This research delves into the innovative application of feed-forward neural networks (FNNs) specifically the multi-layer perceptron (MLP). MLP is a flexible algorithm due to its ability to adapt to different realworld problems amongst other features, and this makes it a preferred machine learning algorithm in the early detection of mental health disorders. MLP’s number of layers and the number of neurons per layer changes to accommodate these abilities. MLP was chosen for this work becau...
Abstract: Smart societies have an increasing demand for quality-oriented services and infrastructure in an industrial Internet of Things (IIoT) paradigm. Smart urbanization faces numerous challenges. Among them, secured energy demand-side management (DSM) is of particular concern. The IIoT renders the industrial systems to malware, cyberattacks, and other security risks. The IIoT with the amalgamation of big data analytics can provide ef cient solutions to such challenges. This paper propose...
Abstract: Technological advances for low-cost Wi-Fi applications such as ‘the wireless sensor network (WSN) deployment’ are at an advanced stage of acceptance, especially in smart home environments. The application of this kind of network is referred to as a wireless sensor home network (WSHN). In literature, the evaluation of customers' home wireless network performance level is usually done via real-time experiment or by experience to test the network’s performance, leading to networ...
Abstract: Physical layer security (PLS) is considered as a promising technique to prevent information eavesdropping in wireless systems. In this context, cooperative relaying has emerged as a robust solution for achieving PLS due to multipath diversity and relatively lower transmission power. However, relays or the relay operators in the practical environment are unwilling for service provisioning unless they are incentivized for their cost of services. Thus, it is required to jointly consid...
Abstract: Energy consumption has risen to be a bottleneck in wireless sensor networks. This is caused by the challenges faced by these networks due to their tiny sensor nodes that have limited memory storage, small battery capacity, limited processing capability, and bandwidth. Data compression has been used to reduce energy consumption and improve network lifetime, as it reduces data size before it can be forwarded from the sensing node to the sink node in the network. In this paper, a surv...
Abstract: Automatic Sign Language Recognition (ASLR) helps with converting hand gestures to spoken language, therefore, enabling communication between those able to hear and those unable to hear. There is abundant research work on ASLR of British Sign Language and American Sign Language. However, Botswana Sign Language has received less attention at least in terms of computational representation leading to automatic sign language recognition which can be attributed to lack of a Botswana ...
Abstract: The explosive growth of biological sequences over the last decade has consequently led to a lot of research on effective techniques for storing and analysing this big data. Generating Deoxyribonucleic Acid (DNA) sequences has become more reliable, faster, easier and cheaper due to latest sequencing technology leading to big data sequences. This poses a challenge to efficient analysis to such massive sequences. Advanced indexing algorithmic techniques are required to facilitate effi...
Abstract: This research presents a new approach in modeling and implementing a framework for linear image change detection using Field Programmable Gate Arrays (FPGA) based implementations. Detecting changes between digital images of the same location or region of interest have attracted huge interest in research due to its wide range of applications such as medical diagnosis, astronomy and forensics. In recent years, the steady increase in the use of hardware implementation in image pr...
Abstract: This thesis addresses the problem of biometrics security and accuracy through the fusion of fingerprint and face images. The Biometrics community in recent years came up with different approaches to improve the accuracy and security of systems. Multimodal authentication has attracted a lot of attention because of its advantage over single biometrics matchers. Even though efforts were made to improve these systems, they are, however, still vulnerable to security threats such as spoo...
Abstract: Unmanned Aerial Vehicle (UAV) swarms are not common due to lack of readily available coordinated protocols and applications for synchronizing UAV swarms in outdoor environments. To solve the problem, this study design, implement, and evaluate a leaderfollower Unmanned Aerial Vehicle Swarm Synchronization Protocol (UAVSSP). Unlike other studies that deal with UAV swarm synchronization, this study introduces the concept of pair correlation and back propagation communication scheme am...
Abstract: The use of electronic voting systems (EVS’s) is seen as an alternative to traditional manual voting because it aims at increasing efficiency, lowering cost of running election, reducing counting mistakes and improving the accuracy of the results. This has led to electronic voting systems being adopted in most countries to replace traditional paper-based voting systems. Currently, Botswana uses a traditional paper-based voting system. This method of voting comes with several chall...
Abstract: The use of cattle disease diagnosis expert systems has the ability to improve the cattle production as they would help in disease control. Particularly if the system is usable, that is, if it is efficient, effective, satisfying and requires less effort to use. Cattle disease diagnosis expert systems have been adopted in recent years in the cattle production industry particularly in Asian countries like China. However, the usability of these systems still remains a challenge. There...
Abstract: Over the past years the use of unmanned aerial vehicle (UAVs) swarms has increased drastically. Multiple cooperative unmanned aerial vehicles have introduced numerous possibilities of performing several tasks, saving time, money and impediments. However, even though they are making life easier unequal responsibility propagation amongst unmanned aerial vehicles in a swarm is the biggest detriment that has resulted in inconsistent battery consumption. Missions have failed as a re...
Abstract: Object recognition using Unmanned Aerial Vehicles (UAVs) is increasingly becoming more useful. Tremendous success has been achieved on UAV object recognition in clear weather conditions where adequate illumination makes it easier for UAVs to recognize objects in the scene. Unfortunately, for outdoor applications, there is no escape from bad weather moments such as haze, fog, dust, smoke and smog. These weather nuisances occur due to suspended particles in the atmosphere, ultimately...
Abstract: The intention in Wireless Sensor Networks (WSNs) is to group sensed raw facts from geographical area under monitoring. Yet, sensor nodes sometimes report tempered (falsified) information resulting from malicious nodes. Hence, various studies recommend pre-identification of malicious node as essential for reliable and healthy networks. Different techniques have been proposed to deal with bogus sensor nodes in WSNs, ranging from authentication to trust based approaches. In this ...