School of Technology
Permanent URI for this collectionhttp://192.168.8.146:4000/handle/123456789/18
Browse
125 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 Generic model for estimating wlan infrastructure costs(kca university, 2013) Kebut, Vancy J.In setting up LAN or WLAN infrastructure, the business has to make careful decisions on the choice of LAN or WLAN infrastructure to be laid for them to have a robust LAN infrastructure as well as have cost effective solution. (Cawley & Harman, 2005) has said that: “there is need for a tool enabling estimating LAN infrastructure costs that would lead to cost effective decisions. It will also provide an opportunity to compare network infrastructure choices which can be deployed in a network.” (p.2). There exist two cost estimation models; Tolly group – 2000 and TIA FOLS – 2005 which is always updated. From the Tolly group and TIA FOLS models, one can be able to estimate costs of having fiber on the vertical and either UTP or fiber on the horizontal using the standardized architectures; distributed or hierarchical star, FTTD/All-fiber and FTTE. Due to the advancement of technologies, there is also need for a tool to estimate the costs of WLAN infrastructure. The WLAN cost estimation tool developed in this thesis can be used by WLAN users or designers to estimate costs of either hierarchical star design, centralized or FTTD design or FTTE design and compare between costs among the three architectures. It can be used to identify which of the standard-compliant architectures is cost effective without any compromise to the computer network performance. Therefore computer network users or designers are able to make decisions as to which standard compliant architecture is the cost optimal solution for their LAN.Item A road map model towards unified software requirements engineering process management: System dynamics approach(kca university, 2018) Njoroge, Githinji DavidThe Success of software projects heavily and critically depends on the effectiveness of Requirements Engineering (RE) and the Requirements Engineering Process Improvement (REPI). This research study adopts and applies System Thinking/System Dynamics (SD) approach to the complex and dynamic REPI process. The research paper presents a unified model for improving quality software and delivery. Review of the state-the-art practice in RE and REPI literature indicates six categories of problem that motivated the research work reported in this paper. Poor RE and REPI processes make projects to fall behind schedule, encounter budget over-shoots and poor software specification and development. The research study seeks to understand these problems from a feedback control point of view due to lack of quantitative data and agreement on the nature of deficiencies in the current RE and REPI processes. The model developed therefore not seen to be an answer to the existing RE and REPI problems, but as an aid tool for research, researchers and RE stakeholders to advance a deeper understanding needed to answer them. The study identifies several strategies for performing REPI research from empirical to paradigm shift and isolates hot areas of research that address RE and REPI needs for effective software product delivery. Development of the model contributes to research by providing foundation for theory building on RE and RE improvement management of software projects in learning institutions, RE, REPI and software stakeholders.Item Implementation of a universal public Wi-Fi access(kca university, 2013) Muango, Charles O.As demand for Internet grows and its usage keeps evolving, there is need to create an avenue through which users can have access to this facility wherever they are without subjection to ISP providers; this will facilitate economic growth, job creation, and global competitiveness. To address this today depends on incremental solutions that increase and guarantee connectivity without any hassle of having to purchase DTE/DCE (modems). The objective of this study was to implement a universal public wireless Internet access by use of the Wi-Fi enabled feature on laptops and other devices today. This will ensure drive to innovation, deliver seamless connectivity and optimize network use. This study evaluated the effectiveness of the Internet services offered by ISPs (Safaricom, Airtel, Orange and YU). The results from this study revealed that Network coverage was the key reason for subscription to an ISP by a client among others such as cost, equipment (Modem) availability and spread of bandwidth for purchase. Based on the study, a Web based solution was developed from which all transactions pertaining to online purchase of bundles (based on the amount of funds one has in his/her account) and connecting to the Internet everywhere through a Public Wi-Fi would be achieved. This is the uniqueness of the developed solution in this work. Finally, conclusion and recommendations that will help provide better Universal Public Wi-Fi Access have been discussed.Item Improving performance of 3G mobile data offloading through WiFi networks by data caching(kca university, 2013) Gichuhi, Cecilia WambuiIn the recent years there has been a skyrocket rise in mobile data usage especially due to the large number of smartphones in use. This has led to a rigorous traffic overloading in cellular networks and the trend is expected to continue. It is imperative that architectures are put in place to handle this data. Use of Wifi to offload data has been considered as one of the immediate solutions. In this paper I propose Wifi caching to offload mobile data. Tests were carried out using OMNet++ a discreet event simulator. From the experiments done it can be seen that the throughput is best when the number of hosts are about 3 and 10. Further increase of hosts above 10 hosts then the throughput and efficiency begin to go down. However when LRU caching is implemented the general throughput is slightly lower than when caching is not implemented which is a concern, and was not the expected result. The user request latency is slightly higher after caching. The AP caching model can be tested using other different caching algorithms to see which one would give best results.Item A tool for predicting loss-to-follow-up among people living with HIV at Busia border(kca university, 2017) Juma, Denice OHuman Immuno-Deficiency Virus (HIV) and Acquired Immune Deficiency Syndrome (AIDS) are a global emergency. Infection with HIV can lead to poor health, loss of lives, increased number of orphans and reduced national productivity. In Kenya and Uganda, National AIDS & STI Control Programme (NASCOP) and the Uganda AIDS Commission (UAC) respectively are promoting combination of approaches for HIV prevention with the key populations. Studies have revealed that 1.5 million people live with HIV with a 5.9% adult HIV prevalence. There are an estimated 78,000 new HIV infections with 36,000 aids related deaths and 59% adults on antiretroviral treatment (AVERT 2016). Complex socio-cultural, economic, and health-system factors inhibit excellent patient retention. Better tracking, enhanced social support, and regular adherence counseling in addressing stigma, and alternative healing options are needed. Intervention strategies aimed at changing clinic routines and improving patient–provider communication could address many of the identified barriers (Tiruneh et al. 2016). The objective of the study is to develop a tool to predict possible loss-to-follow-up among mobile people living with HIV/AIDS enrolled in care and treatment at the Busia border.