’ diagnoses through access to their virtual replica data. This enables healthcare professionals to make informed decisions about patients’ conditions and treatment options. This paper presents the results of a systematic literature review that investigated how digital twins are being utilized in the healthcare sector. A total of 6,714 papers published between 2019 and April 2024 were retrieved from four databases using specific search terms. A screening process based on inclusion and exclusion criteria resulted in a final set of 34 studies that were analyzed. The qualitative content analysis of the 34 studies resulted in the identification of five themes namely; (i) the technologies that are integrated into digital twins; (ii) the medical specialties where digital twins are being used; (iii) the different application areas of digital twins in healthcare; (iv) the benefits of the application of digital twins in healthcare and; (v) the challenges associated with the use of digital twins in healthcare. The outcome of the study showcased the potential for the adoption of digital twins to revolutionize healthcare service delivery by mapping the medical specialties of use to the different application areas. The study also highlights the benefits and challenges associated with the adoption of digital twins in the healthcare sector.
Authors - Nazli Tokatli, Mucahit Bayram, Hatice Ogur, Yusuf Kilic, Vesile Han, Kutay Can Batur, Halis Altun Abstract - This study aims to create deep learning models for the early identification and classification of brain tumours. Models like U-Net, DAU-Net, DAU-Net 3D, and SGANet have been used to evaluate brain MRI images accurately. Magnetic resonance imaging (MRI) is the most commonly used method in brain tumour diagnosis, but it is a complicated procedure due to the brain’s complex structure. This study looked into the ability of deep learning architectures to increase the accuracy of brain tumour diagnosis. We used the BraTS 2020 dataset to segment and classify brain tumours. The U-Net model designed for the project achieved an accuracy rate of 97% with a loss of 47%, DAU-Net reached 90% accuracy with a loss of 33%, DAU-Net 3D achieved 99% accuracy with a loss of 35%, and SGANet achieved 99% accuracy with a loss of 20%, all demonstrating effective outcomes. These findings aim to improve patient care quality by speeding up medical diagnosis processes using computer-aided technology. Doctors can detect 3D tumours from MRI pictures using software developed as part of the research. The work packages correctly handled project management throughout the study’s data collection, model creation, and evaluation stages. Regarding brain tumour segmentation, 3D U-Net architecture with multi-head attention mechanisms provides doctors with the best tools for planning surgery and giving each patient the best treatment options. The user-friendly Turkish interface enables simple MRI picture uploads and quick, understandable findings.
Authors - Radford Burger, Olawande Daramola Abstract - Clinical Decision Support Systems (CDSS) have the potential to significantly improve healthcare quality in resource-limited settings (RLS). Despite evidence supporting the effectiveness of CDSS, their adoption and implementation rates remain low in RLS due to low levels of computer literacy among health workers, fragmented and unreliable infrastructure, and technical challenges. A thorough understanding of requirements is critical for the design of CDSS, which will be relevant to RLS. This paper explores the elicitation and prioritisation of requirements of a CDSS tailored to gait-related diseases in RLS. To do this, we conducted a qualitative literature analysis to identify potential requirements. After that, the requirements were presented to gait analysis experts for revision and prioritisation using the MoSCoW requirements prioritisation technique. The analysis of the results of the prioritisation process shows that for the functional requirements, 59.1% are fundamental and essential (Must Have), 36.3% are important but not fundamental (Should Have), 4.5% are negotiable requirements that are nice-to-have, but not important or fundamental (Could Have). All the non-functional requirements (100%) that pertain to usability and security were considered fundamental and essential (Must Have). This study provides a solid foundation for understanding the requirements of CDSS that are tailored to gait-related diseases in RLS. It also provides a guide for software developers and re-searchers on the design choices regarding the development of CDSS for RLS.
Authors - Omar Ahmed Abdulkader, Bandar Ali Alrami Al Ghadmi, Muhammad Jawad Ikram Abstract - In an era characterized by escalating digital threats, cybersecurity has emerged as a paramount concern for individuals and organizations globally. Traditional security measures, often reliant on centralized systems, face significant challenges in combating increasingly sophisticated cyberattacks, leading to substantial data breaches, financial losses, and erosion of trust. This paper investigates the transformative potential of blockchain technology as a robust solution to enhance cybersecurity frameworks. By leveraging the core principles of blockchain—decentralization, transparency, and immutability—this study highlights how blockchain can address critical cybersecurity challenges. For instance, the use of blockchain for data integrity ensures that information remains unaltered and verifiable, significantly reducing the risk of tampering. Furthermore, decentralized identity management systems can provide enhanced security against identity theft and phishing attacks, allowing users to maintain control over their personal information. Through a review of current applications and case studies, this paper illustrates successful implementations of blockchain in various sectors, including finance, healthcare, and supply chain management. Notable results include a reported 30% reduction in fraud rates within financial transactions utilizing blockchain technology and a marked improvement in incident response times due to the transparency and traceability offered by blockchain solutions. Despite its promising applications, this paper also addresses existing challenges, such as scalability issues that can hinder transaction speed, regulatory concerns that complicate implementation, and technical complexities that require specialized knowledge. These barriers pose significant obstacles to the widespread adoption of blockchain in cybersecurity. In conclusion, this paper emphasizes the need for further research and development to overcome these challenges and optimize the integration of blockchain within cybersecurity frameworks. By doing so, we can foster a safer digital environment and enhance resilience against the evolving landscape of cyber threats.
Authors - Catia Silva, Nelson Zagalo, Mario Vairinhos Abstract - The preservation of cultural heritage, crucial for maintaining cultural identity, is increasingly threatened by natural degradation and socio-economic changes. Cultural tourism, supported by information and communication technologies, has become a key strategy for sustaining and promoting heritage sites. However, research on the most effective digital elements for amplifying tourist engagement remains limited. To address this gap, the present study explored the use of the Cultural Engagement Digital Model, which integrates participatory activities through game, narrative, and creativity elements, to enhance visitor engagement at cultural sites. The study focused on designing and testing three prototypes for Almeida, a historical village in in Guarda, Portugal, involving both visitors and interaction design experts to evaluate user preferences regarding the proposed activities. The findings of this study indicate that activities aligned with participatory dimensions can effectively engage users. These results help to solidify the model as a valuable instrument for designing mobile applications capable of promoting tourist engagement.
Authors - Juliana Silva, Pedro Reisinho, Rui Raposo, Oscar Ribeiro, Nelson Zagalo Abstract - As global life expectancy rises and the population of older adults in-creases, a higher prevalence of age-related diseases, such as dementia, is being observed. However, dementia-like symptoms are not exclusively caused by neurodegenerative conditions; pseudodementia, associated with late-life depression, can mimic the symptoms of dementia but may be potentially reversible with appropriate interventions. Despite this, individuals with pseudodementia still have a higher risk of progressing to neurodegenerative dementia. To counteract this possibility and aid in symptom reversal, non-pharmacological interventions may be a potential treatment. The present case study explored the feasibility of promoting storytelling through virtual reminiscence therapy in an older adult with pseudodementia, while also assessing the level of technological acceptance. The intervention included two sessions: one using a digital memory album and an-other utilizing 360º videos of personally significant locations. The results support the viability of using virtual reality as a therapeutic instrument to stimulate reminiscence and promote storytelling with a manageable learning curve and without inducing symptoms of cybersickness.
Authors - Franciskus Antonius Alijoyo, N Venkatramana, Omaia AlOmari, Shamim Ahmad Khan, B Kiran Bala Abstract - The Internet of Things (IoT) is becoming a crucial component of many industries, from smart cities to healthcare, in today's networked world. IoT devices are becoming more and more susceptible to security risks, especially zero-day (0day) attacks, which take advantage of undiscovered flaws. The dynamic and dispersed nature of these systems makes it difficult to identify and mitigate these assaults in IoT contexts. This research focuses on a deep learning model that was created and put into use with Python software. It was made especially to do a detection job with great accuracy. The proposed Autoencoder (AE) with Attention Mechanism model demonstrates exceptional performance in detecting zero-day attacks, achieving an accuracy of 99.45%, precision of 98.56%, recall of 98.53%, and an F1 score of 98.21%. The involvement of the attention mechanism helps to focus on the most relevant features, enhancing its efficiency and reducing computational overhead, making it a promising solution for real-time security applications in IoT systems. Compared to previous methods, such as STL+SVM and AE+DNN, the proposed model significantly outperforms the methods. These results highlight its superior ability to identify anomalies with minimal false positives. Because of its resilience, the model is very good at making zero-attacks. The results demonstrate how deep learning may improve IoT systems' security posture by offering proactive, real-time protections against zero-day threats, resulting in safer and more robust IoT environments.
Authors - Freedom Khubisa, Oludayo Olugbara Abstract - This paper presents the development and evaluation of an artificial intelligent (AI) driven web application for detecting maize diseases. The AI application was designed according to the design science methodology to offer accurate and real-time detection of maize diseases through a user-friendly interface. The application used Flask framework and Python programming language, leveraging multiple libraries and Application Programming Interfaces (APIs) to handle aspects such as database, real-time communication, AI models, weather forecast data, and language translation. The application's AI model is a stacked ensemble of cutting-edge deep learning architectures. Technical performance testing was performed using GTmetrix metrics, and the results were remarkable. The WebQual4.0 framework was used to evaluate the application's usability, information quality and service interaction quality. The Cronbach’s alpha (α) reliability measure was applied to assess internal consistency for WebQual4.0, which yielded an acceptable reliability score of 0.6809. The usability analysis showed that users perceived the AI-driven web application as intuitive, with high scores computed for navigation and ease of use. The quality of information was rated positive with users appreciating the reliability and relevance of the maize disease detection results of the AI application. The service interaction indicated potential for enhancement, which is a solicitude also highlighted in qualitative user feed-back that will be considered for future improvement. The study findings generally indicated that our AI application has great potential to improve agricultural practices by providing early maize disease diagnostics and decisive information to aid maize farmers and enhance maize yields.
Authors - Abdulrahman S. Alenizi, Khamis A. Al-Karawi Abstract - The liver is a vital organ responsible for numerous physiological functions in the human body. In recent years, the prevalence of liver diseases has risen significantly worldwide, mainly due to unhealthy lifestyle choices and excessive alcohol use. This illness is made worse by several hepatotoxic reasons. Obesity is the root cause of chronic liver disease. Obesity, undiagnosed viral hepatitis infections, alcohol consumption, increased risk of hemoptysis or hematemesis, renal or hepatic failure, jaundice, hepatic encephalopathy, and many other conditions can all contribute to chronic liver disease. Using machine learning for illness identification, hepatitis, an infection inflating liver tissue, has been thoroughly investigated. Numerous models are employed to diagnose illnesses, but limited research focuses on the connections between hepatitis symptoms. This research intends to examine chronic liver disease through machine learning predictions. It assesses the efficacy of multiple algorithms, including Logistic Regression, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbours (K-NN), and Decision Tree, by quantifying their accuracy, precision, recall, and F1 score. Experiments were performed on the dataset utilising these classifiers to evaluate their efficacy. The findings demonstrate that the Random Forest method attains the highest accuracy at 87.76%, surpassing other models in disease prediction. It also demonstrates superiority in precision, memory, and F1 score. Consequently, the study concludes that the Random Forest model is the most effective for predicting liver disease in its early stages.
Authors - Phuong Thao Nguyen Abstract - In recent years, the application of machine learning (ML) in anomaly detection for auditing and financial error detection has garnered significant attention. Traditional auditing methods, often reliant on manual inspection, face challenges in accuracy and efficiency, especially when handling large datasets. This study explores the integration of ML techniques to enhance the detection of anomalies in financial data specific to Thai Nguyen Province, Vietnam. We evaluate multiple ML algorithms, including supervised models (logistic regression, support vector machines) and unsupervised models (k-means clustering, isolation forest, autoencoders), to identify unusual patterns and potential financial discrepancies. Using financial records and audit reports from Thai Nguyen, the models were trained and tested to assess their accuracy, precision, and robustness. Our findings demonstrate that ML models can effectively detect anomalies and improve error identification compared to traditional methods. This paper provides practical insights and applications for local auditors, highlighting ML’s potential to strengthen financial oversight and fraud prevention within Thai Nguyen. Future research directions are also proposed to enhance model interpretability and address unique challenges in Vietnamese financial contexts.
Authors - Aman Mussa, Madina Mansurova Abstract - The rapid advancement of neural networks has revolutionized multiple domains, as evidenced by the 2024 Nobel Prizes in Physics and Chemistry, both awarded for contributions to neural networks. Large language models (LLMs), such as ChatGPT, have significantly reshaped AI interactions, gaining unprecedented growth and recognition. However, these models still face substantial challenges with low-resource languages like Kazakh, which accounts for less than 0.1% of online content. The scarcity of training data often results in unstable and inaccurate outputs. To address this issue, we present a novel Kazakh language dataset specifically designed for self-instruct fine-tuning of LLMs, comprising 50,000 diverse instructions from internet sources and textbooks. Using Low-Rank Adaptation (LoRa), a parameter-efficient fine-tuning technique, we successfully fine-tuned the LLaMA 2 model on this dataset. Experimental results demonstrate improvements in the model’s ability to comprehend and generate Kazakh text, despite the absence of established benchmarks. This research underscores the potential of large-scale models to bridge the performance gap in low-resource languages and highlights the importance of curated datasets in advancing AI-driven technologies for underrepresented linguistic communities. Future work will focus on developing robust benchmarking standards to further evaluate and enhance these models.
Authors - Eduardo Puraivan, Pablo Ormeno-Arriagada, Steffanie Kloss, Connie Cofre-Morales Abstract - We are in the information age, but also in the era of disinformation, with millions of fake news items circulating daily. Various fields are working to identify and understand fake news. We focus on hybrid approaches combining machine learning and natural language processing, using surface linguistic features, which are independent of language and enable a multilingual approach. Many studies rely on binary classification, overlooking multiclass problems and class imbalance, often focusing only on English. We propose a methodology that applies surface linguistic features for multiclass fake news detection in a multilingual context. Experiments were conducted on two datasets, LIAR (English) and CLNews (Spanish), both imbalanced. Using Synthetic Minority Oversampling Technique (SMOTE), Random Oversampling (ROS), and Random Undersampling (RUS), we observed improved class detection. For example, in LIAR, the classification of the ‘false’ class improved by 43.38% using SMOTE with Adaptive Boosting. In CLNews, the ROS technique with Random Forest raised accuracy to 95%, representing a 158% relative improvement over the unbalanced scenario. These results highlight our approach’s effectiveness in addressing the problem of multiclass fake news detection in an imbalanced, multilingual context.
Authors - Mariam Esmat, Mohamed Elgemeie, Mohamed Sokar, Heba Ali, Sahar Selim Abstract - This paper explores the relationship between deep learning approaches and the intricate nature of EEG signals, focusing on the development of a P300 brain speller. The study uses an underutilized dataset to explore the classification of EEG signals and distinguishing features of "target" and "non-target" signals. The data processing adhered to current literature standards, and various deep learning methods, including Recurrent Neural Networks, Artificial Neural Networks, Transformers, and Linear Discriminant Analysis, were employed to classify processed EEG signals into target and non-target categories. The classification performance was evaluated using the area under the curve (AUC) score and accuracy. This research lays a foundation for future advancements in understanding and utilizing the human brain in neuroscience and technology.
Authors - Angel Peredo, Hector Lugo, Christian Narcia-Macias, Jose Espinoza, Daniel Masamba, Adan Gandarilla, Erik Enriquez, Dong-Chul Kim Abstract - This paper explores the under-examined potential of offline reinforcement learning algorithms in the context of Smart Grids. While online methods, such as Proximal Policy Optimization (PPO), have been extensively studied, offline methods, which inherently avoid real-time interactions, may offer practical safety benefits in scenarios like power grid management, where suboptimal policies could lead to severe consequences. To investigate this, we conducted experiments in Grid2Op environments with varying grid complexity, including differences in size and topology. Our results suggest that offline algorithms can achieve comparable or superior performance to online methods, particularly as grid complexity increases. Additionally, we observed that the diversity of training data plays a crucial role, with data collected through environment sampling yielding better results than data generated by trained models. These findings underscore the value of further exploring offline approaches in safety-critical applications.
Authors - Mohammed Sabiri, Bassou Aouijil Abstract - Let Rm = IFpr [v]= < vm - v >, where p is an odd prime, IFpr is a finite field with pr elements and vm = v. In this study, we investigate quantum codes over IFpr by using constacyclic codes over Rm, which are dual containing. Furthermore, by using cyclic codes over the ring Rm and their decomposition over the finite field IFpr into cyclic codes, a LCD codes are given as images of LCD codes over Rm.
Authors - Hector Lugo, Angel Peredo, Christian Narcia-Macias, Jose Espinoza, Daniel Masamba, Adan Gandarilla, Erik Enriquez, DongChul Kim Abstract - Cancer continues to be a major global health challenge, with high rates of morbidity and mortality. Traditional chemotherapy regimens often overlook individual patient variability, leading to suboptimal outcomes and significant side effects. This paper presents the application of Reinforcement Learning (RL) and Decision Transformers (DT) for developing personalized chemotherapy strategies. By leveraging offline data and simulated environments, our approach dynamically adjusts dosing strategies based on patient responses, optimizing therapeutic efficacy while minimizing toxicity. Experimental results show that DTs outperform both traditional Constant Dose Regimens (CDR) and online training methods like Proximal Policy Optimization (PPO), leading to improved survival times and reduced mortality. Our findings highlight the potential of RL and DTs to revolutionize cancer treatment by offering more effective and personalized therapeutic options.
Authors - Sharmila Rathod, Aryan Panchal, Krish Ramle, Ashlesha Padvi, Jash Panchal Abstract - Diabetes or Hyperglycemia, a condition where an individual is characterized by significantly elevated blood sugar levels, may pose a significant threat to the effective lifespan as well as may pose a significant risk for various cardiovascular diseases. Reliable and non-invasive monitoring of hyperglycemia and also hypoglycemia is important for timely intervention and prognosis. The paper presents an extensive and structured survey dealing with the non-invasive glucose monitoring and diabetes detection using machine learning and signal analysis techniques. The paper focuses on a comparative analysis approach which showcases the literature in tabular and diagrammatic form. Examination of 10 papers that deal with Photoplethysmography (PPG) and Electrocardiography (ECG) signals to detect glucose variations using machine learning techniques has been carried out. The review highlights the respective proposed system, unique findings, improvements, techniques, methods, future prospects, comparison with previous studies, feature importance and model evaluation as well as stated accuracy. This comprehensive analysis aims to provide insights into the methodologies in non-invasive glycemic conditions thereby contributing to the development of improved disease analysis.
Authors - Anastasia Vitvitskaya, Almaz Galimov Abstract - We are living in the age of digitalization, a time when the latest technologies are changing everything around us. Artificial intelligence and digitalization have affected all aspects of our life and society. It is important to realise that the Covid-19 pandemic accelerated the development of digital technologies. Technologies of augmented and virtual reality (AR/VR) are used in many fields, including education. Online platforms allowed people to work and study remotely from the comfort of their homes, which made the online format more popular. Now, informal online education and the use of generative artificial intelligence is actively developing, but it is crucial to understand the implications that the active use of artificial intelligence in education will have. The purpose of the study is to identify the tasks for which generative artificial intelligence is used. As a method of research, we used the collection and analysis of scientific literature, as well as the method of survey, in which 750 people answered for which purposes they use artificial intelligence. The article considers theoretical and practical aspects of generative artificial intelligence application, defines and classifies the tasks.
