https://dr.ur.ac.rw/handle/123456789/7 Theses and dissertations submitted to UR Sun, 05 Apr 2026 21:42:50 GMT 2026-04-05T21:42:50Z https://dr.ur.ac.rw/handle/123456789/2853 Design and development of a TinyML– IoT- based vehicle crash detection and emergency alert system KAPALAMULA, Henry Eric This thesis aimed at employing IoT and TinyML techniques to develop a system that accurately detects vehicle crash accidents using acoustic data and triggers an emergency alert in real time to the nearest police unit. The methodology involved collecting secondary data on vehicle crashes, training a machine learning model, and deploying it on the Arduino Nano 33 BLE microcontroller, which supports TinyML. This technology enables low-power, on-device machine learning for embedded systems, facilitating real-time data processing and decision-making while extending battery life without requiring cloud connectivity. To detect a vehicle crash, the model uses acoustic data to identify an accident and transmits the GPS location via a LoRaWAN communication model. The system successfully alerts and provides the exact location of the accident by showing it on google map. Results demonstrate high accuracy, with 99.3% for training and 98.4% for testing, indicating effective differentiation between accident and non-accident scenarios. When an accident is detected, the GPS location is sent to the Arduino Cloud, plotted on a map, and an alert sound is produced. Further improvements can be made by employing energy harvesting techniques, developing a dedicated mapping system, and creating a model capable of classifying and detecting various forms of accidents beyond vehicle crashes. Master's Dissertation Thu, 12 Dec 2024 00:00:00 GMT https://dr.ur.ac.rw/handle/123456789/2853 2024-12-12T00:00:00Z https://dr.ur.ac.rw/handle/123456789/2852 Impact of climate change on irrigation projects. Case study of Cyaruhogo rice perimeter USANASE, Marie Claire Irrigation projects are important for food security; however, water requirements for sustainable irrigation may be affected by climate change. Climate change is projected to have significant impacts on agricultural production. Therefore, understanding the regional impacts of climate change on irrigation demand for crop production is important for watershed managers and agricultural producers to understand for effective water resources management. For irrigation project, the climate change affects it through the erosion, sedimentation in reservoir, flood, drought, etc. These impacts was be assessed in this research and measures were be taken for maintaining the irrigation system in Cyaruhogo wetland. The specific objectives like identifying the source of water for irrigation at Cyaruhogo wetland, assessing the cause of sedimentation in irrigation reservoir and Results analysis and discussion according to the laboratory tests were be used for achieving on the goal. To reach on objectives, interview were be conducted according to the prepared question for sample population in beneficiary area. The PH of water was be tested in laboratory to know if the irrigated water has acceptable PH for supporting crops. The PH of water in chemical analysis is 6.91 which is in acceptable limit, electrical conductivity is 374.4µs/cm and it is in range. The sediment has measured in laboratory and then the total sediment per year each dam is 13440tons, 11600tons and 13440 tons to Cyimpima, Bugugu and Gashara respectively. So the erosion control structure is needed to reduce the sediment enters in dam for maintain the capacity of water storage and keeping the product rises from Cyaruhogo wetland. Master's Dissertation Thu, 29 Aug 2024 00:00:00 GMT https://dr.ur.ac.rw/handle/123456789/2852 2024-08-29T00:00:00Z https://dr.ur.ac.rw/handle/123456789/2851 Smart agri-soil monitoring and maintenance through excess water based on ICT and fuzzy inference system Itangukwishatse, Mathieu In Agriculture, water plays a big role, like watering the vegetation and helps the micronutrients to be mixed. The farmlands watering may be drenched from different sources, which include rainfalls, fountains, wells and rivers. The water level monitoring is an essential task in farmlands, as each plant requires its own moderate water level. The deficit of water in a given plant may affect its growth; even the excess of water may affect the life of plant. The development of plant may be affected by the moisture stress. As the water becomes excess at a time of heavy rainfall, the micronutrients become unstable and it affects the life of vegetation. There are different methods, which are currently applied to manage water in farmland, like making manholes in fields, directing water in different rivers, building tanks to capture water from farmlands and using manpower to fetch water from farmlands. These techniques are traditionally used. Today, as technology advances every single step in agriculture, this research aims to deploy an intelligent system that is able to monitor soil temperature and humidity, soil moisture and water level. The system is able to fetch excess water from farmland and let the plant to remain with the required water for its growth. In this research, the NYABARONGO Valley is taken as consideration and divided into sections; each section has its corresponding water irrigation pump, water Drainage pump and mega tank. Each section is enabled to sense, actuate and communicate with the cloud. Sugarcane vegetation is also taken as a sample to be monitored because it occupies a big place in Nyabarongo valley. With the help of sensory prototype results, Matlab fuzzy logic based simulations, and the Matlab Simulink experimental results, the proposed research proves its ability of delivering soil maintenance and minimization of negative effects of excess water. Master's Dissertation Mon, 14 Oct 2024 00:00:00 GMT https://dr.ur.ac.rw/handle/123456789/2851 2024-10-14T00:00:00Z https://dr.ur.ac.rw/handle/123456789/2850 Hydrid energy storage system for large-scale renewable energy penetration MAKUPE, Sylvia Integration of renewable energy on a large scale into the grid poses a huge problem for the stability of the grid due to the variations that arise with most renewable energy resources like solar and wind. Sustainable energy storage systems must be put in place to boost the penetration of renewable energy sources in the grid. These energy storages help in achieving power quality, help in load following and leveling and managing energy seasonal shifting among other functions. This work designed and simulated long-duration power-to-gas systems of hydrogen and methane energy storages coupled to a solar system to analyze the technical, economic performance and environmental emissions of the systems. 3 energy storage systems have been designed, one with hydrogen only, one with synthetic natural gas and one with a combination of hydrogen and synthetic natural gas. The weather conditions of the Salima district in Malawi have been used in the designing of the systems. HOMERPRO software has been used as a design and simulation tool, to provide an optimized system of the designed systems. Having a hybrid system of SNG and hydrogen can help achieve a higher percentage of renewable penetration into the grid because the storage systems can complement the PV when the PV is not able to produce electricity. This system can also help in the reduction of emissions like carbon dioxides and sulfur oxides and a reduction in the cost of energy and the net present cost. Master's Dissertation Mon, 29 Jan 2024 00:00:00 GMT https://dr.ur.ac.rw/handle/123456789/2850 2024-01-29T00:00:00Z