ABSTRACT
Kampala City, Uganda’s capital, faces severe and escalating traffic congestion due to rapid urbanisation, population growth, and rising vehicle ownership, leading to substantial economic losses, increased emissions, and degraded quality of life. Traditional reactive traffic management systems are inadequate for addressing dynamic urban mobility patterns in resource constrained environments. This study develops an intelligent traffic congestion prediction framework using machine learning classification. A dataset of 500 observations from 15 major road segments is processed through rigorous preprocessing, domain-informed feature engineering (including capacity utilisation and flow efficiency), and ensemble classifiers to categorise congestion into four actionable severity levels: Low, Medium, High, and severe. Experimental evaluation on a stratified test set shows that XGBoost outperforms Random Forest, achieving 84.0% overall accuracy and the highest precision (0.808%), recall (0.840%), and F1-score (0.820%). Feature importance analysis highlights capacity utilisation, vehicle density, and flow efficiency as the dominant predictors, consistent with fundamental traffic flow theory. The proposed system establishes a scalable, interpretable foundation for proactive congestion management in developing cities. With future enhancements in real-world data integration and temporal-spatial modelling, it holds strong potential to support adaptive traffic control, incident response, and data-driven urban planning in Kampala and similar contexts.

ABSTRACT
The rapid and continuous rise of sophisticated cyberattacks has driven the adoption of Deep Learning models in Intrusion Detection Systems (IDS). While these models deliver superior detection performance compared to traditional approaches, their “black-box” nature poses a significant barrier to real-world deployment. Network administrators often struggle to trust system-generated alerts when they cannot understand the reasoning behind them. This paper proposes a comprehensive solution to address this challenge by integrating Explainable Artificial Intelligence (XAI) techniques into IDS. Specifically, we apply SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-Agnostic Explanations) to Deep Neural Network (DNN) models trained on benchmark datasets, namely NSL-KDD and UNSW-NB15. The results demonstrate not only the model’s high effectiveness in detecting various types of cyberattacks but also its ability to provide detailed explanations at both global and local levels. These insights enable network administrators to better analyze the root causes of alerts, thereby improving the reliability and transparency of cybersecurity defense systems.

ABSTRACT
The manufacturing sector is globally considered a crucial engine room, which plays a strategic role in value addition, economic development/diversification, industrialization and employment generation. However, in Nigeria, this sector, operates far below optimal capacity, largely due to chronic deficiencies in energy supply and affordability. Manufacturers in Nigeria face energy expenditures that constitute a significant portion of total production costs, with resultant negative impacts on the economy. This study investigates the socio-economic consequences of electricity tariff adjustments on the manufacturing industry in South-South region of Nigeria, with particular emphasis on production costs and productivity. Empirical evidence indicates that manufacturing firms continue to experience unreliable electricity supply, compelling reliance on alternative power sources that substantially raise operational expenses. The results show that rising electricity tariffs significantly increase overhead and total production costs and adversely affect productivity, thereby constraining output efficiency and competitiveness within the sector. Inferential and regression analysis reveal a strong and statistically significant positive relationship between electricity tariff increases and manufacturing production costs, confirming that higher tariffs are closely associated with escalating production expenses. This substantial explanatory power underscores electricity tariffs as a dominant determinant of manufacturing cost structures in Nigeria. The findings establish that increased electricity tariffs, compounded by persistent supply unreliability, significantly elevate production costs and reduce productivity in the manufacturing sector. The study therefore, concludes that electricity tariff policies have direct and measurable implications for industrial performance and sustainability, highlighting the need for policy frameworks that balance cost recovery with the operational rea

ABSTRACT
The erroneous prediction of the speed of light in dispersive media has been looked upon historically as unequivocal proof that Newton's corpuscular theory is incorrect. Examination of his arguments shows that they were only directly applicable to the momentum of photons, however, leaving open the possibility that the cause of his mistake was the unavailability of a suitable mechanical theory to enable a correct light speed prediction, rather than his use of a particle model. It is shown that Hamilton's canonical equations of motion remove Newton's error quantitatively, and also lead to the most basic formulas of quantum mechanics without reference to any of the pioneering experiments of the late nineteenth century. An alternative formulation of the wave-particle duality principle is then suggested which allows the phenomena of interference and diffraction to be understood in terms of statistical distributions of large populations of photons or other particles.

ABSTRACT
The spiders, in comparison with the majority of others animals, it has the ability to access to that kind of environment where others animals or even the humans can’t. Those attributes of the spiders are taken into this project in order to design and develop a quadruped spider robot in conditions to move in all kind of directions and perform such movement like ascend or descend. The paper is presented the dynamic and kinematics model with the purpose of understand how, mathematically, a quadruped animal and a spider walk. In this case we have studied the movement of a real spider, so we can define a suitable bio-mimetic model for our robot. Similarly, the motion simulation was implemented and the results are shown.

ABSTRACT
Agriculture serves as a fundamental pillar of Nigeria's economy. A significant portion of the available freshwater resources is allocated to agricultural activities. In Northern Nigeria, irrigation systems are essential. Over the years, farming practices have remained largely primitive, particularly in sub-Saharan Africa. This situation arises from a lack of advanced technological knowledge that could enhance agricultural practices. Various challenges hinder agricultural practices, including reliance on traditional farming methods, limited understanding of concepts and practices, policy issues, environmental concerns, and financial constraints. The purpose of this study was to optimize an IoT-based model for smart agriculture and irrigation water management. The study aimed to design, implement, test, and evaluate the performance of this optimized IoT-based model. The proposed system utilized the prototyping model as its methodology. The design was created using the Balsamiq application. The system is intended to feature a login page, a dashboard, a system use case diagram, an actuators page, a sensor page, and an application interface design. The Justinmind tool was employed to illustrate the flow of information within the system, encompassing data input and output, data storage, and all subprocesses through which the data traverses. The optimized IoT model was developed using four primary platforms: the ReactJS frontend application development platform, Amazon Web Services IoT Core for the backend, the Arduino development platform for sensor node creation, and the Python programming language for the actuator node based on the Raspberry Pi board. When compared to existing systems using the specified parameters, the optimized model demonstrates superior performance, particularly in terms of measurement accuracy, irrigation water management, operational modes, platform accessibility, real-time video capabilities, user-friendliness, and overall efficiency. The perform

ABSTRACT
sickle cell disease is a genetic condition characterized by abnormal red blood cell morphologies. It can be quite challenging to identify and monitor its response to treatment. Although deep learning-based models exhibit great potential in medical image processing, existing approaches often fail to cope with variability in sickle cell morphology. Additionally, publicly available sickle cell datasets tend to have a few samples with imbalanced classes. To mitigate the above challenges, we propose using the synthetic minority sampling technique (SMOTE) mechanism to handle class imbalances and a deep CNN architecture that aims to capture complex patterns and descriptive features in a newly created low-resolution sickle cell dataset from hospitals in eastern Uganda. This could help improve the efficiency of the diagnosis and classification of the disease. We performed experiments and examined several algorithms in the literature for related tasks. Based on the evaluation results, the proposed SMOTE-based DL-SCD outperforms the best baseline, its variant without the SMOTE component, with a 2.06% increase in classification accuracy. SDL-SCD could help to conveniently and early detect sickle cell anemia, especially in low-developed settings where medical services are constrained. Our code is accessible at https://github.com/MarthaKJ/sickle-cell-detection-using-nvidia.