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 - Given Sichilima, Jackson Phiri Abstract - the health and productivity of poultry farms are significantly impacted by the timely detection of diseases within chicken houses. Manual disease monitoring in poultry is laborious and prone to errors, underscoring the need for sustainable, efficient, reliable, and cost-effective farming practices. The adoption of advanced technologies, such as artificial intelligence (AI), is essential to address this need. Smart farming solutions, particularly machine learning, have proven to be effective predictive analytical tools for large volumes of data, finding applications in various domains including medicine, finance, and sports, and now increasingly in agriculture. Poultry diseases, including coccidiosis, can significantly impact chicken productivity if not identified early. Machine learning and deep learning algorithms can facilitate earlier detection of these diseases. This study introduces a framework that employs a Convolutional Neural Network (CNN) to classify poultry diseases by examining fecal images to distinguish between healthy and unhealthy samples. Unhealthy fecal images may indicate the presence of disease. An image classification dataset was utilized to train the model, which achieved an accuracy of 84.99% on the training set and 90.05% on the testing set. The evaluation indicated that this model was the most effective for classifying chicken diseases. This research underscores the benefits of automated disease detection within smart farming practices in Zambia.
Authors - Ruqaya Majeed Kareem, Mohammed Kh. Al-Nussairi Abstract - Since the establishment of microgrids, the frequency stability and reliability in operating the voltage of microgrids have become necessary due to local sources of reactive power. Droop control technology has been successfully applied to this problem and remains popular today. This study proposes a control strategy that can be utilized to power-sharing and adjust the voltage and frequency appropriately according to the load condition. The main aim of the research is to control the frequency and voltage of microgrids under various conditions by using two algorithms, the Gray Wolf Optimizer (GWO) and Kepler Optimization Algorithm (KOA) to optimize the droop control and optimize the PI controller parameters. Simulation findings using Simulink in MATLAB demonstrate the performance of the suggested microgrid stability techniques. Finally, to evaluate the efficiency of the suggested control strategy, its results are compared with conventional methods.
Authors - Ahmed Abu-Khadrah, Munirah Ali ALMutairi, Mohammad R. Hassan, Ali Mohd Ali Abstract - The Internet of Things (IoT) devices are employed in various industries, including health care, smart homes, smart grids, and smart cities. Researchers address the intricate connection between the growth of the Internet of Things and the hazards to its security. The vast and varied features of the Internet of Things make traditional security solutions ineffective. A new model is developed to enhance IoT malware detection by combining three machine learning algorithms: KNN, Bagging, and support vector machines. The proposed model is evaluated by measuring accuracy, precision, recall and F1-score. In addition, two comprehensive datasets are utilized to evaluate the proposed model dataset. The study explores the potential of three ensemble classification models for Malware Detection. This study investigated the efficacy of a novel ensemble machine-learning approach for detecting malware within the Internet of Things (IoT) domain. The result of this research is that the accuracy on the validation set is 95.76%, the precision on the validation set is 97.01%, the recall is 94.55%, and the F1 score is 95.77%. The findings of this study indicate that the proposed model, a synergistic combination of K-Nearest Neighbours (KNN), Bagging, and Support Vector Machines (SVM), achieved a commendable overall accuracy of 95.76% in correctly classifying both malware and benign programs within the utilized IoT dataset.
Authors - Hoang Minh Tuan, Ngo Gia Quoc, Nguyen Huu Tien, Vu Thu Diep Abstract - This paper provides a method for automatically detecting fake beef by image analysis. High-quality classification models could have a major impact on ensuring food quality, supporting supply chain management in the meat industry, and preventing fraudulent commercial practices. Because low-quality meat is cheaper and more widely available than beef, it is common to use them as a substitute for fake beef. The problem is due to the differences in meat appearance, texture, mutilation, and color of cuts, as well as similarities between real beef and fake beef. These characteristics require a robust method to distinguish subtle characteristics to obtain reliable results. This paper combines the strength of Convolutional Neural Networks to detect a true classification of beef and fake beef. This model targets mobile applications and is suitable for the practical deployment of various environments.
Authors - George Kwamina Aggrey, Amevi Acakpovi, Emmanuel Peters Abstract - ERP systems are integrated information systems (IIS) popularly used among tertiary institutions in the globe. ERP has attained familiarization in certain parts of the globe due to its huge acquisition in tertiary institutions. Notwithstanding the rising acquisition, choice and execution of ERPs in higher education, there remains a scarcity in literature about their performance especially in the developing world. It is, therefore, important to further examine whether these ERPs fulfill their anticipated benefits. This paper aims to evaluate the effectiveness of KNUST's enterprise system (comprising ARMIS, Panacea, and Synergy Systems) in HEIs through a system integrative framework. A combined-method research approach was employed, collecting data from a sample of 60 respondents for both quantitative and qualitative investigation. The data were examined through partial_least_squares structural_equation_modeling (PLSSEM) and inductive_thematic_analysis. The study's results revealed that the customer/stakeholder-perspective, learning-growth-perspective, financial-perspective and system-quality-perspective significantly influence and positively relate to the effectiveness of KNUST's enterprise system evaluation in Ghanaian higher education. Internal business process, according to the findings, was the only perspective that had no significant impact on the performance of KNUST enterprise system in the Ghanaian higher education. Works on ERPs assessments, readiness, and implementations are scarce in developing world, particularly in the Ghanaian context. This study has successfully assessed the KNUST enterprise system, demonstrating its effectiveness through the research model deployed.
Authors - Jimmy Katambo, Gloria Iyawa, Lars Ribbe, Victor Kongo Abstract - The vulnerability of Southern Africa to climate variability, especially drought, places substantial pressure on agriculture, water systems, and the economy. This study explores how El Niño-Southern Oscillation (ENSO)-related Sea Surface Temperature (SST) variations influence drought patterns across the region using machine learning methods. Two approaches were taken: (i) a feature ranking of SST in comparison to twelve other climate variables and (ii) drought model performance comparisons with and without SST data. Results reveal SST’s significant and consistent impact across all climate zones, with both methods indicating that SST data, particularly in connection with ENSO phases, strongly influences drought variability, despite slight variations in its order of effect with respect to climatic zonal divisions. This underscores the value of incorporating SST in climate models for enhanced drought prediction and adaptation planning. Although limited by a focus on SST and not fully accounting for interactions with other climate factors, this research provides a solid foundation for understanding regional climate dynamics. Adding more climate indicators and studying SST’s interactions with land-based factors could help future studies make drought predictions more reliable and better prepare vulnerable areas.
