A thesis submitted in fulfilment of the requirements for the degree of Master of Science Computer Science in the School of Computer Science. Faculty of Science November 21, 2016. / There is stiff competition for customers and market share in the South African telecommunications industry amongst the four predominant mobile service providers, namely Vodacom, MTN, Cell C and Telkom Mobile. The First National Bank (FNB) through one of its entities, FNB Connect, has also joined this intensely competitive environment. These companies face a constant challenge of having to come up with new and innovative ways of attracting new customers and retaining their current ones. Cell C has embarked on a good strategy of claiming solid market share and growing itself against the competition by using the Private Label Promotions (PLP) group, a leading BEE Level 3 company that provides a variety of business solutions, to market GetMore, its value-added service package. A recommender system could be used to suggest and promote the items available in this package to existing and potential clients (users). There are different approaches to recommendation, the most widely used ones being the collaborative and content-based recommendation. The collaborative filtering approach uses the ratings of other users to recommend the items the current (active) user might like. In the content-based approach, items are recommended in terms of their content similarity to items a user has previously liked, or elements that have matched a user’s attributes (features). Hybrid recommendation approaches are used To eliminate the drawbacks individually associated with the CF and CBF approaches and to leverage their advantages. One of the aims of this research was to design and implement a prototype hybrid recommender system that would be used to recommend Cell C’s GetMore package to current and potential subscribers. The system was to implement matrix factorisation (collaborative) and cosine similarity (content-based) techniques. Several experiments were conducted to evaluate its performance and quality. The metrics used included Mean Absolute Error (MAE), Root Mean Squared Error (RMSE) and Area Under the ROC Curve (AUC). We expected the proposed hybrid recommender system would leverage the advantages provided by its different components and demonstrate its effectiveness in providing Cell C’s customers with accurate and meaningful recommendations of its GetMore package services. Keywords: Content-based Recommendation, Collaborative Recommendation, Hybrid Recommendation, Cosine Similarity, Matrix Factorisation, Association Rule Mining, J48 Classifier, Decision Table, Naive Bayes, Simple K-means, Expectation Maximization, Farthest First, Predictive Apriori / LG2017

M. Tech. Information Technology / Voting is a widely spread and democratic way of making decisions. For centuries, South Africa has been using the popular paper-based voting system though it does not provide the desirable blend of accessibility and efficiency. Missing ballot papers, invalid votes and miscount are some of the challenges that come with the paper-based voting system. Time is precious to everyone and correct information is even more precious in the fast-paced information technology era. Merging all these together we look in for easier, effective, efficient and time managing way of casting a vote. Mobile phones facilitate communication and rapid access to information and their diffusion has reached a larger proportion of the population in a short period of time. In this thesis, we propose designing and developing a mobile phone voting system, which allows users to vote spontaneous and timeous, using existing mobile phone networks and technologies via their mobile phones.

Second economy people in developing countries are people living in communities that are underserved in terms of basic amenities and social services. Due to literacy challenges and user accessibility problems in rural communities, it is often difficult to design user interfaces that conform to the capabilities and cultural experiences of low-literacy rural community users. Rural community users are technologically illiterate and lack the knowledge of the potential of information and communication technologies. In order to embrace new technology, users will need to perceive the user interface and application as useful and easy to interact with. This requires proper understanding of the users and their socio-cultural environment. This will enable the interfaces and interactions to conform to their behaviours, motivations as well as cultural experiences and preferences and thus enhance usability and user experience. Mobile phones have the potential to increase access to information and provide a platform for economic development in rural communities. Rural communities have economic potential in terms of agriculture and micro-enterprises. Information technology can be used to enhance socio-economic activities and improve rural livelihood. We conducted a study to design user interfaces for a mobile commerce application for micro-entrepreneurs in a rural community in South Africa. The aim of the study was to design mobile interfaces and interaction techniques that are easy to use and meet the cultural preferences and experiences of users who have little to no previous experience of mobile commerce technology. And also to explore the potentials of information technologies rural community users, and bring mobile added value services to rural micro-entrepreneurs. We applied a user-centred design approach in Dwesa community and used qualitative and quantitative research methods to collect data for the design of the user interfaces (graphic user interface and voice user interface) and mobile commerce application. We identified and used several interface elements to design and finally evaluate the graphical user interface. The statistics analysis of the evaluation results show that the users in the community have positive perception of the usefulness of the application, the ease of use and intention to use the application. Community users with no prior experience with this technology were able to learn and understand the interface, recorded minimum errors and a high level of v precision during task performance when they interacted with the shop-owner graphic user interface. The voice user interface designed in this study consists of two flavours (dual tone multi-frequency input and voice input) for rural users. The evaluation results show that community users recorded higher tasks successes and minimum errors with the dual tone multi-frequency input interface than the voice only input interface. Also, a higher percentage of users prefer the dual tone multi-frequency input interface. The t-Test statistical analysis performed on the tasks completion times and error rate show that there was significant statistical difference between the dual tone multi-frequency input interface and the voice input interface. The interfaces were easy to learn, understand and use. Properly designed user interfaces that meet the experience and capabilities of low-literacy users in rural areas will improve usability and users‟ experiences. Adaptation of interfaces to users‟ culture and preferences will enhance information services accessibility among different user groups in different regions. This will promote technology acceptance in rural communities for socio-economic benefits. The user interfaces presented in this study can be adapted to different cultures to provide similar services for marginalised communities in developing countries

Copper cable theft (CCT) has a devastating effect on the South African economy, and essential services such as TELKOM, ESKOM AND TRANSNET have been seriously disrupted, due to CCT. This dissertation focuses on the value of the cell phone record as a source of intelligence during (CCT) investigations. The cell phone industry is growing each year, and millions of people worldwide possess a cell phone. Some of these people are involved in criminal activities – which mean that cell phones, with their advanced capabilities, hold evidence which relates to crime. The activation of cell phone activity is contained on a cell phone record, and, when analysed, such information becomes intelligence which has a positive impact on CCT investigations. The purpose of this study is to assist and give guidance to investigators, in order to analyse the cell phone record(s) of CCT thieves. / Criminology and Security Science / M. Tech. (Forensic Investigation)

Copper cable theft (CCT) has a devastating effect on the South African economy, and essential services such as TELKOM, ESKOM AND TRANSNET have been seriously disrupted, due to CCT. This dissertation focuses on the value of the cell phone record as a source of intelligence during (CCT) investigations. The cell phone industry is growing each year, and millions of people worldwide possess a cell phone. Some of these people are involved in criminal activities – which mean that cell phones, with their advanced capabilities, hold evidence which relates to crime. The activation of cell phone activity is contained on a cell phone record, and, when analysed, such information becomes intelligence which has a positive impact on CCT investigations. The purpose of this study is to assist and give guidance to investigators, in order to analyse the cell phone record(s) of CCT thieves. / Criminology and Security Science / M. Tech. (Forensic Investigation)