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: Beneficiation of chalcopyrite and most minerals in general requires specific conditions and raw materials based on characteristics of the mineral to optimize processing hence income. Therefore characterization of minerals is an important aspect in mineral processing. In this investigation X-ray diffraction (XRD) and Scanning Electronic Microscope (SEM) techniques where applied on a sample of chalcopyrite. XRD was mainly applied to obtain phase compositions, lattice parameters hence...
Abstract: New generalized distributions namely Topp-Leone-G Power Series class of distributions, Marshall-Olkin-Exponentiated Odd Exponential Half Logistic-G family of distributions, Exponentiated Odd Exponential Half Logistic-G Power Series class of distributions and Marshall-Olkin-Type II-Topp-Leone-G family of distributions are presented. Properties of these generalized distributions including series expansion of density functions, hazard functions, quantile functions, moments, conditiona...
Abstract: Studies have linked herbal teas to the prevention of many diseases, leading to an increase in their use and demand which has endorsed an increase in their commercial activity and production. Consequently, performing a quality assessment of herbal teas in Botswana to determine their safety, medicinal and economical value has become of greater importance. The quality assessment tools used in this study entail: Antioxidant activity profiling using 2,2- diphenyl-1-picrylhydrazyl (D...
Abstract: Mixture models have gained popularity in statistical analyses because of their flexibility in cap turing local variations in heterogeneous populations. Model based approaches to classification use mixture models to fit data via maximum likelihood based approaches and provide labels to unlabelled observations. Over the years model based approaches have grown into an important sub-field of classification because they provide the uncertainty of classifying the unlabelled observations ...
Abstract: Network downtime is the period in which a computer system is unavailable or system fails to provide/perform its primary functions. System reliability and/or availability are very Key as an unavailable system is a failing system. It is very common is Botswana for government clients to forfeit being serviced because the government department system is down. The primary aim of this project was to investigate the causes of system/network downtimes in Botswana government department. Thr...
Abstract: In this article factors that affect the comminution behavior of heterogeneous diorite rocks obtained from two quarry locations in Botswana were investigated. Diorite rocks are in great abundance in Botswana and they are increasingly viewed as a relatively inexpensive and reliable alternative construction material to sustain the infrastructure growth in Botswana. The diorite rock samples collected from both the Central and North-Eastern districts were studied for structural similari...
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: In this thesis, the synthesis, optimization and application of a simple aflatoxin B1 (AFB1) specific extraction polymer sorbent based on molecular imprinting technology (MIT), for the selective pre-concentration of the potent AFB1 toxin from child weaning food, Tsabana manufactured in Serowe, Botswana is presented. As a food safety regulatory measure, the Tsabana must be cleared of the hazardous aflatoxins especially AFB1 before consumption as it is the most potent amongst those co...
Abstract: Liquid-liquid mixtures are ubiquitous in many natural and industrial processes. Their excess thermodynamic properties are governed by the intermolecular interactions. As such, experimental techniques such as neutron and x-ray diffractions, or computational chemistry methods can be used to probe structure at atomic level. However, they are rather scarce and expensive. Our interest is on the binary liquid mixtures involving 2,2′-difurylmethane (DFM) and n-alcohol, which have been s...
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: Antibiotic resistance genes (ARGs) and antibiotic resistant bacteria (ARB) have been globally considered emerging environmental contaminants that pose a serious concern to human health and the ecosystem. The ubiquitous nature of ARB and ARGs among pathogens from wastewater effluents, indicate that wastewater treatment facilities are major reservoirs for antibiotic resistance determinants, thus contributing to the widespread dissemination of antibiotic resistance. The primary object...
Abstract: The Banana Zone Cu-Ag Prospect is within the SW-NE trending Ghanzi-Chobe Belt (GCB), which extends from the Namibia-Botswana border in the south to Shinamba Hills in the north near the Botswana-Zambia border. The Banana Zone is also part of the Ghanzi Project owned by Khoemacau Copper Mining and situated between the Ghanzi and Maun townships, in Botswana. The Banana Zone has inferred resource of over 225.4 million metric tonnes (Mt) grading 0.64% Cu and 8.1 g/t Ag. The GCB consists...