JOURNAL OF AGRICULTURE, SCIENCE AND TECHNOLOGY https://ojs.jkuat.ac.ke/index.php/JAGST <p>The Journal of Agriculture, Science, and Technology (JAGST) is a peer-refereed bi-monthly publication first produced in 1997. It features research articles in Agriculture, Biotechnology, Forestry, Human and Veterinary Medicine, Engineering, Architecture, Information Technology, and Physical and Social Sciences. It also carries current scientific reports and, occasionally, reviews of publications with a scientific orientation. <br />The journal serves as an important tool in the mandate of the University’s Research, Production and Extension (RPE) Division to facilitate dissemination of research findings. <br />The goal of the Journal is to:</p> <ul> <li>Provide a forum for the University staff and students, and researchers from the region and other parts of the world to participate in the discovery, transmission, <br />preservation and enhancement of knowledge in various disciplinary areas.</li> <li>Contribute towards the University’s goal of integrating teaching and research for effective application and preservation of knowledge and skills.</li> <li>Provide a platform for sound academic discourse among researchers.</li> </ul> <p>To view issues that were published in the past years i.e. before 2010 click this link :<a href="https://www.ajol.info/index.php/jagst/issue/archive">Previous JAGST issues before 2010</a></p> en-US jast@rpe.jkuat.ac.ke (JAGST Office) akivaa@jkuat.ac.ke (Amos Mwoni) Fri, 29 Dec 2023 08:05:54 +0000 OJS 3.3.0.6 http://blogs.law.harvard.edu/tech/rss 60 Comparison of Machine Learning Methods for the Prediction of Type 2 Diabetes in Primary Care Setting Using EHR Data https://ojs.jkuat.ac.ke/index.php/JAGST/article/view/659 <p>Diabetes remains a major global public health challenge, thus the need for better methods for managing diabetes. Machine learning could provide reliable solutions to the need for early detection and management of diabetes. This study conducted experiments to compare a number of selected machine learning approaches to determine their suitability for early detection of diabetes in the primary care setting. A retrospective study was conducted using EHR dataset of confirmed cases of diabetes collected during routine care at Nairobi Hospital. Institutional ethical approvals were obtained, and data were retrieved from the database through stratified sampling based on gender. Diagnoses were confirmed using the ICD-10 codes. Records with 5% or so of missing values were excluded from this analysis. Data were processed by correction of errors and replacement of missing values using measures of central tendency. The data were transformed through normalization using the decimal-scaling method. Data analysis was conducted using selected supervised and unsupervised learning algorithms. Model performances were validated using metrics for the evaluation of classification and clustering results, respectively. Random Forest had the highest accuracy (0.95) and error rate (0.05), while Gradient Boosting and Multilayer Perceptron (MLP) with 3 hidden layers obtained accuracy (0.94) and error rate (0.06), respectively. The process of selecting machine learning algorithms needs to explore both supervised and unsupervised learning techniques. In addition, an appropriate architectural design of an MLP could present astounding results for classification tasks in primary care settings.</p> Amos O. Olwendo, George Ochieng, Kenneth Rucha Copyright (c) 2023 Amos Otieno Olwendo, George Ochieng, Kenneth Rucha https://ojs.jkuat.ac.ke/index.php/JAGST/article/view/659 Mon, 09 Oct 2023 00:00:00 +0000 Association between Work-Related Musculoskeletal Disorders’ risk factors and different body parts affected among Housekeepers in selected hotels in Mombasa County https://ojs.jkuat.ac.ke/index.php/JAGST/article/view/644 <p>Work-related musculoskeletal disorder (WRMSDs) affects primarily muscles, tendons, joints, intervertebral discs, peripheral nerves, and the vascular system<strong>. </strong>WRMSDs are a worldwide issue and are experienced in both developed countries and industrially developing countries (IDCs). The prevalence of WRMSDs and their risk factors are not well known among hotel housekeepers in Kenya. Therefore, this study aimed to establish the annual prevalence of work-related musculoskeletal disorders among housekeepers in selected hotels in Mombasa County. The study also sought to assess the common body parts affected by pain as well as the WRMD risk factors associated with these body parts among housekeepers at selected hotels in Mombasa County. The study employed a cross-sectional approach. The sample size of 276 study participants’ housekeepers was obtained by considering housekeepers’ availability at the time of study at 18 purposefully selected hotels. Data collection was done through standardized questionnaires. Qualitative and quantitative methods were used for data analysis. Quantitative data was coded and entered into the Statistical Package for Social Sciences (SPSS 23) for analysis. Descriptive and inferential statistical analyses were utilized to analyze the quantitative data collected from the structured questionnaires. To establish the link between variables, descriptive statistical analysis, including frequencies and percentages, and inferential statistical analysis, including the Chi-square test and linear regression, were utilized, with findings displayed in frequency tables, bar graphs, and pie charts. On the other hand, the qualitative analysis utilized thematic analysis, with findings presented in narrations. WRMDs were found to be prevalent in 91.7% of hotel housekeepers in Mombasa County. The most widely reported WRMD by housekeepers was lower back pain. The study cohort also reported leg, neck, and shoulder joint and muscle pains as a result of carrying, lifting, pulling, or pushing heavy objects weighing more than 20 kilograms. Hotels ought to identify the common WRMDs among housekeepers and determine specific risk factors associated with these pains. The study's key recommendations are for hotels to evaluate their labor practices to mitigate understaffing, invest in the mechanization of equipment to ensure that staff have reasonable working hours per day with adequate breaks in between chores, and take reasonable leave. Implementing health and safety standards is crucial, with an emphasis on good posture and techniques while performing tasks. The study recommends strengthening labor regulations by raising awareness and sensitizing labor unions and health committees on musculoskeletal disorders and preventing undue work-related injuries among hotel housekeepers.</p> Enid K Gikunda, Charles M. Mburu, Cromwell M Kibiti Copyright (c) 2023 Enid K Gikunda, Charles M. Mburu, Cromwell M Kibiti https://ojs.jkuat.ac.ke/index.php/JAGST/article/view/644 Fri, 29 Dec 2023 00:00:00 +0000