The Nelson Mandela African Institution of Science and Technology
Institutional Repository

Research Collection
Select to browse Research collections.
Recent Submissions
Mechanism for detection and mitigation of address resolution protocol spoofing attacks in large-scale software-defined networks
(NM-AIST, 2025-03) Patrice,Laurent
Address Resolution Protocol (ARP) spoofing has been a long-standing problem, with no clear remedy until now. The attacks can be launched easily, utilizing an enormous number of publicly available tools on the web. However, they are extremely tough to counterattack due to ARP's stateless nature for not authenticating ARP replies for subsequent requests. Previous studies have demonstrated significant efforts to counterattack these assaults in Software Defined Networks (SDN). However, they mainly focused on detecting the assaults, with little effort being made to address performance bottlenecks, scalability, and Single Point of Failure (SPOF) issues in large-scale LANs. This study focuses on developing ARP spoofing attacks detection and mitigation mechanism in large-scale SDN that is resistant to SPOF, performance bottlenecks, and scalability constraints. It enables controllers to intercept and analyze incoming ARP packets, learn address mappings, and store them in the application’s memory for ongoing ARP cache comparisons while maintaining a global ARP cache in the controller. Simulation experiments were carried out in a closed network environment to
precisely monitor network traffic and result patterns. Mininet and Open Network Operating System were used to implement the data plane and OpenFlow-based control plane, respectively. The results show that the proposed solution is resistant to ARP spoofing attacks, with an average detection and mitigation time of 4.3 and 26.19 milliseconds, respectively. Further significant improvement has been observed in alleviating SPOF, performance bottlenecks, and scalability constraints. Further improvement can be done to enhance the proposed solution to counterattack multiple types of assaults through machine learning models.
Machine learning model for early detection of sexually transmitted infections
(NM-AIST, 2025-07) Shija,Juma
Sexually Transmitted Infections are diseases transmitted mostly through unprotected sex with an infected partner. Every day, about one million people throughout the world get sexually transmitted infections. The most vulnerable groups in Tanzania are commercial sex workers, truck drivers who travel long distances and grocery and hotel workers. Common sexually transmitted infections in Tanzania are Gonorrhoea, Syphilis, Chlamydia and Trichomoniasis. The STIs have several effects if they are not cured on time or use the wrong medications. The STIs can induce infertility or sterility, make the body prone to more serious diseases like HIV, and even cause death. The stigma and humiliation associated with sexually transmitted infections create significant hurdles to seeking effective diagnosis and treatment. This study aimed to develop a machine learning model integrated into a web application to facilitate seamless communication between patients and health centres, specifically addressing communication challenges between sexual health clinics and STI patients. Both qualitative and quantitative research methods were employed in the study. Qualitative data were gathered through interviews with health practitioners and ICT officers from the respective hospitals, while quantitative data were collected using survey questionnaires from four hospitals, supported by the Government of Tanzania Health Operation Management Information System (GoT-HoMIS). Dataset with features which included several STI symptoms and the label features which are laboratory diagnosis results. The model was trained on a local dataset using five machine learning algorithms: AdaBoost, Support Vector Machine (SVM), Random Forest, Decision Tree, and Stochastic Gradient Descent (SGD). In this study, results revealed that the highest accuracy score was 97.45% and the F1 score of 97.70% from the AdaBoost classifier. Thus, the model from the AdaBoost algorithm was serialised for integration with the web app. The validation of the web app system was done with a higher number of people recommending the system to be used in the Health Information Management System. The developed machine learning model can benefit policymakers and health practitioners by using telemedicine to enable remote diagnosis and patient monitoring. Apart from telemedicine, the model can remove stigmatisation barriers among STI patients. And lastly, a machine learning-powered system can increase patient adherence to medication and treatment strategies by anticipating future noncompliance and offering timely reminders or interventions.
Assessment Of The Influence Of Business Practices On Start-Up Performance: The Case Of Selected Municipalities In Dar-Es-Salaam City
(NM-AIST, 2025-07) Wanyancha, Mwita
Startups are critical engines of innovation, employment, and inclusive economic growth. In Tanzania, Dar es Salaam accounts for over 66% of the nation's startups, yet approximately 70% fail within the first three years. Despite increasing support mechanisms, little empirical evidence exists on how contextual business practices shape startup performance in urban African settings. Guided by Entrepreneurial Event Theory, Action Theory, and Strategic Resource Management Theory, this study assessed the influence of Business Behavioral Practices, Regulatory Practices, and Business Resource Management Practices on startup performance in Dar es Salaam. A quantitative, cross-sectional design was adopted, with data collected from 244 startup founders across five municipalities using structured questionnaires. Statistical analyses included descriptive statistics, factor analysis, Pearson correlation, and multiple regression. Results indicate that Business Behavioral Practices, particularly innovation, proactiveness, and competitive aggressiveness, positively influence startup performance, while high risk aversion hinders growth. Regulatory Practices showed mixed influence, with strategic engagement supporting performance, but challenges remain in adaptation and awareness. Business Resource Management Practices emerged as the most significant predictor, with financial planning, human capital development, and supply chain coordination strongly linked to startup success. The study provides actionable insights for entrepreneurs to adopt more insight driven behavioral practices, for policymakers to strengthen regulatory frameworks that support startup growth, and for ecosystem enablers including incubators, accelerators, universities and NGOs to enhance resource-based support systems and capacity-building initiatives. The findings underscore that startup performance is shaped not just by external resources, but by how effectively local business practices are integrated into strategic execution.
Socioeconomic Determinants Of Household Access To Clean Water: A Case Study Of A Selected Peri-Urban Ward In Northern Tanzania
(NM-AIST, 2025-08) Ngayaga, Mwahija
Access to water is essential to sustain human and ecological life. Despite the acclaimed crucial importance of clean water for human and ecological life and sustenance, most communities in sub-Saharan Africa, Tanzania included, still lack clean and safe water. This study highlights the need to investigate socio-economic factors that influence the achievement of the desired clean water for peri-urban dwellers who depend on piped and tap water. The current study was carried out in Kikwe ward, Arusha, Tanzania. Mixed methods guided by a cross-sectional research design were employed. Data was collected via a survey, with 353 questionnaires
personally administered to respondents. Quantitative data analysis techniques, including descriptive and inferential statistics, were employed in the analysis. Qualitative data was collected through key informant interviews and analyzed thematically. The results from the current study indicate that 29.2% of the study participants had access to clean water. Furthermore, household income, paying water bills, and engaging in water-dependent activities had a significant relation with clean water accessibility. The findings highlight significant disparities in water accessibility and safety in the surveyed community. The village-by-village
analysis indicates that 71.6% in Nambala had their households connected to piped water. For Kikwe, 84.8% depended on centralized community access points. Furthermore, 90.7% of Karangai indicated that their main water source was rivers. Overall, 15.3% had access to treated water, there are potential health risks, such as exposure to waterborne diseases. While Nambala showed better access to piped water, most other areas relied heavily on centralized community access points or riverine sources. This underscores the urgent need for improved water infrastructure and public education on safe water practices. The study concluded that there is a need for women's inclusion in decision-making on clean water accessibility. Therefore, there is a need for enhancing education and awareness initiatives, increasing investment in water infrastructure, including rainwater harvests, and accelerating the implementation of water projects to safeguard and promote the well-being of peri-urban communities.
Age-Stratified Spatial Radiological Risk Assessment of 226Ra 232Th and 40K in Water Surrounding the Geita Gold Mine in Tanzania
(MDPI, 2025-09-26) Mwimanzi, Jerome; Haneklaus, Nils; Lolila, Farida; Marwa, Janeth; Rwiza, Mwemezi; Mtei, Kelvin
Long-term ingestion of water contaminated with naturally occurring radioactive material
(NORM) may pose health risks. Water around the Geita Gold Mine in Tanzania was assessed
by high-purity germanium gamma spectrometry to quantify the activity concentrations
of 226Ra, 232Th, and 40K, and computed age-stratified ingestion doses and risk indices
were determined. The average activity concentrations were 57 mBq L−1 for 226Ra and
5026 mBq L−1 for 40K, while the activity concentrations of 232Th were below the detection
limit in all samples. The estimated adult fatal cancer risk ranged from 0.9 × 10−6 to
3.1 × 10−6 (mean 2.0 × 10−6). The excess lifetime hereditary effect ranged from 2.0 ×
10−6 to 7.3 × 10−6 for males (average 4.5 × 10−6 ± 1.5 × 10−6) and 2.1 × 10−6 to 7.7
× 10−6 for females (average 4.8 × 10−6 ± 1.6 × 10−6). One-way ANOVA and Pearson
correlations indicated significant spatial variation in activities and indices across sites and
age groups. Under current conditions, waters appear to be radiologically safe. However,
mine-adjacent hotspots warrant targeted surveillance. The obtained results provide a
baseline for sound monitoring approaches at the Geita Gold Mine and other mines showing
similar activity profiles.