Browsing by Author "Samson O. Ooko"

Now showing 1 - 4 of 4

An Evaluation of Machine Learning Techniques for Crop Detection from Garden Images
(IEEE Xplore, 2023) Samson O. Ooko; Grace Kwagalakwe; Lossan Bonde
Agriculture is a major driver for different economies across the globe. With the continued advancement in technology, there is a move towards precision agriculture. A major area of research interest is the detection of crops by use of computer vision. Such can help in controlling pests and diseases and thus increase yields. However, given the wide range of techniques applied, there is a need to evaluate them to recommend the most suitable for the detection of different crops. This study was thus aimed at evaluating both traditional Machine Learning (ML) and Deep Learning (DL) techniques for the detection of banana and cassava crops from a set of garden images. First, a crop classification model was built using the traditional machine learning model with feature extraction algorithms being applied before training using K-Nearest Neighbor (KNN) and Naïve Bayes. Another crop classification model was also built using deep learning (CNN) on an annotated dataset. The performance of both models was evaluated with deep learning giving the best result. Deep learning is thus recommended as the best model for crop detection.
Application of Tiny Machine Learning in Predicative Maintenance in Industries
(Journal of computing theories and applications, 2024-08-02) Samson O. Ooko; Simon M. Karume
The advancements in the Internet of Things (IoT) and Machine Learning (ML) have enabled significant improvements in Predictive Maintenance (PdM) in industries, providing economic benefits by reducing equipment downtime and maintenance costs. Traditional ML approaches, however, re-quire more computational resources and are often limited to cloud-based processing, leading to in-creased costs and high latencies. Tiny Machine Learning (TinyML) offers a novel solution by enabling ML models to run on low-power, resource-constrained devices at the edge, facilitating real-time, on-device inference. This review analyzesTinyML applications in PdM, highlighting the technology's po-tential to transform industrial maintenance practices. We explore the differences between TinyML and standard ML, discuss the economic and operational advantages of adopting PdM, and present practical case studies where TinyML has been successfully implemented. In addition, we address the challenges facing TinyML, including hardware limitations and the need for specialized algorithms. Our findings indicate that while TinyML is a promising technology for PdM, further research is needed to overcome these challenges and fully realize its potential. This review contributes to understandingTinyML's role in industrial PdM and outlines a roadmap for future research and development in this emerging field.
Monitoring and Predicting African Rural Household Air Pollution Using Internet of Things and Artificial Intelligence
(Pan-African Journal of Health and Environmental Science (AHJES), 2024-07-02) Samson O. Ooko; Enatha Rweyemamu
According to a 2020 report from the World Health Organization (WHO), household air pollution has led to over 3 million deaths globally, with recent statistics showing a worsening situation in Africa. Integrating Internet of Things (IoT) and Artificial Intelligence (AI) technologies can help address this global challenge. IoT enables real-time data collection for monitoring pollution levels, while AI algorithms predict pollution before it reaches hazardous levels. However, existing solutions are not tailored to the African context, where wood fuel is a primary pollutant, and they predominantly focus on monitoring rather than prediction. This study presents the design and implementation of an IoT-based solution for monitoring and predicting indoor air pollution in rural African households. The system collects data in real time and transmits it to the cloud for storage, processing, and analysis, with alerts to users when pollution is detected. An AI model was successfully trained and tested to predict indoor air pollution based on the collected data. The results indicate that this approach significantly improves the accuracy and timeliness of pollution alerts, potentially reducing health risks associated with indoor air pollution. The successful implementation and testing of the system demonstrate its potential for broader applications in various indoor environments.
Tiny Machine Learning (TinyML) Based Self Diagnostic Kit for Respiratory Diseases
(IEEE Xplore, 2023) Samson O. Ooko; Jimmy Nsenga
The World Health Organization (WHO) 2022 statistics show that over 3 million deaths globally result from chronic respiratory diseases yearly. Interestingly 90% of these deaths are reported from middle- and low-income countries. This may be attributed to the poor health care systems with few medical experts to enable early diagnosis and treatment of the diseases. There is therefore a need for cheap and accessible solutions to help solve the problems. The use of the latest technologies of Machine Learning (ML) and Internet of Things (IoT) provide capabilities that can enable cheap and convenient detection and monitoring of respiratory diseases. However, existing solutions are cloud-based and thus depend on the availability of internet connectivity to function. This poses privacy, security, and even connectivity challenges, especially in Africa. The concept of using an emerging ML technique for inferencing on resource-constrained devices known as Tiny ML was used as a solution enabling the development of a self diagnostic kit. The system captures breath Volatile Organic Compounds (VOC) the collected data will be processed on the device and a Tiny ML algorithm used to detect if the sample is infected or not. The designed prototype was used to collect from healthy and unhealthy volunteers. The collected data was then used to train the prediction model. The ML model predicts respiratory diseases with an accuracy of 95.4% using less than 20% of the device resources. The proposed solution will reduce the dependency on medical experts and healthcare facilities and enable early detection of respiratory diseases.