RP-Department of Computing & Information Technology

Permanent URI for this collection

https://repository.ku.ac.ke/handle/123456789/5396

Browse

Now showing 1 - 20 of 46

An Ensemble Feature Selection Model with Machine Learning Model for Detection of Fraudulent Motor Vehicle Insurance Claims.
(TIJER-International Research Journals(TIJER), 2024-04) Wambu, Anthony Mwiti; Araka, Erik
Insurance companies are continuously inventing new competitive insurance products in order to enlarge their market share. This has continuously created opportunities for insurance fraud as well. In motor vehicle insurance, fraudulent claims continue to be a big challenge despite the insurance industry having vast amounts of motor vehicle insurance policy data and claim’s data. Proper analysis of this data can help to develop a more efficient way of detecting fraudulent claims. The challenge is how to extract insightful information and knowledge from this data since by their nature insurance datasets contain noisy features or subsets of data which are of poor quality. In order to achieve an effective machine learning model, one needs to choose the right set of features of data in the pre-processing step. Including noisy and less important features has proven to affect the performance of most of the existing machine learning models being used in the insurance companies. With aid of proper and effective feature selection techniques machine learning models that uses only relevant features of data can be developed in order to detect fraudulent insurance claims effectively. These models can be employed in insurance industry to aid in detecting fraudulent motor vehicle insurance claims. This will result in reduction of loss adjustment expenses and also improve customer satisfaction. Although there exist several other methods and ways of data preprocessing this study employed an ensemble multiple filter feature selection method. This study involved development of motor vehicle fraud detection model using multiple algorithms whose results were combined by use of a voting method.
Weather Forecasting using Radial Basis Function Network
(TIJER – International Research Journal, 2024-10) Kabue, Ceasar Waweru; Matheka, Abraham Mutua
Weather forecasting has been a critical component in various industries such as agriculture, disaster management, transportation, and urban planning. Accurate weather predictions have helped minimize disruptions, enhance decision-making, and reduce economic losses. Traditional forecasting models, including Numerical Weather Prediction (NWP) and Autoregressive Integrated Moving Average (ARIMA), proved effective but faced challenges due to the nonlinear and chaotic nature of weather systems. Minor errors in the initial conditions of these models resulted in substantial inaccuracies, especially for long-term forecasts. This phenomenon, commonly referred to as the "butterfly effect," highlighted the inherent limitations of traditional models in capturing the complexity of atmospheric systems. In response to these challenges, machine learning emerged as a promising alternative, offering the ability to manage vast amounts of complex, nonlinear data. Machine learning models, particularly Artificial Neural Networks (ANNs), demonstrated considerable success in short-term and mid-term weather forecasting. These models identified and generalized patterns in meteorological data that were not apparent through traditional methods. Among ANNs, Radial Basis Function Networks (RBFNs) showed potential due to their efficient handling of time-series data, fast training times, and ability to model nonlinear relationships with noisy inputs. This study explored the performance of RBFNs in weather forecasting and compared their effectiveness to advanced deep learning models such as Convolutional Neural Networks (CNNs) and Long Short-Term Memory networks (LSTMs). While CNNs were highly effective in extracting spatial features from satellite data and other weather imagery, LSTMs excelled in learning temporal dependencies, making them suitable for long-term weather forecasting tasks. However, both CNNs and LSTMs proved computationally expensive, requiring large datasets, extensive training times, and significant computational resources, which limited their application in real-time forecasting, especially in resource-constrained environments. The primary objective of this research was to evaluate the comparative performance of RBFNs, CNNs, and LSTMs in weather forecasting, focusing on accuracy, computational efficiency, and training time. Using historical weather data from the Kenya Meteorological Department, spanning from 2013 to 2023, the study assessed the predictive power of these models for key meteorological variables such as temperature, humidity, windspeed, sea-level pressure, and rainfall. The results indicated that RBFNs consistently outperformed CNNs and LSTMs, particularly in terms of computational efficiency and accuracy, making them a more viable option for real-time applications where speed and resource efficiency were critical. Additionally, this research highlighted the potential of hybrid models that combined RBFNs, CNNs, and LSTMs to leverage the strengths of each architecture. While RBFNs offered rapid real-time predictions, CNNs provided the spatial accuracy required for analyzing satellite imagery, and LSTMs captured long-term temporal patterns. The integration of these models significantly improved forecasting accuracy, particularly for chaotic and highly variable weather phenomena such as rainfall and windspeed. The study concluded that RBFNs were an optimal solution for weather forecasting in resource-limited environments due to their fast training times and reduced computational demands. The findings also suggested that further exploration into hybrid models could provide a more comprehensive and accurate framework for weather prediction. Future research should focus on integrating satellitebased data with ground-level observations to enhance spatial accuracy and utilizing hybrid machine learning models to combine the strengths of RBFNs, CNNs, and LSTMs. Moreover, the scalability and accessibility of these models could be improved through advanced data preprocessing techniques, model optimization, and transfer learning, ensuring their applicability in diverse geographical regions with varying levels of data availability
Enhancing Service Delivery in Public Sector by Leveraging on Digital Transformation: A Case of Kiambu Level Five Hospital
(Reviewed Journal of Social Science & Humanities, 2024-09) Wachira, Purity Wamuyu; Kandiri, John
In the publ ic sector, the main goal of service delivery is to make sure that people can get to and use important tools and services in a way that meets their needs. Service delivery is very important in the healthcare field, especially in state hospitals, because it has a direct effect on how well patients do and on the health of the people as a whole. Digital change has a big effect on service delivery because it lets companies use flexible organizational structures and connect digital business communities. The goal of this study was to look into how going digital has changed the way services are provided at Kenya's Kiambu Level 5 hospital. The study looked at how customer relationships, growing skills, and constant improvement affect the digital change process. Resou rce - based view, identify, distinguish, connect, and modify theories, as well as dynamic capability theories, were used to guide the study. Based on a detailed study approach, the study was carried out. The target group was made up of 282 Kiambu Level 5 hos pital workers. A group of 165 individuals was used as a sample. Structured surveys and an interview plan were used to gather the data. The study looked at how accurate and reliable research tools were. Descriptive statistics and regression analysis were us ed to look at quantitative data. Content analysis, on the other hand, was used to look at qualitative data. A strong link (r=0.822, p<.001) was found between the digital change factors and service performance. The study found that the three digital transfo rmation factors can explain about 66.9% of the differences in service performance. Continuous growth (p<.001) and customer interaction (p<.001) were both important. The study found that going digital has a big and good impact on service delivery at Kenya's Kiambu Level 5 Hospital, mainly through bettering relationships with customers and always making things better. The study said that Kiambu Level 5 Hospital should use digital tools to try to keep customers they already have. It was also suggested that the hospital spend money on digital technology to make the hospital more productive and find technology that guarantees on-ti me delivery of health services.
A Multi-Agent Monitoring System for Computer Networks
(International Journal of Computer and Organization Trends, 2025-03) Harrison, Amwayi; Mutua, Abraham
In today's business landscape, reliable network infrastructure is essential for uninterrupted operations. As networks increase in complexity, effective monitoring systems become crucial to ensure device performance and availability. This study presents a multi-agent-based system for monitoring computer network devices, utilizing autonomous agents to gather data through the Simple Network Management Protocol (SNMP). The proposed solution addresses scalability and network congestion challenges often seen in centralized monitoring systems by leveraging Apache Kafka to distribute and manage monitoring data efficiently while autonomous agents handle data collection, thereby reducing latency and minimizing network load. The research first examines existing multi-agent applications that leverage SNMP agents, identifying their limitations before introducing a novel model that integrates SNMP agents with Apache Kafka to facilitate scalable data ingestion. The system's performance was tested in a simulated environment, and significant enhancements in scalability and efficiency were observed for real-time monitoring. The findings conclude that combining multi-agent systems with Apache Kafka offers a robust framework for efficient, real-time network monitoring, with improved scalability and reduced latency compared to traditional centralized models.
YOLO-APD: Enhancing YOLOv8 for Robust Pedestrian Detection on Complex Road Geometries
(International Journal of Computer Trends and Technology, 2025-06) Joctum, Aquino; Kandiri, John
- Autonomous vehicle perception systems require robust pedestrian detection, particularly on geometrically complex roadways like Type-S curved surfaces, where standard RGB camera-based methods face limitations. This paper introduces YOLO-APD, a novel deep learning architecture enhancing the YOLOv8 framework specifically for this challenge. YOLO-APD integrates several key architectural modifications: a parameter-free SimAM attention mechanism, computationally efficient C3Ghost modules, a novel SimSPPF module for enhanced multi-scale feature pooling, the Mish activation function for improved optimization, and an Intelligent Gather & Distribute (IGD) module for superior feature fusion in the network's neck. The concept of leveraging vehicle steering dynamics for adaptive region-of-interest processing is also presented. Comprehensive evaluations on a custom CARLA dataset simulating complex scenarios demonstrate that YOLO-APD achieves state-of-the-art detection accuracy, reaching 77.7% mAP@0.5:0.95 and exceptional pedestrian recall exceeding 96%, significantly outperforming baseline models, including YOLOv8. Furthermore, it maintains real-time processing capabilities at 100 FPS, showcasing a superior balance between accuracy and efficiency. Ablation studies validate the synergistic contribution of each integrated component. Evaluation on the KITTI dataset confirms the architecture's potential while highlighting the need for domain adaptation. This research advances the development of highly accurate, efficient, and adaptable perception systems based on cost-effective sensors, contributing to enhanced safety and reliability for autonomous navigation in challenging, less-structured driving environments.
The Type of Knowledge Being Shared and its Effect on Organizational Growth at Kenyatta National Hospital, Nairobi County Kenya
(Journal of Multidisciplinary Engineering Science and Technology, 2022-11) Nyambaso, Elvinah Kerubo; Namande, Wekalao
Organizational growth of health sector in Kenya have not been exceptional in the challenges that face human resource management which among them is the patients complains on poor service delivery, lack of medical equipment, shortage of drugs, poor reputation that arises from malfunctioning Knowledge sharing strategies among others on the staff members. This study thus seeks to investigate the effect of knowledge sharing on the organizational growth of Kenyatta National Hospital. The study research objective was to determine the effect of the types of knowledge shared on organizational growth at Kenyatta National Hospital. The study was guided by Healthcare Knowledge-Sharing Model. The study used descriptive survey research design. The target population of the study was 200 respondents and sample size of 133 was used. The respondents of the study include 100 members of the staff who work at the hospital (5 doctors, 70 nurses, 5 laboratory technicians, 6 pharmacists, 7 clinical officers, 3 human resource staff & 4 nutritionists) and 100 patients. Quantitative data were analysed using both descriptive and inferential statistics. Descriptive statistics included frequencies, percentages, means, and standard deviation. Inferential statistics was analyzed using correlation and multiple linear regressions. Qualitative data was analysed thematically. Pearson Product Moment Correlation Coefficient and regression analysis was used in order to test the relationship between the dependent and independent variables. The study is significant as it helps address knowledge sharing, which is one of the most pertinent issues affecting organizational growth for hospitals and in particular Kenyatta National Hospital. The study is also important as it helps incorporate theories related to knowledge sharing and organizational growth. The study results showed that the types of knowledge commonly used at the Hospital is explicit knowledge sharing, organizational knowledge sharing, and provider knowledge sharing. In conclusion the type of knowledge being shared has a positive and statistically significant effect on organizational growth.
Network Intrusion Detection Using Extreme Machine Learning Algorithm with Extreme Gradient Boosting for Feature Selection
(Journal of the Kenya National Commission for UNESCO, 2024) Ntwiga, Alex; Araka, Eric
This study addresses the challenge of improving the performance of the Extreme Learning Machine model, particularly in accurately identifying minority classes in unbalanced datasets like UNSW-NB15 and NSLKDD. The research question guiding this study is: How can we improve the ELM model's performance for better accuracy and minority class recognition in network intrusion detection? The methodology includes balancing the dataset to address the issue of poor minority class identification, using XGBoost for feature selection to reduce the curse of high data dimensionality, Particle Swarm Optimization finally used to optimize the model. The results show that the proposed approach outperformed other models when tested on the NSL-KDD dataset, achieving accuracies of 94.29% for binary classification and 89.02% for multiclass classification. However, on the UNSW-NB15 dataset, the model achieved a binary accuracy of 90.79%, which was lower than the performance of Random Forest (93.02%) and Decision Tree (92.76 In the multiclass classification the accuracy achieved was 78.79%, indicating underperformance compared to the other state-of-the-art models. The study concludes that although the suggested approach performs well in binary classification, future studies need to focus on improving detection accuracies of datasets that are heavily unbalanced with multiple classes like UNSW-NB15 dataset.
Integrating Generative Artificial Intelligence in Assessment Generation for Higher Education: Computer Science Use Case
(IST-Africa, 2025) Kituku, Benson; Araka, Eric; Muuro, Elizaphan
The overburdened lecturers today face the dual challenge of monitoring online attendance and ensuring active student engagement, while also receiving instant feedback on concept comprehension during live lectures. They are further pressed to extend practical problem-solving experiences beyond the classroom and deliver higher-order thinking assessments - all without increasing their workload. In response, this paper presents a one-year experiment involving 590 students across seven computer science units. The study integrated generative AI-generated questions into live lectures, weekly discussion forums, and both formative and summative exams. The findings reveal that, with ethical use and proper human-inthe-loop, AI can significantly boost student engagement, promptly rectify misconceptions, and foster collaborative learning outside traditional settings and offer diverse question styles. However, given potential pitfalls such as low-quality outputs and overreliance, instructors must adhere to best practices and maintain rigorous oversight to ensure that assessments remain balanced, engaging, and of high quality, eventually benefiting both educators and learners.
Students’ Perceptions on the Use of Generative AI in Enhancing Teaching and Learning Computer Science Courses
(IST-Africa, 2025) Mwaniki, Susan; Araka, Eric; Kituku, Benson; Maina, Elizaphan
This research study examines the perception of third-year computer science students in Kenya towards the use of Generative Artificial Intelligence tools in their studies. The researchers used descriptive research design to understand student attitudes, the perceived usefulness of Generative Artificial Intelligence, and the challenges they face. The study finds that students generally see Generative Artificial Intelligence tools as beneficial for learning, especially in areas like coding and research. However, they also identify concerns about over-reliance on Generative Artificial Intelligence, accuracy of information, and ethical considerations, such as plagiarism. The study concludes that Generative Artificial Intelligence can be valuable in computer science education, however, it should be used reliably and balanced with traditional teaching methods to ensure critical thinking and creativity.
Promoting University Students’ Self-Regulated Learning Skills on E-Learning Platforms Using Educational Data Mining
(IST-Africa, 2025) Araka, Eric; Wario, Ruth; Maina, Elizaphan
Current e-learning platforms used by higher education institutions for open and distance learning often lack automation tools that offer personalized support to students. As a result, learners must take an active role in managing their learning process, as emphasized by the self-regulated learning theory. Given the flexibility of online learning, where students are not bound by fixed schedules, they must develop self-discipline and autonomy to effectively navigate and control their learning experience. This study examines the potential of educational data mining techniques to enhance students' self-regulated learning skills. A true experimental research design was deployed to assess the effectiveness of the developed educational data mining techniques -based interventions in fostering self-regulated learning. The study sample consisted of University students enrolled in a 12-week Data Science with Python course. Results from an independent t-test indicated that educational data mining interventions positively influenced students’ self-regulatory skills by strengthening their cognitive and behavioral learning strategies. However, no significant difference was found in final academic performance between students who received educational data mining interventions and those who received instructor-led support. By providing data-driven support, the study contributes to efforts aimed at improving student retention, reducing dropout rates, and enhancing academic performance in online learning environments. These findings provide a foundation for future research on integrating intelligent automation to support SRL in higher education.
Big data and personal information privacy in developing countries: insights from Kenya
(frontiers, 2025) Masinde Johnson; Mugambi Franklin; Muthee Daniel Wambiri
The present study examined the correlation between big data and personal information privacy in Kenya, a developing nation which has experienced a significant rise in utilization of data in the recent past. The study sought to assess the effectiveness of present data protection laws and policies, highlight challenges that individuals and organizations experience while securing their data, and propose mechanisms to enhance data protection frameworks and raise public awareness of data privacy issues. The study employed a mixed-methods approach, which included a survey of 500 participants, 20 interviews with key stakeholders, and an examination of 50 pertinent documents. Study findings show that the regulatory and legal frameworks though present are not enforced, demonstrating a gap between legislation and implementation. Furthermore, there is a lack of understanding about the risks posed by sharing personal information, and that more public education and awareness activities are required. The findings also demonstrate that while people are prepared to trade their personal information for concrete benefits, they are concerned about how their data is utilized and by whom. The study proposes the establishment of a National Data Literacy Training and Capacity Building Framework (NADACA), that should mandate the training of government officials in best practices for data governance and enforcement mechanisms, educate the public on personal data privacy and relevant laws, and ensure the integration of data literacy into the curriculum, alongside the provision of regular resources and workshops on data literacy. The study has significant implications for policymakers, industry representatives, and civil society organizations in Kenya and globally.
Trends and Advances on The K-Hyperparameter Tuning Techniques In High-Dimensional Space Clustering
(IJAIDM, 2023-09) Gikera, Rufus Kinyua; Mwaura, Jonathan; Maina, Elizaphan; Mambo, Shadrack
Clustering is one of the tasks performed during exploratory data analysis with an extensive and wealthy history in a variety of disciplines. Application of clustering in computational medicine is one such application of clustering that has proliferated in the recent past. K-means algorithms are the most popular because of their ability to adapt to new examples besides scaling up to large datasets. They are also easy to understand and implement. However, with k-means algorithms, k-hyperparameter tuning is a long standing challenge. The sparse and redundant nature of the high-dimensional datasets makes the k-hyperparameter tuning in high-dimensional space clustering a more challenging task. A proper k-hyperparameter tuning has a significant effect on the clustering results. A number of state-of-the art k-hyperparameter tuning techniques in high-dimensional space have been proposed. However, these techniques perform differently in a variety of high-dimensional datasets and data-dimensionality reduction methods. This article uses a five-step methodology to investigate the trends and advances on the state of the art k-hyperparameter tuning techniques in high-dimensional space clustering, data dimensionality reduction methods used with these techniques, their tuning strategies, nature of the datasets applied with them as well as the challenges associated with the cluster analysis in high-dimensional spaces. The metrics used in evaluating these techniques are also reviewed. The results of this review, elaborated in the discussion section, makes it efficient for data science researchers to undertake an empirical study among these techniques; a study that subsequently forms the basis for creating improved solutions to this k-hyperparameter tuning problem.
K-Hyperparameter Tuning in High-Dimensional Space Clustering: Solving Smooth Elbow Challenges Using an Ensemble Based Technique of a Self-Adapting Autoencoder and Internal Validation Indexes
(Tech Science Press, 2023-10-26) Gikera, Rufus; Mwaura, Jonathan; Muuro, Elizaphan; Mambo, Shadrack
k-means is a popular clustering algorithmbecause of its simplicity and scalability to handle large datasets.However, one of its setbacks is the challenge of identifying the correct k-hyperparameter value. Tuning this value correctly is critical for building effective k-means models. The use of the traditional elbow method to help identify this value has a long-standing literature. However, when using this method with certain datasets, smooth curves may appear, making it challenging to identify the k-value due to its unclear nature.Onthe other hand, various internal validation indexes, which are proposed as a solution to this issue, may be inconsistent. Although various techniques for solving smooth elbow challenges exist, k-hyperparameter tuning in high-dimensional spaces still remains intractable and an open research issue. In this paper, we have first reviewed the existing techniques for solving smooth elbow challenges. The identified research gaps are then utilized in the development of the new technique. The new technique, referred to as the ensemble-based technique of a self-adapting autoencoder and internal validation indexes, is then validated in high-dimensional space clustering. The optimal k-value, tuned by this technique using a voting scheme, is a trade-off between the number of clusters visualized in the autoencoder’s latent space, k-value from the ensemble internal validation index score and one that generates a value of 0 or close to 0 on the derivative f ___ (k)(1+f _ (k)2)−3 f __ (k)2f __ ((k)2f _ (k), at the elbow. Experimental results based on theCochran’sQtest,ANOVA, andMcNemar’s score indicate a relativelygoodperformanceof thenewlydevelopedtechnique ink-hyperparameter tuning.
Hybrid Machine Learning Techniques for Comparative Opinion Mining
(IJAIDM, 2023-08) Ondara, Bernard; Waithaka, Stephen; Kandiri, John; Muchemi,Lawrence
Comparative opinion mining has lately gained traction among individuals and businesses due to its growing range of applications in brand reputation monitoring and consumer decision making among others. Past research in sub-field of opinion mining have mostly explored single-entity opinion mining models and the mining of comparative sentences suing single classifiers. Most of these studies relied on a limited number of comparative opinion labels and datasets while applying the techniques in limited domains. Consequently, the reported performances of the techniques might not be optimal in some cases like working with big data. In this study, however, we developed four hybrid machine learning techniques, with which we performed multi-class based comparative opinion mining using three datasets from different domains. From our results, the best-performing hybrid machine learning technique for comparative opinion mining using a multi-layer perceptron as the base estimator was the Multilayer Perceptron + Random Forest (MLP + RF). This technique had an average accuracy of 93.0% and an F1-score of 93.0%. These results show that our hybrid machine learning techniques could reliably be used for comparative opinion mining to support business needs like brand reputation monitoring.
The Competencies of Fashion Design Teachers in Public Institutions of Higher Learning in Nairobi County, Kenya
(IJSBAR, 2016) Isika, Juliet Kaindia; Mburugu, Keren; Nguku, Everlyn; Obere, Almadi
‘Real’ fabric draping involves the use of sample textile, fabric or cloth to make patterns or garments on a model or dress form stands manually. The technique is suitable for ready-to-wear and couture garment designs and has numerous advantages, including satisfaction with garment fit, accurate proportions of fabric division and reduced time waste. Numerous studies in Kenya have been carried out on the subject of Home Science. However, little documentation exists on ‘real’ fabric draping for design in Kenya. This paper anchors its discussion on the findings of a study that sought to assess the usage of ‘real’ fabric in draping by teachers in public institutions of higher learning and fashion designers in Nairobi County, Kenya, and assesses the competencies of fashion design teachers in Nairobi County, Kenya. It also examines the relationship between the use of ‘real’ fabric draping for design, on the one hand, and the teachers’ area of training on the other hand. The study was guided by the activity theory and pedagogic activity system structure. Employing a crosssectional survey research design, five public institutions of higher learning were purposively selected. The sample size comprised five heads of department, 32 teachers and 266 students. The data was collected using questionnaires and interview schedules. Both qualitative and quantitative data analysis techniques were used. The results revealed that very few public institutions of higher learning use ‘real’ fabric draping for design. Majority of the teachers were not trained in the area of fashion design. Chi-square analysis results yielded a fairly strong relationship between use of ‘real’ fabric draping for design and pattern development technique taught (V= 0 .646; p < 0.0001*) and sources of curriculum (V= 0.623; p < 0.0001*). Use of ‘real’ fabric draping for design had a weak association with teachers’ area of training (V = 0. 018; p < 0.006). It was concluded that the teachers area of training was not highly associated with the use of ‘real’ fabric draping. This may be due to the fact that most fashion design teachers were trained in clothing / garment design and are able to understand the technique. Pattern development technique taught and sources of curriculum and teachers’ area of training are the key issues associated with the use of ‘real’ fabric draping for design in public institutions of higher learning. This paper recommends that public institutions of higher learning should ensure that teachers engaged have the adequate skills to teach ‘real’ fabric draping for design as a practical unit. This would ensure that the students acquire pertinent skills imparted as prescribed in the curriculum.
Social Media Influence on Personal Security among the Youth in Nairobi City County, Kenya
(EANSO, 2023) Soita, Sally; Njoroge, Harrison
This study examined positive uses of social media that include warning and preventing individuals from violence resulting from negative uses of social media and user victimisation. The study was guided by Space transition theory which states that criminals are more likely to commit crimes in cyberspace more than in physical space due to anonymity and identity flexibility. The objective of the study was to determine the forms of social media use among the youths in Nairobi County. The target population were members of the Professional Criminologists Association of Kenya (PCAK). Purposive sampling was used to select 155 youth respondents from a population of 15000 youths and 145 law enforcement informant interviewees drawn from 2,000 law enforcement officers in PCAK in Nairobi County. Piloting of the questionnaire was disseminated among 30 PCAK youths Nakuru chapter. The research instruments were verified by the supervisor for content validity. Statistical Packages for Social Sciences, SPSS and Microsoft Excel software were used in data entry and descriptive statistics were used to analyse the data. Qualitative data were analysed using content analysis, coding, classification, and text inferencing. This study was significant to academic research, criminal justice practitioners and the private sector to assist in goal formulation and achievement of cyber security. The results of this research showed that the form of social media that youth mostly prefer +are WhatsApp over other social media platforms. The most preferred social media platforms by both genders were found to be WhatsApp and Twitter. It was recommended that future research could focus on the modern methods of social media as technology is dynamic. This will give direction on the contemporary forms of social media and their relationship to personal security; this, in turn, improves the security settings suitable for the users.
Critical Literature Review on Current State-of-the Art in Predicting Students’ Performance using Machine Learning Algorithm in Blended Learning Environment
(AJOEI, 2023) Ofori, Francis; Matheka, Abraham; Maina, Elizaphan
Background of the study: Predicting and analyzing the performance of the student in a blended learning environment is important to help educators identify poor performing students and improve their academic score. Meanwhile, achieving accurate predictions require selecting machine learning techniques that can produce optimum score. However, there seems to be no critical literature review on current state of art in predicting students’ performance using machine learning algorithms in blended learning environment. Methodology: This critical literature review focuses on, studies on the current state of the art in predicting students’ performance in the blended learning for past 10 years, sources of dataset used by various authors and the machined learning algorithm with high prediction accuracy. Findings: Naïve Bayes was the most frequently used algorithm for predicting students’ performance. Authors mostly used online data for their student’s performance prediction. Finally, artificial neural network was found to give higher prediction accuracy of 98.7%.
Using Educational Data Mining Techniques to Identify Profiles in Self-Regulated Learning: An Empirical Evaluation
(International Review of Research in Open and Distributed Learning, 2022) Araka, Eric; Oboko, Robert; Maina, Elizaphan; Gitonga, Rhoda
With the increased emphasis on the benefits of self-regulated learning (SRL), it is important to make use of the huge amounts of educational data generated from online learning environments to identify the appropriate educational data mining (EDM) techniques that can help explore and understand online learners’ behavioral patterns. Understanding learner behaviors helps us gain more insights into the right types of interventions that can be offered to online learners who currently receive limited support from instructors as compared to their counterparts in traditional face-to-face classrooms. In view of this, our study first identified an optimal EDM algorithm by empirically evaluating the potential of three clustering algorithms (expectation-maximization, agglomerative hierarchical, and k-means) to identify SRL profiles using trace data collected from the Open University of the UK. Results revealed that agglomerative hierarchical was the optimal algorithm, with four clusters. From the four clusters, four SRL profiles were identified: poor self-regulators, intermediate self-regulators, good self-regulators, and exemplary selfregulators. Second, through correlation analysis, our study established that there is a significant relationship between the SRL profiles and students’ final results. Based on our findings, we recommend agglomerative hierarchical as the optimal algorithm to identify SRL profiles in online learning environments. Furthermore, these profiles could provide insights on how to design a learning management system which could promote SRL, based on learner behaviors.
Determinants of Mobile Banking Adoption by Customers of Microfinance Institutions in Nairobi County in Kenya
(International Journal of Science and Research (IJSR), 2015) Wamai, John; Kandiri, John M
Mobile technology usage has had various impacts on individuals and enterprises at different levels. Several factors have been sighted by different researchers as contributing either positively or negatively to the adoption of Mobile banking technology. Banks have implemented this technology to enable them reach more customers due to its ubiquitous nature and to reduce the cost of putting up new branches in their areas of operations. For this effort to be felt and for the technology to be implemented effectively, there is need to understand the factors contributing to its adoption by the customers. This study was carried out to investigate the effects of important factors that affect adoption of mobile banking technology by customers of Microfinance Institutions in Nairobi County, Kenya. A sample of 210 customers were selected randomly and the researcher extended the Technology Acceptance Model (TAM) framework. The study found that both perceived usefulness and perceived ease of use positively correlate and affects adoption of mobile banking technology positively. On the other hand, Perceived Risk and Perceived transaction costs were found to have negative correlation with the adoption of mobile banking technology
Students’Perceived Challenges in an Online Collaborative Learning Environment: A Case of Higher Learning Institutions in Nairobi, Kenya
(\'E}rudit, 2014) Muuro, Maina Elizaphan; Wagacha, Waiganjo Peter; Oboko, Robert; Kihoro, John
Earlier forms of distance education were characterized by minimal social interaction like correspondence, television, video and radio. However, the World Wide Web (WWW) and online learning introduced the opportunity for much more social interaction, particularly among learners, and this has been further made possible through social media in Web 2.0. The increased availability of collaborative tools in Web 2.0 has made it possible to have online collaborative learning realized in Higher Learning Institutions (HLIs). However, learners can perceive the online collaborative learning process as challenging and they fail to utilize these collaborative tools effectively. Although a number of challenges have been mentioned in the literature, considerable diversity exists among countries due to diversity in infrastructure support for e-learning and learners’ background. This motivated this study to investigate components of online collaborative learning perceived as challenging by learners in HLIs in Kenya. Using a questionnaire, a survey was conducted in two public universities and two private universities to identify students’ perceived challenges in an online collaborative learning environment. Through purposive sampling the questionnaire was distributed to 210 students using e-mail and 183 students responded. Based on descriptive analysis the following five major challenges were rated as high: lack of feedback from instructors, lack of feedback from peers, lack of time to participate, slow internet connectivity, and low or no participation of other group members. There was also a relationship between the university type (private or public) with the perceived challenges which included: lack of feedback from the instructor (𝒑=0.046) and work load not shared equally among group members (𝒑=0.000). Apart from slow internet connectivity the rest of the challenges were in line with the observed challenges in the literature.These key challenges identified in this study should provide insight to educators on the areas of collaborative learning that should be improved in order to provide access to quality education that supports effective online collaborative learning in HLIs in Kenya

Browse

Recent Submissions