Makhulu Relebogile Langa

This paper applies a Convolutional Neural Network (CNN)-based vehicle security enhancement model, with a specific focus on the South African context. While conventional security systems, including immobilizers, alarms, steering locks, and GPS trackers, provide a baseline level of protection, they are increasingly being circumvented by technologically adept adversaries. These limitations have spurred the development of advanced security solutions leveraging artificial intelligence (AI), with a particular emphasis on computer vision and deep learning techniques. This paper presents a CNN-based Vehicle Security Enhancement Model (CNN-based VSEM) that integrates facial recognition with GSM and GPS technologies to provide a robust, real-time security solution in South Africa. This study contributes a novel integration of CNN-based authentication with GSM and GPS tracking in the South African context, validated on a functional prototype.The prototype, developed on a Raspberry Pi 4 platform, was validated through practical demonstrations and user evaluations. The system achieved an average recognition accuracy of 85.9%, with some identities reaching 100% classification accuracy. While misclassifications led to an estimated False Acceptance Rate (FAR) of ~5% and False Rejection Rate (FRR) of ~12%, the model consistently enabled secure authentication. Preliminary latency tests indicated a decision time of approximately 1.8 s from image capture to ignition authorization. These results, together with positive user feedback, confirm the model’s feasibility and reliability. This integrated approach presents a promising advancement in intelligent vehicle security for regions with high rates of vehicle theft. Future enhancements will explore the incorporation of 3D sensing, infrared imaging, and facial recognition capable of handling variations in facial appearance. Additionally, the model is designed to detect authorized users, identify suspicious behaviour in the vicinity of the vehicle, and provide an added layer of protection against unauthorized access.

The widespread use of automobiles has revolutionized transportation and attracted a large population owing to their convenience and effectiveness. However, this widespread adoption has resulted in a significant increase in road traffic accidents. The alarming road fatalities suggest that medical responders are overwhelmed by the need to save lives in a timely manner. This is due to a lack of affordable autonomous detection and notification mechanisms. Prior work in this domain includes the use of vehicular ad hoc networks, Arduinos, and Raspberry Pis; machine-learning approaches for predictions; and smart devices using integrated sensors. These methods are either expensive to acquire, human-reliant, or require vehicular modifications. Therefore, the aim of this study is to suggest a cheap prototype that can work with smartphones. The prototype should have embedded micro-electromechanical system (MEMS) sensors that measure g-force to find car accidents and global system for mobile communications-long term evolution (GSM-LTE) to call the closest medical responders, which would be found using GPS. A prototype was developed using the .NET Multi-Platform App UI (MAUI) framework. This study applied the design science research methodology (DSRM) to produce a socially acceptable, low-cost artifact similar to existing in-vehicle systems to save lives on the road during a road traffic accident. The FEDS evaluation of the results indicated that smartphones can perform such complex tasks with reasonable accuracy compared with expensive in-vehicle systems. The prototype can be adopted by lower- to middle-class individuals as it is a cheaper alternative. This study makes a practical contribution to the society by utilizing artifacts to ensure road safety.

Limpopo, one of South Africa's nine provinces, is mostly rural, where agriculture serves as the primary occupation for around 89 percent of the total population. Agriculture relies on water, making it its most valuable asset. Through irrigation, water is supplied to crops for growth, frost control, and crop cooling. Irrigation can occur naturally, as with precipitation, or artificially, as with sprinklers. However, artificial irrigation is wasteful as it is regulated and monitored through human intervention, leading to water scarcity which is one of the obstacles that threatens the agricultural sector in the province of Limpopo. A machine learning precipitation prediction algorithm optimizes water usage. The paper also describes a system with multiple sensors that detect soil parameters, and automatically irrigate land based on soil moisture by switching the motor on/off. The objective of this paper is to develop an automated farming irrigation system that is both efficient and effective, with the intention of contributing to the resolution of the water crisis in the province of Limpopo. The proposed solution ought to be capable of decreasing labour hours, generating cost savings, ensuring consistent and efficient water usage, and gathering informed data to inform future research. Thus, farmers will have greater access to information regarding when to irrigate, how much water to use, weather alerts, and recommendations. In acquiring these, the ARIMA model was applied alongside DSRM for implementing the mobile application. The results obtained indicate that the use of AI and IoT (AIoT) in agriculture can improve operational efficiency with reduced human intervention as there is real-time data acquisition with real-time processing and predictions.