http://ir.tum.ac.ke/handle/123456789/175 Contains PDF journal articles for this institute Sat, 13 Jun 2026 18:31:59 GMT 2026-06-13T18:31:59Z http://ir.tum.ac.ke/handle/123456789/17647 Deep learning models for the early detection of maize streak virus and maize lethal necrosis diseases in Tanzania Mayo, Flavia; Maina, Ciira; Mgala, Mvurya; Mduma, Neema Agriculture is considered the backbone of Tanzania’s economy, with more than 60% of the residents depending on it for survival. Maize is the country’s dominant and primary food crop, accounting for 45% of all farmland production. However, its productivity is challenged by the limitation to detect maize diseases early enough. Maize streak virus (MSV) and maize lethal necrosis virus (MLN) are common diseases often detected too late by farmers. This has led to the need to develop a method for the early detection of these diseases so that they can be treated on time. This study investigated the potential of developing deep-learning models for the early detection of maize diseases in Tanzania. The regions where data was collected are Arusha, Kilimanjaro, and Manyara. Data was collected through observation by a plant. The study proposed convolutional neural network (CNN) and vision transformer (ViT) models. Four classes of imagery data were used to train both models: MLN, Healthy, MSV, and WRONG. The results revealed that the ViT model surpassed the CNN model, with 93.1 and 90.96% accuracies, respectively. Further studies should focus on mobile app development and deployment of the model with greater precision for early detection of the diseases mentioned above in real life. 10.3389/frai.2024.1384709 Fri, 16 Aug 2024 00:00:00 GMT http://ir.tum.ac.ke/handle/123456789/17647 2024-08-16T00:00:00Z http://ir.tum.ac.ke/handle/123456789/17646 Mapping Population Densities and Waste Management Systems in Mombasa County Nyachiro, Asnath; Mgala, Dr. Mvurya Mombasa County is one of the five counties along the coastline of Kenya. Currently, Mombasa County has a human population of 1.2 million people, and the population is rapidly increasing through rural-urban immigration and natural births. However, the inadequacy of well-established waste management systems on the mainland and coastlines of the County is a threat to the well-being of the local residents. Poorly disposed of wastes both on land and at sea can lead to health problems not only for humans and terrestrial animals but also for aquatic animals such as fish, with the latter being one of the main sources of affordable proteins for poor coastal communities. This paper aimed to conduct a review of the spatial human population density of Mombasa County and the geospatial location of waste dumping sites and their proximity to settled areas. This literature review synthesized existing research on the application of Geographic Information Systems (GIS) and Remote Sensing techniques in mapping population densities and assessing waste management systems. The review began by examining studies that investigate population distribution patterns in urban and rural areas, utilizing GIS to analyze demographic data and satellite imagery. It explored methodologies used to estimate population densities, including dasymetric mapping, spatial interpolation, and land use classification techniques. Key findings were that limited studies have utilized GIS technologies to assess the population in Kenya. GRASP and Random Forest (RF) were the main techniques previously used to assess population densities in the rural Taita Hills area and along the coastal region. The population has exponentially increased in Mombasa County since the 1950s and is projected to increase further. Additionally, waste management in Mombasa County is majorly controlled by the county government. Ten geo-tagged waste collection spots were identified during the review, spread across the residential areas. In conclusion, the county should endeavor to employ GIS techniques to assess the rapid population change within the county and have targeted interventions to address the disparities in waste collection systems against population increase 10.24940/ijird/2024/v13/i6/JUN24050 Mon, 01 Jan 2024 00:00:00 GMT http://ir.tum.ac.ke/handle/123456789/17646 2024-01-01T00:00:00Z http://ir.tum.ac.ke/handle/123456789/17645 A Systematic Review of Computer Science Solutions for Addressing Violence Against Women in Educational Institutions Omar, Amina S.; Mgala, Mvurya : Approximately one in three women worldwide experience physical, mental, or sexual violence, making violence against women (VAW) a serious public health emergency. One of the main issues in educational institutions is violence against women. With the introduction of smart campuses and smart technologies, educational institutions are doing everything within their power to avert these kinds of incidents. Recent developments in computer science, such as artificial intelligence (AI), Internet of Things (IoT), and pattern recognition, have been essential in creating solutions meant to stop and react to VAW. This study presents a thorough systematic review from academic digital libraries from 2010-2023 of some of the initiatives that have been used to address the issue of violence against women. The state-of-the-art for these contributions is currently described in this document along with trends, architectures, technologies, and open problems. It highlights how these technological interventions are utilized for early detection, prevention, and response to incidents of VAW. The findings suggest a growing reliance on technology to create safer educational environments, but also emphasize the need for continued research, particularly in developing inclusive, ethical, and effective technological solutions. This review aims to inform stakeholders in the education and technology sectors about the current state of computer science applications in the fight against VAW, providing insights into best practices and areas for future development. 10.7753/IJCATR1307.1001 Mon, 01 Jan 2024 00:00:00 GMT http://ir.tum.ac.ke/handle/123456789/17645 2024-01-01T00:00:00Z http://ir.tum.ac.ke/handle/123456789/17644 A Machine Learning Model to Predict Suicidal Thoughts among Adolescent Girls with Access to Social Media. A Review of Literature Jepchirchir, Aseneth; Mgala, Mvurya; Mwakondo, Fullgence Suicidal thoughts is one of the leading factors that cause deaths among the adolescents and young adults. Suicidal thoughts have been ranked as the major cause of deaths among adolescents in Kenya. This paper presents a systematic review of literature on prediction of suicidal thoughts among adolescent girls with access to social media. The study adopted the snowballing methodology to review the relevant literature. This involved identifying relevant and current literature on modeling of suicidal thoughts. The initial set of relevant literature was obtained by searching using keywords such as social media, suicide, mental health, adolescents, self-esteem and algorithms. The process of conducting backward and forward snowballing which entail reference tracking and citation tracking respectively followed this. Boolean operators were used to narrow down the search to at least fifty research papers relevant to the topic of study. The databases that were used to search for the literature included Google scholar, Medline, TUM university catalogue, and Project MUSE. Findings from the literature review indicated that machine learning modelling could be used to predict suicidal thoughts. The results also showed that logistic regression, decision tree, AdaBoost, artificial neural network and random forest were the commonly used algorithms in predicting suicidal thoughts among adults and youths. AdaBoost had the highest prediction accuracy of 93%. However, most studies reviewed did not mention about adolescent girls in their research thus this research paper dwelt on adolescent girls to establish how to curb suicidal thoughts among that gender. 10.7753/IJCATR1308.1003 Mon, 01 Jan 2024 00:00:00 GMT http://ir.tum.ac.ke/handle/123456789/17644 2024-01-01T00:00:00Z