Senior Theses and Projects

Permanent URI for this collection


Recent Submissions

Now showing 1 - 5 of 348
  • Item
    Designing wearable obstacle detection and avoidance technology for the visually-impaired
    (2021-05) Segbefia, Tamisha Dzifa
    Assistive technology for the visually impaired is developed regularly, but many of these solutions are either bulky, difficult to maneuver, or expensive. Visually impaired people need a way to avoid obstacles and move around in safety. Due to limited visibility, the person cannot tell with confidence if there is an obstacle approaching them. This project proposes a wearable obstacle and avoidance system for the visually impaired housed on an embedded microcontroller. The system consists of both RFID and sonar localization techniques for static and dynamic obstacles. Both approaches work well in terms of obstacle detection and avoidance, but further research is needed to integrate the processes to complement each other fully. A simultaneous localization and mapping (SLAM) approach, though computationally expensive, is also considered. The results show that it is possible to combine both RFID and sonar localization; however, this approach might be better suited for a less constrained system.
  • Item
    Cattle tracking with LoRa and machine learning
    (2021-05) Mabuza, Sula Thembumenzi
    To curb the increase in livestock theft in Sub-saharan countries, this project looked at machine learning applications like cattle tracking on a farm. Received signal strength indicators from home available WiFis were utilized to fingerprint locations on the farm. Where WiFis were not available, ESP866 Node MCUs were used to deploy access points. These ESP8266 Node MCUs were also given SSIDs that could easily be used for classification using the SSIDs as labels in the program. Two classifiers were explored, the support vector machine (SVM) and the Decision Tree. A linear kernel with a very low gamma value of 0.001 was used for the SVM classifier. The decision tree classifier yielded an average accuracy of 0.89683659, while the support vector machine yielded an average accuracy of 0.915699. The SVM classifier emerged as a suitable classifier to use to achieve reliable accuracy in cattle tracking. Lora proved to be an essential tool in wireless communication of the prediction results from the pendant/transmitter designed to the receiver, hence enhancing mobility in tracking. Future works include incorporating distance calculation to make the tracking process more straightforward and efficient. Sensor nodes that will further provide the machine learning algorithm designed with unique data values will also be incorporated to compensate for longer farms that might need the deployment of more Node MCU access points. This is an effort to maintain low costs in tracking using the solution provided by this project. Therefore, the solution presented by this project proved to be feasible.
  • Item
    Developing a micropatterned surface to prevent bacterial adhesion
    (2021) Omole, Oluwatobiloba
    Hospital Acquired Infections (HAIs), also commonly referred to as Nosocomial infections, present a significant problem to hospitals around the world. The problem is more pronounced in African hospitals due to the lack of thorough and efficient sanitation and hygiene practices. They present a substantial danger to infants in neo-natal care who do not have well developed immune systems. Hospital acquired infections also pose a significant economic and social problem in urban areas. Although a wide range of pathogens can cause nosocomial infections, bacteria is responsible for a larger number of infections. With this in mind, a safe, effective and cost-effective solution is essential to minimize the occurrence of nosocomial infections. The strategy employed will be to try to reduce bacterial colonies in hospitals to prevent infection by bacteria. Natural fibres have been documented to exhibit anti-microbial action and they are also very cheap. The creation of a mat using such fibres that can be used in hospitals to reduce bacterial growth will form the basis of the solution.
  • Item
    Optimization of epoxy-based coir fibre composites for roofing sheets in Ghana
    (2021-05) Barley, Ivana Ayorkor
    Contemporary roofing materials in Ghana such as aluminium and zinc are quite costly. Metal roofing sheets require large amounts of energy to manufacture which affects the sustainability of them. Also, coastal areas in Ghana that rely on metal roofing sheets are subjected to corrosion and loud noise during rains. Traditional roofing materials such as palm leaves and straws need periodic maintenance and are also labour intensive to install. Thus, a sustainable alternative to current roofing methods is needed in Ghana. In this project, coir fibre reinforced eposy composites were created as substitute roofing sheets. The coir fibres were first treated with sodium hydroxide solution. The fibres were cut into lengths while considering the critical fibre length. The coir fibres were mixed at different weight ratios with eposy-hardener matrix and allowed to fully cure. The samples were loaded with thermal cycles to mimic the effect of thermal degration induced by the sun. The mechanical properties were analysed as well. Thermal conductivity, corrosion studies, and sound absorption tests were also performed on the composites while varying the coir composition in the epoxy matrix.
  • Item
    Billing and location tracking app for transportation
    (2021-05) Owusu, Stephen Kwadwo Yiadom
    Most companies in Ghana provide their staff with buses to make transportation more accessible, but this transportation medium is not tracked, making its operations difficult for staff. Means of payment become a problem when the staff has a higher denomination. This project aims to solve these problems by adapting the tracking technology based on GPS and the cashless payment system based on RFID. Using these technologies, this project will make tracking and payment on these company buses easy. This project goes beyond tracking to estimating the arrival time of the bus and beyond RFID payment to tracking user pickup and endpoints. This system is flexible and allows users to make payments with cash and make payments by scanning a QR code.