Browsing by Author "Barasa, Peter Wawire"

Now showing 1 - 9 of 9

E-learning Transforming Economies
(International Journal of Trend in Research and Development, 2016-12-28) Barasa, Peter Wawire; Owoche, Patrick Oduor; Nambiro Alice Wechuli,
as E-learning technology has quickly evolved into more sophisticated forms, it is opening the options for educators and business professionals to expand learning opportunities and transform economies globally. The ability to transform economies from low income, to more vibrant growing economies which can generate employment and growing incomes to citizens generally, has been described as economic development. It is recognized that „Human Capital,‟ a term attributed to economist Theodore Schultz, is a reflection on the human capacities. Schultz believed human capital was like any form of capital. It could be invested in through education, training and enhanced benefits that would lead to an improvement on the quality and level of production. In this paper the authors make a case of how a nation‟s education system that is E-learning relates to its economic performance
Enhancing climate resilience: A data-driven north rift weather prediction system for real-time forecasting and agricultural decision support
(Heliyon, 2025-02-07) Makokha, John Wanjala; Barasa, Peter Wawire; Khamala, Geoffrey W.
This study presents the development and integration of predictive models for the Normalized Difference Vegetation Index (NDVI) and Bare Soil Index (BSI) using the XGBoost algorithm within the North Rift Weather Prediction System (NRWPS) to enhance ecosystem monitoring in Kenya’s North Rift region. Trained on a comprehensive dataset spanning 1995 to 2020, which includes precipitation (from the Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS)), temperature (TerraClimate), historical NDVI (Landsat 4–5 Thematic Mapper (from 1995 to 2013) and Landsat 7 Enhanced Thematic Mapper plus (ETM+) (from 2014 to 2020)), and BSI (SoilGrids) data, the models effectively capture the complex relationships between environmental factors and vegetation health. The BSI model achieved an MSE of 0.029, an MAE of 0.019, and an R-squared score of 0.93, while the NDVI model yielded an MSE of 0.002, an MAE of 0.024, and an R-squared score of 0.945. These results demonstrate the models’ strong predictive accuracy, enabling precise assessments of vegetation health and bare soil exposure. By analyzing temporal variations in vegetation health and land degradation from 1995 to 2020, the study identifies a significant inverse relationship between NDVI and BSI, where increasing bare soil exposure corresponds to declining vegetation health. The analysis also reveals that climatic factors particularly temperature (minimum and maximum) and precipitation play a critical role in shaping these trends, with high temperatures after 2000 associated with reduced NDVI, while regions with higher precipitation show healthier vegetation and lower BSI. The successful development of the NRWPS model provides significant opportunities for informing land management strategies, conservation efforts, and agricultural practices, enabling data-driven decision- making. Moreover, its integration into larger decision support systems allows for proactive interventions to mitigate land degradation and climate change stressors. This study emphasizes the importance of sustainable land-use practices and climate adaptation strategies to preserve vegetation health and manage ecosystem vulnerabilities effectively in the wake of regional climate change with the North Rift region most affected.
Green talent workforce planning and employee performance in Kenyan public hospitals
(International Journal of Research in Human Resource Management, 2025-04-15) Wekesa, Abraham Simiyu; Wanyonyi, Kadian Wanyama; Sirai, Sylvia Chebet; Barasa, Peter Wawire
Green Talent Workforce Planning on employee job performance in Kenyan public hospitals using a mixed-methods cross-sectional survey of 345 healthcare professionals. Structural equation modeling revealed a strong positive relationship between GTWP and performance (β = 0.385, p<0.001), with the model explaining 84.5% of performance variance and leadership support emerging as a critical moderator (β = 0.364, p<0.001); qualitative themes converged with these quantitative findings, highlighting benefits in competency development, resource management, team dynamics, career satisfaction, and organizational transformation. The study, grounded in Green HRM, Transformational Leadership, and Human Capital theories, concluded systematic implementation of GTWP strategies with robust leadership support to maximize employee performance and sustainability outcomes, providing recommendations spanning policy, practice, and future research to advance green talent management in healthcare.
Integrated machine learning system for curbing corruption
(KIBU, 2018-06-12) Barasa, Peter Wawire; Wechuli, Alice Nambiro; Barasa, Samuel Wafula
In this paper, the authors focus on using machine learning to fight corruption in governments. Corruption has been rampant in public and private sectors though prosecuting the cases in court has been wanting due to lack of clear evidence that convicts those involved. Since government operations have been digitized, machine learning algorithms can be used to scout corruption evidence which can be used to prosecute those involved in corruption. The research will adopt a positivism research philosophy and Inductive research approach. Desktop research design will be used. This paper seeks to come up with an integrated machine learning system that will connect to all the digitized government systems to curb corruption in governments.
Multi-Agent Based M-Voting System
(International Journal of Trend in Research and Development, 2016-12-28) Barasa, Peter Wawire; Wechuli, Alice Nambiro; Savatia, Edward
Multi-agent based m-voting system is capable of saving time, minimizing errors in voting and making voting easier. M-voting is an emerging area with wide application in all sectors of the Economy; m- voting is given a new dimension. M-voting is considered a brand new model which is based on use of mobile phone for voting in elections. The whole of M-voting in computing technology may be viewed as distributed, complex, dynamic because it has attributes such as network, popularization, personalization and lifelong. The object oriented design methodologies have been used in solving the voting problem. The voting problem is also being approached from artificial intelligence point of view. Many questions therefore arise about M-voting. One general question is how modern artificial intelligence models can be applied to the voting problem. An open direction of inquiry into this problem is the investigation of how multi-agents can be used to solve M-Voting. In this study, we focus on design of a multi-agent systems model, where the components in the Mvoting scenario are intelligent and can reactively and proactively participate in solving the voting problem. An agent oriented methodology –Prometheus- was used in the analysis and design of the multi agent based M-voting system We see the overall solution to the multi agent based M-voting system as the settlement resulting from communications and negotiations of individual agents in the M- voting process. This is a multi-agent scenario.
Multi-agent Based Surveillance System for Diseases
(International Journal of Trend in Research and Development, 2016-12-28) Barasa, Peter Wawire; Wechuli, Alice Nambiro
In this paper the authors make a case for medical care practitioners and governments to harness the power of technology to improve surveillance of diseases. Thus, using the multi-agent technology based surveillance system for diseases as a solution to the surveillance problems facing the healthcare sector in Kenya and the entire continent of Africa. The current surveillance problem is as a result of disease cases being carried out in a manual, inefficient and ineffective manner. An agent oriented methodology –Prometheus was used in the analysis, design, implementation and evaluation of a program designed to assist medical care practitioners..
Report of the Baseline Study on Technology-Enabled Learning at Kibabii University
(Commonwealth of Learning, 2020-04-28) Barasa, Peter Wawire; Anselemo, Peters Ikoha; Wechuli, Alice Nambiro; Wekesa, MacDonald
Report of the baseline study on technology-enabled learning at Kibabii university
(Commonwealth of Learning, 2020-07-30) Barasa, Peter Wawire; Anselimo, Ikoha Peters; Nambiro, Alice; Wekesa, Macdonald
This document reports the findings of a baseline survey conducted between 1st June 2020 and 30th July 2020 at Kibabii University (KIBU). The objective of the study was to establish Technology-Enabled Learning (TEL) preparedness at KIBU and implement TEL systematically with support from the Commonwealth of Learning (COL). It reports the findings of a self-review of the institutional facilities related to technology, policies, and the preparedness of faculty and students to use technology for teaching and learning at KIBU. The following is a summary of the findings and recommendations based on the study.
The use of internet of things to combat the global challenge of terrorism
(KIBU, 2018-06-12) Barasa, Samuel Wafula; Wechuli, Alice Nambiro; Barasa, Peter Wawire
In the global arena, Internet of Things has transpired as a prominent technology which is capable of providing better methods of identification and monitoring. Today, more and more devices are connected to not only the Internet but also to each other, thus Internet of Things enables increased convenience, efficiency and energy conservation. Therefore, internet connectivity moving away from the traditional devices to wearables and household devices such as fridges and washing machines, the Internet of Things can easily be used for monitoring, location tracking, identification, surveillance and eventually gaining access to networks. Each device will have an IP address for communication on the network. The security experts can use the surveillance services to intercept signals of networked devices. The information from speeches, satellites, videos and news is monitored, collected and analyzed to facilitate intelligence services to close in on terrorists. This will be achieved by identifying the state of the art technologies using desktop research on a global perspective to combat terrorism.