School of Technology
Permanent URI for this collectionhttps://repository.kcau.ac.ke/handle/123456789/70
Browse
7 results
Search Results
Item Data Mining in Pediatric Radiology in the Era of Artificial Intelligence(Springer, 2026) Guarnera, Alessia; Ghosh, Adarsh; Gikera, Rufus; Vahdati, Sanaz; Zhang, Kuan; Gupta, AmitData mining is the systematic process of extracting useful knowledge from large multimodal datasets and is increasingly enabled by artificial intelligence (AI) methods. Pediatric radiology is a natural field for data mining because multimodal data sources, including images, reports, metadata, and electronic health records, together capture rich information on anatomy, disease, treatment, and outcomes. In the current era, the boundaries between data mining and AI are increasingly blurred. AI assists in key steps of the mining workflow through automated labeling, information extraction, and representation learning, while data mining provides the high-quality curated datasets that underpin model performance, generalizability, and safety. This review, therefore, examines both domains together, emphasizing their interdependence in the pediatric context. We describe core concepts and workflows of data mining in pediatric radiology, including data collection, linkage, annotation, analysis, validation, and governance, and outline how modern AI tools such as deep learning, large language models, multimodal fusion, and federated learning support advanced pattern discovery across limited and heterogeneous pediatric datasets. We summarize current and emerging clinical applications across diagnosis, prognosis, radiation dose monitoring, operational analytics, reporting safety nets, and continual learning. We then discuss current challenges related to data quality and standardization, ethics, regulation, workflow integration, resource disparities, sustainability, and explainability. Finally, we highlight future perspectives, including synthetic data generation, foundation models, structured reporting, and pediatric-focused ethical frameworks that aim to enable safe, transparent, and equitable integration of AI-driven data mining to improve outcomes in children.Item Knowledge management considerations in learning management systems in higher education institutions: a systematic review, synthesis and research agenda(Emerald Publishing, 2023) Omanyo, Joshua O.; Ndiege, Joshua R.Purpose This paper aims to examine the state of research on the symbiotic relationship between knowledge management and learning management systems in advancing the mutual strategic agenda of the two initiatives in higher education institutions (HEIs), so as to uncover the themes that have been studied, identify gaps in the existing studies and suggest future areas of research work. Design/methodology/approach The study adopted systematic literature review (SLR), in which 64 articles published between 2010 and 2022 were identified and analyzed. Findings Whereas the review revealed some focus areas that have been researched, it also found that only few studies have explicitly explored the symbiotic relationship between knowledge management and learning management systems, with fewer articles exploring this relationship finding their way to mainstream journals. Thus, the findings showed that examination of the interlink between knowledge management and learning management systems in HEIs is still less explored and has multiple possibilities for future research with potential benefits to the higher education industry. Originality/value Although different SLRs exist separately in the fields of knowledge management and learning management systems, there seem to be no reviews on the interconnection between the two fields in the context of HEIs. Additionally, this review offers insights into future research avenues for theory, content and context of interplay between knowledge management and learning management systems in HEIs.Item E-learning and sustainability of higher education in Sub-Saharan Africa: a review and synthesis(Emerald Publishing, 2025) Omanyo, Joshua O.; Ndiege, Joshua R. A.Purpose This study aims to examine the state of literature on the role of e-learning in the sustainability of higher education institutions in Sub-Saharan Africa, with the goal of identifying explored thematic areas, finding out the deficiencies in extant literature and recommending areas of future research work. Design/methodology/approach The research used a systematic literature review, examining articles published between 2012 and 2022. In total, 52 publications were identified and subjected to analysis. Findings The findings reveal that few studies have explored the relationship between e-learning and the sustainability of higher education in Sub-Saharan Africa, with larger economies in the region dominating research output. In addition, traditional technology adoption and social learning theories dominate the theoretical frameworks in this area. Moreover, the authors observed limited adaptation of these theories to local contexts, leading to outcomes with limited contextual details or lack of the same. Despite its potential, e-learning has yet to be fully embraced as a strategic tool for the sustainability of higher education in Sub-Saharan Africa. Originality/value Although various systematic literature reviews exist in the field of sustainability in higher education, there seem to be no reviews specifically focused on e-learning within the context of Sub-Saharan Africa. This review sheds some light on potential future research paths regarding the theory, content and context of e-learning for the sustainability of higher education in Sub-Saharan Africa, and by extension, in developing countries worldwide.Item Learning management systems and sustainability in Kenyan higher education institutions: a multi-group analysis using PLS-SEM(Emerald Publishing, 2026) Omanyo, Joshua O.; Ndiege, Joshua R. A.; Okello, Gabriel O.Purpose – This study seeks to examine how learning management system (LMS) quality influences perceived sustainability value (PSV) among usersin Kenyan higher education institutions(HEIs), by examining usage and user satisfaction as mediators based on the DeLone and McLean information systems success model (DMISSM). The triple bottom line (TBL) theory provided the theoretical grounding for measuring the overall perceived sustainability impact derived from LMS utilization in HEIs. Design/methodology/approach – This is a cross-sectional study. A stratified random sampling technique was used to collect data from 384 students and 375 instructors. Hypothesis testing was carried out following partial least squares structural equation modeling procedures using R statistical software. Findings – The empirical findings revealed that user satisfaction significantly mediated the relationship between LMS quality and PSV, while LMS Use had an insignificant mediating role in the same relationship. The impact of user satisfaction on PSV varied between teachers and students, with teachers experiencing a stronger influence. The findings also confirmed a statistically significant direct relationship between LMS quality and PSV. Originality/value – This study advances the DMISSM by adding learner and instructor quality contributors to the antecedent quality constructs, while integrating TBL sustainability dimensions as net benefits. The integration of sustainability into the model creates a new pathway for evaluating educational technologies beyond technical and user-centric metrics to a more long-term value-driven success aligned with global sustainability goals.Item A visual analytic framework for monitoring terror attacks: a case study of Mandera county, Kenya(KCA University, 2025) Mong'are, Brion G.Terrorism remains a persistent and evolving threat in Kenya, particularly in border counties such as Mandera, which face heightened vulnerability due to their proximity to Somalia. The Country’s ongoing instability, weak governance structures, and the presence of terrorist groups like al-Shabaab (AS) create fertile ground for cross-border militant activity, posing significant challenges to both regional security and local stability. A critical gap in current counterterrorism efforts is the absence of localised, data-driven frameworks capable of monitoring and predicting terrorist activities in real time. This study addresses that gap by developing a Visual Analytics (VA) framework tailored to monitor, analyse, and predict terrorist incidents, using Mandera County as a case study. Beyond processing complex datasets, the framework offers strategic guidance to decision-makers, enhancing situational awareness and enabling proactive counterterrorism interventions. The core objective is to strengthen counterterrorism strategies through spatiotemporal data mining techniques, such as cluster analysis, association analysis, and outlier detection, to derive actionable insights from both structured and unstructured data sources. The methodology integrates data from social media, security reports, and established databases such as the Global Terrorism Database (GTD) and the Armed Conflict Location & Event Data Project (ACLED). Visuals in the framework are guided by Shneiderman’s Visual Information-Seeking Mantra: “overview first, zoom and filter, then details on demand.” Through this approach, the system identifies attack hotspots, temporal patterns, and early warning indicators, delivering a user-centric tool for informed decision-making. Findings demonstrate the framework’s effectiveness in predicting high-risk areas and attack types, with particular emphasis on armed assaults and improvised explosive device (IED) incidents, which constitute over 50% of recorded attacks in Mandera. The results show improved allocation of security resources, enhanced inter-agency coordination, and timely intervention capabilities. Key recommendations include deploying the framework in high-risk regions, integrating it with existing security infrastructure, and expanding its use to other terrorism-affected areas. The framework’s scalable and adaptable design positions it as a valuable tool for strengthening counterterrorism efforts across Kenya and similar contexts.Item Detecting Data Exfiltration Anomalies in Academic Networks Using the Isolation Forest Algorithm(KCA University, 2025) Arusei, Mike K.; Dr. Njenga, StephenAcademic networks face increased risks of data exfiltration due to sensitive personal information and research data. Traditional supervised detection models rely on labeled datasets which are often unavailable in resource constrained institutions. This study investigates the applicability of the unsupervised Isolation Forest algorithm for detecting anomalous network traffic indicative of data exfiltration. The research utilized the CICIDS2017 dataset focusing on the Thursday-WorkingHours-Afternoon-Infiltration subset. Key features including Flow Duration, Total Fwd Packets, Flow Bytes/s, Flow IAT Mean, and Destination Port were preprocessed and normalized for modeling. The model achieved a precision of 1.00, recall of 0.99 and F1-score of 1.00 for anomalous traffic detection successfully identifying approximately 4.8% of flows as anomalous. Comparative analysis with previous methods, including supervised Random Forest and SVM demonstrated that Isolation Forest offers competitive accuracy with lower computational overhead and does not require labeled data. The findings highlight the algorithm’s suitability for academic network monitoring, providing an effective early warning mechanism while emphasizing the importance of threshold tuning to reduce false positives.Item Applying Data Mining in Graduates’ Employability : A Systematic Literature Review(International Journal of Engineering Pedagogy, 2023) Mburu, Lucy W.; Mwendia, Simon N.; Mpia, Héritier N.Envisaging an adequate IT/IS solution that can mitigate the employability problems is imperative because nowadays there is a high rate of unemployed graduates. Thus, the main goal of this systematic literature review (SLR) was to explore the application of data mining techniques in modeling employability and see how those techniques have been applied and which factors/variables have been retained to be the most predictors or/and prescribers of employability. Data mining techniques have shown the ability to serve as decision support tools in predicting and even prescribing employability. The review determined and analyzed the machine learning algorithms used in data mining to either predict or prescribe employability. This review used the PRISMA method to determine which studies from the existing literature to include as items for this SLR. Hence, 20 relevant studies, 16 of which are predicting employability and 4 of which are prescribing employability. These studies were selected from reliable databases: ScienceDirect, Springer, Wiley, IEEE Xplore, and Taylor and Francis. According to the results of this study, various data mining techniques can be used to predict and/or to prescribe employability. Furthermore, the variables/factors that predict and prescribe employability vary by country and the type of prediction or prescription conducted research. Nevertheless, all previous studies have relied more on skill as the main factor that predict and/or prescribe employability in developed countries and none studies have been conducted in unstable developing countries. Therefore, the need to conduct research on predicting or prescribing employability in such countries by trying to use contextual factors beyond skill as features.