ANGOLE Okelo Richard
Ontology-Based Model for Integrating Knowledge of Modern and Traditional Medicine

Mr. ANGOLE Okelo Richard developed ontology model for integrating complex knowledge of African traditional medicine and modern medicine. complex African Society; African Traditional Medicine (ATM) is used in parallel to Modern medicine (MM). Various attempts have been made to bridge the gap between ATM and MM in order to harmonize treatment and to create an equal form of therapeutic cooperation but in vein due to lack of formal structure and complexity of the knowledge. each practitioner has their own terminologies and ways of providing healing services unlike Knowledge generated from Modern medicine which is structured. Therefore, ATM knowledge is isolated and mistrusted yet a lot of knowledge is generated in the practices which could be used across the whole health sector. In addition, modern medicine alone does not provide whole health needs of patients and the drugs are characterized by having undesired side effects, ATM provides holistic health intervention. ATM treats the body, the mind and the spirit. There is need to come up with a better technology to handle this complex structure of medical knowledge which the current artificial Intelligent (AI) systems used in e-health cannot manage. The model developed bush the backend of AI to handle complexity in medical knowledge. The work was supervised by Assoc Prof. Gilbert Maiga and Dr George Wiiliam Okori.

ATUHURIIRE Marriette Katarahweire
Form-based Data Security in Mobile Health Data Collection Systems in Low-Resource Settings

Ms. ATUHURIIRE Marriette Katarahweire investigated security challenges in mobile health data collection systems deployed in low-resource settings. It was found out that data in MHDCS are diverse and have varying security requirements depending on their sensitivity levels. Particular emphasis was on incorporating security controls early in the development process through electronic forms to be used for data collection, and according to sensitivity levels of the data. A data sensitivity model was developed that takes into consideration both static and dynamic parameters for data sensitivity and categorizes data into different sensitivity levels using parameters defined by the stakeholders. Use of the model enables developers to design and build mobile health data collection systems that adhere to the security goals of confidentiality, integrity and availability. This is expected to reduce the potential threats and increase the confidence and adoption of eHealth services. The study was funded by NORAD and was supervised by Assoc Prof Engineer Bainomugisha and Assoc Prof Khalid Azim Mughal.

KAMUKAMA Ismail
A model for spatial variability of typhoid disease incidences in Uganda

Mr. KAMUKAMA Ismail integrated clinical, environmental and demographic data to explore spatial variability of typhoid disease incidences in Uganda for the period 2012 to 2017 using data science method. The study first explored spatial-temporal trends and distribution patterns of typhoid disease incidences at both regional and national levels in order to gain initial disease burden insights in the population. The study then revealed highest incidences and clustering of the disease in the central region, followed by Western, Eastern and Northern regions throughout the study period. Geographically Weighted Regression model revealed that poor handwashing practice was mainly influencing disease occurrences in Northwestern, Northern and Northeastern parts of the country. Excessive rainfall was most responsible for disease occurrences in the Eastern, Central and Southern parts of the country. Poor drainage was mainly influencing disease occurrences in the Western, Central and Southern parts of the country. This knowledge is essential for planners and decision-makers to: efficiently plan, enforce preventive measures and make targeted interventions, which eventually reduce disease surveillance costs. The study was funded by SIDA and supervised by Assoc Prof. Gilbert Maiga, Dr. Denis Ssebuggwawo and Dr. Peter Nabende.

KAMULEGEYA Grace Bugembe
Characterization of Practices and Measurements in Software Start-ups in an Emerging Ecosystem

Mr. KAMULEGEYA Grace Bugembe, through case studies investigated and characterized software hub operations and software start-up practices, and growth-tracking metrics in the emerging East Africa start-up ecosystem. His study characterized the operations of hubs in East Africa as not much had been established about how hubs nurture software start-ups. He also established that software start-ups indeed measured but adopted and adapted some practices and metrics used in start-ups in developed ecosystems. He designed and developed a progress measurement dashboard that start-ups can use to monitor their key growth metrics. He also iteratively derived 10 dimensions that can be used to influence and distinguish metrics used in software start-ups and mature software companies. The compiled hub practices can be used by existing and new hubs to benchmark their operations against the successful hubs in the East African region. The growth metrics will enable software start-ups to track the important aspects of their businesses in the different stages as they grow. This study was funded by SIDA and Supervised by Prof Regina Hebig and Dr. Raymond Mugwanya.

MBABAZI Ruth Mutebi
Designing Persuasive Technologies For Societal Benefit: A Persuasive Technology For Fighting Electricity Theft In Kampala, Uganda

Ms. MBABAZI Ruth Mutebi studied persuasive technology design frameworks, with the aim of developing a technology that could aid in reducing electricity theft in Kampala Uganda. After conducting a survey, Ruth found that electricity consumers are not willing to fight electricity theft, despite its’ negative impact on them. She was modified Fogg’s Eight Step Process using design theory resulting into the Design Theory-Fogg’s Eight Step Process (DT-FESP). This was used to develop a persuasive mobile application to increase willingness to participate in fighting electricity theft called, “Faayo” Evaluation of “Faayo” showed that it had potential to persuade electricity consumers. The research demonstrated the feasibility of persuasive technologies and recommended that Umeme includes them in their electricity theft mitigation strategies. The study was funded by SIDA and was supervised by Dr Julianne Sansa-Otim and Prof. Sebitosi Ben.

NAKASI Rose
Automated Diagnosis of Malaria in Thick Blood Smear Films: Deep Neural Network Approach

Ms. NAKASI Rose investigated how deep learning algorithms can be used for the automated detection of malaria and its parasitemia determination in microscopic thick blood smear images. Using an experimental design, the study revealed that by exploiting recent technological advances in 3D printing and deep learning to produce effective hardware and software respectively, a functioning point-of-care diagnosis system for malaria on this principle, capable of running on multiple microscopes and phone combinations can be produced. A malaria parasite detection accuracy of over 98% as compared to conventional machine learning methods was achieved. This study contributes to the practical improved malaria diagnosis especially in highly endemic, but low-resource settings in the Sub-Saharan Africa, where there are few trained lab experts. Further, the diagnostic solutions developed in this study could be adapted for the general microscopy disease diagnosis. The study was funded by SIDA, and was supervised by Dr. Ernest Mwebaze and Dr. Aminah Zawedde.

NAMUJUZI Sylvia
Management of Agriculture Archives in National Agricultural Research Institutes in Uganda

Ms. NAMUJUZI Sylvia investigated gaps in the management of agriculture archives in National Agricultural Research Institutes (NARIs) particularly, documentation, maintenance and access. Using case study and descriptive designs, the study established that various agriculture archives existed in NARIs according to their specialties, but were largely in paper format including: Maps, Datasets, Institutional correspondences, Photographs and Government Acts and legislations, among others. However, most of these archival materials were not processed, classified, accessioned and catalogued leading to poor documentation, maintenance and access. Two major outputs of this study were: an evaluated Agriculture Archives Management Framework for closing the gaps and an Agriculture Archives Monitoring and Evaluation Tool for continuous process improvements in agriculture archives management. Further, the framework and the evaluation tool could be adopted by other Agricultural Institutions for the general management of agriculture archives in their possession. The study was funded by Carnegie and was supervised by Prof. Robert Ikoja-Odongo and Dr. Mary Basaasa Muhenda.

SANYA Rahman
Predicting Infectious Disease Density in Urban Settings using Convolutional Neural Networks

Mr. SANYA Rahman’s thesis explored applications of Convolutional Neural Networks (CNN) for modeling and analyzing spatial dynamics of human infectious diseases in low-income urban settings. This work integrates multiple and diverse data sources including housing density signals (used as proxy for indoor overcrowding) extracted from remote sensing satellite imagery, and socio-economic well-being, as predictors for disease density. Using Tuberculosis (TB) disease data from Uganda, the study found that CNN were promising for detecting and quantifying patterns in infectious disease density. This work is the first of its kind in exploring possibilities afforded by advances in deep learning algorithms and remote sensing data to enhance understanding of infectious disease processes. By doing so, it has expanded the frontiers of methods available for digital epidemiology. The study was funded by the African Development Bank and supervised by Dr. Ernest Mwebaze and Assoc Prof Gilbert Maiga.

Browse Citations by College below:

< Director’s Message | CAES | CoBAMS | CoCIS | CEES | CEDAT | CHS | CHUSS | CoNAS | CoVAB | LAW | MUBS >