School of Technology
Permanent URI for this collectionhttp://192.168.8.146:4000/handle/123456789/18
Browse
54 results
Search Results
Item Predicting campus admission through assessment of soft skills using random forest algorithm(KCA University, 2025) Muthui, Dennis M.This study develops a machine learning model to predict college admission success in Kenya by assessing soft skills using the random forest algorithm. The research addresses the growing importance of soft skills in academic and professional success, and current limitations in evaluating these abilities during admissions. The study identifies key soft skills, creates a comprehensive assessment tool, develops and tests a random forest model, and evaluates its performance, interpretability, and fairness. The methodology involves a quantitative predictive modeling design, employing stratified random sampling and rigorous data collection procedures. Results indicate that soft skills, particularly communication and problem-solving, are strong predictors of admission success, often outweighing traditional academic metrics. The random forest model achieved 98.36% accuracy in predicting admissions outcomes, with mathematics performance emerging as the most influential factor (22% importance), followed by GPA (18%), KCSE scores (16%), and science grades (15%), while soft skills showed more modest but meaningful contributions (communication 8%, leadership 5%, problem-solving 4%). The model demonstrated consistent performance across demographic groups, with perfect equal opportunity across gender, school type, location, and school level categories. However, the model reflected existing demographic disparities in admission rates that mirror broader equity challenges in educational access. The study concludes that incorporating soft skills assessments in admissions processes could provide a more holistic evaluation of applicants, though current practices continue to prioritize traditional academic achievement. Recommendations include integrating soft skills development in secondary education curricula and incorporating structured soft skills assessments in university admissions processes. This research contributes to the ongoing dialogue about evolving higher education admissions to better align with 21st-century workforce needs while promoting fairness and transparency in the admission process.Item A paired-algorithm clustering model for describing field staff Deployment in non-governmental organizations (ngos).(KCA University, 2025) Nyakado, Manasses N.This research addresses the inefficiencies and challenges faced by non-governmental organizations (NGOs) in deploying field staff, focusing on the manual processes prevalent in the current systems and leveraging on the possibilities offered by predictive machine learning algorithms. The problem stems from time-consuming and error-prone manual data entry methods, hindering optimal resource allocation. Our objective is to develop and implement a machine learning clustering algorithm to automate the field staff deployment process. By leveraging data analytics – hierarchical and k-means machine learning algorithms – we aim to enhance the efficiency and accuracy of deployment, leading to improved allocation of personnel and resources. The expected outcome is a streamlined deployment system that significantly reduces errors, minimizes time consumption, and maximizes overall operational efficiency in NGO field operations. The project outcomes will also inform advances in the use of combined methods in clustering machine learning algorithms and data analytics.Item Context awareness vulnerabilities detection model in byod environment using a linear regression technique(KCA University, 2025) Wanjiru, Jeremiah N.The purpose of this study was to examine context-awareness vulnerabilities in Bring Your Own Device (BYOD) environments within large SACCOs in Kenya. Adoption of BYOD practices, enable employees of an organization to use personal devices for work. In the recent past there has been incidents of financial vulnerabilities, including losses attributed to both internal collusion and external cyber-attacks, which showed the urgent need for solutions focused on vulnerability detection mechanisms. The analysis of past literature revealed gaps in existing models, which inadequately address SACCO-specific risks such as the role-based access and dynamic access patterns, often relying on a narrow set of data points or reliance of static approaches. The study employed a descriptive survey design, using structured questionnaires to collect data from 86 employees of Mwalimu SACCO’s head office in Nairobi. As the largest SACCO in Kenya, Mwalimu SACCO provided a suitable context to analyse BYOD-related vulnerabilities in a high-risk, resource-constrained environment. Descriptive techniques and multivariate regression analysis were employed to determine the influence of the identified factors on the vulnerability index. The study findings showed that access time, location, and role risk factors significantly wielded and affect vulnerability in BYOD environments. Access time emerged as the most critical determinant, with increased risks observed during non-standard work hours. Location vulnerabilities were heightened in remote settings due to limited security measures, while role risk factors indicated that employees with elevated access privileges, particularly in ICT and finance roles, posed greater risks. The study formulated a multivariate regression model which demonstrated high predictive accuracy, with an R² value of 0.89 and a mean absolute error of 0.12. These results validated its reliability in identifying and predicting context-awareness vulnerabilities in SACCO BYOD environments. The study concludes that; there is increased use of personal devices by SACCO staff to undertake both personal and official engagements. Further, the study concludes that, there is lack of comprehensive BYOD policies that conforms to prevailing vulnerabilities. Through adoption of robust access controls, organization centered BYOD policies, and role-specific security measures, SACCOs can upscale their defenses. These measures would enable SACCOs to mitigate vulnerabilities, reduce insider fraud and external threats, and strengthen their cyber-security posture. This research fills a critical gap in understanding and managing context-aware vulnerabilities in BYOD environments, offering a practical framework for enhancing the security of SACCO operations in Kenya.Item An ensemble deep learning judgement prediction model for civil cases in Kenya.(KCA University, 2025) Amagoye, Jeremy SindigiAbstract This study develops and evaluates an ensemble deep learning model combining Convolutional Neural Networks (CNN), Bidirectional Long Short-Term Memory (BiLSTM) networks, and an Attention Mechanism (AM) to predict judgments in Kenyan civil cases. With Kenya's judiciary facing a backlog exceeding 400,000 cases, this research addresses critical efficiency and consistency challenges. The CNN+BiLSTM+AM architecture extracts key textual features from legal documents, captures sequential dependencies in legal arguments, and prioritizes relevant information through attention weighting, providing both accurate predictions and interpretable results. Using stratified sampling across court levels, the study analyzes civil cases to identify influential predictors of judicial outcomes, including legal representation disparities, citation patterns, and procedural factors. Results demonstrate the model's superior performance compared to baseline approaches, with implications for case management, resource allocation, and access to justice. By providing data-driven insights into judicial decision-making, this research contributes to addressing systemic inefficiencies in Kenya's legal system while establishing a methodological framework applicable across similar jurisdictions. The findings support Kenya's judicial reform efforts by offering an innovative, technologically-driven approach to enhancing transparency, consistency, and efficiency in civil litigation.Item Gaze-based interaction for effective tutoring with social robots(Universitat Politècnica de Catalunya, Technische Universiteit Eindhoven, 2020) Mwangi, E. NjeriThe central thesis of this work is that effective gaze behavior can help build a shared understanding and mutual awareness between humans and robots, leading to positive outcomes in a tutoring interaction. Gaze behavior is an essential cue for social engagement and coordinated action, principally for tasks that imply human-robot collaboration, such as tutoring. The work presented in this dissertation is a compilation of findings from three empirical studies designed to explore the design space of gaze-based interaction to enrich human-robot interaction in educational settings where robots assume tutor or trainer roles. In the first study, we examined how people perceive and interpret social cues from gaze provided by either a human or a robot tutor during a collaborative tutoring activity. The objective was to investigate whether people can notice and accurately interpret gaze-based cues from a tutor and whether they can accept the cues as help during learning interactions. We incorporated eye-tracking to examine gaze interaction during human-human and human-robot communications. We found that participants noticed the gaze cues from the robot tutor significantly more often than those of the human tutor. Consequently, we found that participants performed better with the robot tutor compared to the human tutor. These initial findings provide design recommendations for gaze-based communications to improve learning performance during human-robot tutoring. Based on the results from the first study, we investigated how to implement gaze-based communication as an efficient help mechanism for robot-child tutoring. The objective was to examine child-robot gaze mechanisms to inform the robot's behavior design as a facilitator of children's task-solving. We carried out simultaneous observations of the child's gaze and the robot to examine the events of mutual gaze and gaze following patterns during the tutoring activity and to assess the impact of different child-robot coordinated gaze patterns on children's behavior and performance. We found that if a robot tutor provides gaze-based support, children perform better during the tutoring activity than when a tutor SUMMARY xv does not offer such cues. We also found that more events of mutual gazing patterns between the child and the robot tutor improve children's awareness of the tutor's intention during the activity leading to better performance. Therefore, we concluded that increasing gaze coordination between the child and the robot can improve performance and build mutual awareness during robot-based educative interventions. In the last study, we investigated the nature and dynamics of gaze-based human-robot interaction (HRI) in tutoring. The objective was to examine intricate patterns of gaze interchanges between a child and a robot during the tutoring activity and to assess the impact of child-robot coordinated gaze on children's behavior and performance. We combined both observational and sequential lag methods to examine the relevant gaze sequences during a collaborative tutoring activity. We found that appropriate sequences and timing of the dyad's gaze behaviors between a child and a robot can lead to effective interactions between a child and a robot tutor. Based on these findings, we concluded that a robot tutor could positively influence the flow of the child's actions if the child interprets the social cues appropriately, improving the task execution and the play experience. This new understanding of the dynamic nature of gaze behavior during child-robot interaction contributes to the design of robot gaze behavior, to build better robot-based interventions in education and therapy settings. Overall, the findings from the user studies contribute to new design guidelines for gaze-based communications to improve learning performances and promote positive human-robot tutoring interactions. In addition to the findings of the user studies, the main contributions of this dissertation include; First, an experimental framework for studying how gaze-based cues of robots can be applied to improve performance and quality of tutoring interaction. The experimental setting allows for simultaneous analyses of humans (adult-child) and the robot's gaze during a collaborative tutoring activity. Second, a coding scheme developed to measure the dynamics of child-robot interaction with an emphasis on coordinated and sequential gaze patterns between children and robots. The third is the use of simultaneous observational and lag-based methods to examine coordinated and interaction sequences of gaze between children and robots, helping unravel the dynamics of child-robot interaction in a tutoring setting. The lag-based methods provide an opportunity to investigate complex gaze sequences that—to our best knowledge—have not been previously explored in robot-based educational backgrounds or other human-robot interactions. The lag methods can be extended to analyze, in-depth, other interactive behaviors during human-robot interaction (HRI)Item An Artificial Neural Network Model For Predicting Attainment Of The 50:50 Gender Ratio In Stem Courses In Kenya(http://repository.kca.ac.ke/handle/123456789/601, 2020) Kibet, Cynthia NIn spite of the existing educational policies on gender and several other interventions that are aimed at empowering the girl child, education is not globally available and gender inequality is still a major problem world wide. Many nations are now concerned that fewer girls are going to school in comparison to their male counterparts, and also that males have higher participation and learning achievements than girls ,more particularly in Science, Technology, Engineering and Mathematics (STEM) subjects and courses. STEM education is one of the pillars behind Kenya’s Vision 2030, which aims to turn the country into a newly industrializing, middle-income country providing a high quality life to all its citizens by the year 2030, in a clean and secure environment. STEM education is expected to provide learners with the knowledge, skills, attitudes and behavior required for inclusive and sustainable societies. Graduation trends from the Commission for University Education (CUE) show that more than 30 % of graduating students each year are awarded commerce degrees or one of its other hybrids in business studies, 20 % graduate in education arts and another 20 % in other non-STEM courses. In a study conducted by Dr. Eusebius Juma Mukhwana, (Mukhwana et al., 2016) a former deputy commission secretary in charge of planning and research development at CUE, 74 % of all university students are enrolled in business, education arts and humanities. This leaves only 26% of the students in STEM.To make a bad situation worse, gender disparity within STEM fields is in favor of males. Female students represent only 35% of all the students enrolled in STEM- related fields of study at higher learning levels according to a study conducted by UNESCO through the ‘STEM and Gender advancement’ project in 2015. This disparity in gender is startling, moreso since careers in the STEM fields are now being commonly cited as jobs of the future that are being used, and shall continue to be used to drive innovation, inclusive growth and sustainable development. The female gender is held back by societal norms, biases and prejudice, and expectations that influence the quality of education they receive and even the subjects they choose to study at higher learning levels. Following the above findings, the Kenyan government and stakeholders in the education sector have put measures in place in a bid to bridge this gap in gender. The main aim of this study therefore was to develop a model that would predict when the ratio of males to females in STEM will be 50:50 and further determine what measures can be put in place by government or society, to promote the interest and engagement of girls in STEM. An Artificial Neural Network (ANN) was applied as the predictive data mining method to come up with the model. Exploratory data analysis was performed on the data and a regression model was built inorder to achieve the main objective of the study. The study utilized the data in the repositories of the Kenya Universities and Colleges Central Placement Services (KUCCPS) for the years 2014, 2015, 2016, 2017 and 2018. The method of data collection was ‘Use of existing data as a data collection method for machine learning’ (Yuji et al., 2019). After the model was built, it was evaluated to determine its accuracy.Item A Model Of BYOD Integration To Increase Corporate Information Security In Banks: Case Of Equity Bank Kenya(KCA University, 2021) Dalla, Gladys MBring Your Own Device or BYOD is a novel approach where employees and stakeholders in organizations bring their personal computer devices to the workplace. Employees are able to access organization information and data through their devices under the BYOD policy. On the other hand, the BYOD approach heightens the risk of malware attacks and therefore, diminishes the integrity of the information security within the organization. The current study sought to develop a model for the integration of BYOD in the banking sector while maintaining a sustainable corporate information security. The theories guiding the study are the technology threat avoidance theory and unified Theory of Acceptance and Use of Technology. On the other hand, the research study adopted a cross-sectional survey design to collect data. The survey design is effective in coming up with quantitative data that aids one develop inferences regarding a particular phenomenon. The study established that Mobile device management, Information security policies, Security culture and Employee education as BYOD factors have significant effect on Sustainable corporate information security. Following data collection the researcher was able to clean, code and analyze data using SPSS v27. An OLS model was derived from the analyzed data. The derived statistical model can be instrumental in integration of BYOD while maintain information security. The generated model was tested and validated through multiple regressions test statistics. The Adjusted R value obtained through model summary was r2=0.437 indicating that the independent variables of Mobile device management, Information security policies, Security culture and Employee education contribute 43% variation in Sustainable corporate information security. The ANOVA statistic showed that the independent variables are significant to the dependent variable. Subsequently, the independent variables in the study have a significant impact on the dependent variable of Sustainable corporate information security. Moreover, the researcher recommends that organizations in the banking sector have a device register in the BYOD platform to ensure information security. The findings of the research are significant to the corporate sector as it adds knowledge that will help guide the security model employed in running BYOD. Integration of BYOD is a necessity in most industries, hence this research provides a robust model for heightening Sustainable corporate information security.Item Uplifting Model For Predicting Subscriber Churn Conversion Using Ensemble Learning: A Case Study Of Mobile Telecommunication Sector In Kenya(KCA University, 2021) Ochieng, Anthony CChurn is the number one topic for Telco’s in Kenya and around the world. Customer churn in the telecommunication industry is still a big problem because emerging new technologies, lower costs, among other factors Churn brings with it many negative repercussions. While churn is a helpful key performance indicator for identifying areas of improvement whether in process or product, it can lead to financial disability eventually as customer acquisition cost are normally more astronomical than trying to please a disenchanted Subscriber. By analyzing churn drivers, we can safeguard the most import asset for a telecommunication company from churning. Predicting subscribers who are most likely to churn is fundamental for telecommunication companies. As a result, churn prediction is an important barometer for business success as well vastly studied and common activities that can be accomplished by machine learning applications for telecommunication industry. Telecommunication companies have since come to a realization that churn prediction only provide predictions but do not provide information for optimal decision making within a business setting. This is where uplift modelling has come to the fore. Uplift modeling is a branch of machine learning which aims at predicting the causal effect of an action such as a retention campaign or a marketing campaign on a given population by considering outcomes from the campaign treatment on that group, involving the sample populations that has been subjected to that campaign or treatment, and a control sample population. The model generated is then utilized to select the segment of population that the campaign would be profitable. This dissertation analyzes the use of ensemble methods in uplift modeling. The researcher will attempt to demonstrate higher performance compared to traditional classification and uplifting techniques. The researcher will attempt to show improved performance are a result of using ensemble classification techniques inculcating the differences in class probabilities in the treatment and control groups. The result being a Novel propensity outcome modification model. Safaricom plc was used as a case study to develop an uplifting for predicting subscriber churn conversion on various pre-existing subscriber segments. The objective of the study was to find the most profitable segment to target after using an ensemble classifier to predict probable churn customers on prepaid subscribers. Anonymized and pseudomized subscriber data was used for the study. The final results show the accuracy and precision of the ensemble predictive classifier and also the uplift scores for the various existing subscriber segments using the novel propensity outcome modification approach that identifies the probable segment to target with a retention campaign.Item An Adoption Model For Electronic Health Records System In Health Care Facilities: Case Of Siaya County, Kenya(KCA University, 2021) Mutua, Kennedy WThe electronic health record system offers a number of benefits which can be used to improve service delivery in the health care facilities that have implemented the systems. However, there has been a slow and stagnant adoption of EHR systems in health facilities across Kenya. The main objective of the study was to determine factors affecting adoption of Electronic Health Records systems in health facilities across Kenya and develop a model that could be used to inform implementation of the systems across the country. Siaya County was used as a case study. Collection of Data was done by administering a semi-structured questionnaire to the participants. Accuracy of data was ensured through checking the completed questionnaires before analysis. Analysis was done through the use of SPSS statistical tool. Correlation analysis through cross tabs was used to determine the relationship that might appear in the study. A statistical significance level of p<0.05 was used for the study. Frequency tables, graphs and charts were used to present the analyzed data. Results showed that a majority of the health facilities had between full and partially implemented EHR systems. The study showed that knowledge in ICT, Education level and healthcare perception were among factors that affected the implementation of EHR systems. URIItem A Predictive Model Of Climate Sensors Effectiveness On Sustainability Of Subsistence Agriculture: The Case Of Laikipia County(KCA University, 2021) Kariuki, John NIn contrast to many areas of the globe where farmer posses adequate physical, economic and social resources to adapt to and moderate effects of climate variation and climate change, subsistence agriculture in the arid and semi-arid lands (ASALs) of Kenya are particularly affected in an unfavorable manner by the effects of climate change. This is more so because of the increasing dependency of a good number of the population on rain fed agriculture as a source of livelihood and economic income. An effective adaption mechanism to climate change for sustainability of subsistence agriculture in these areas using communication technologies is therefore highly important for food security and protection of livelihoods within the rural areas. The main aim of this study was to model and predict the effectiveness of climate sensors on the sustainability of subsistence agriculture in Laikipia County, one of the ASALs in Kenya. The study hypothesized that the current community based strategies applied by the local farmers are relevant and important to the present-day quest for climate change adaptation strategies, and that feedback from the stakeholders can generate insight used to generate an improved predictive model to further enhance this adaptation. The study therefore conducted a survey study of rural stakeholders in Laikipia farmlands and assessed the output through descriptive measures. Further, a logistic regression model of variables constructed from the survey study was used to predict the effectiveness of data communication technologies such as climate sensors that are currently employed on the sustainability of subsistence agriculture in these rural areas, using variables such as geographic extent, temporal scope, precision level, frequency of usage, and cost of acquisition. The model was be tested through standard measures of goodness of fit such as Chi-square and adjusted goodness-of-fit index. It is expected that results of this study will be useful in policy formulations regarding adaptation mechanisms to climate change for sustainability of rural-based subsistence agriculture.