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 33

Analysis of Determinants of M-Commerce Adoption by Online Consumers
(Center for Promoting Ideas, USA, 2014) Gitau, L.; Nzuki, D. M.
M-Commerce is the making of payments for products and services through the use of mobile devices. The proliferation of mobile devices has resulted to into substantial growth of M-commerce. This is as a result of anytime anywhere connectivity, low cost of business, increased new sales avenues and customer loyalty. But even with the high penetration rate of Mobile phones, a relatively low adoption rate of M-Commerce has been observed in the developing countries. This study provides the theoretical underpinning for various interventions to promote M-Commerce Adoption. The study uses the literature review to identify the factors which influence the adoption of M-Commerce by consumers. The results from this study will be useful to m-commerce companies in formulating appropriate marketing strategies, as well as developing appropriate applications that address the needs and resources of various stakeholders. The outcome of this study will guide companies that offer MCommerce related products in the selection of digital products and in pursuance of future commercial opportunities. The finding of this study recommends that the government should set up legislation that would ensure customer security in order to enhance trust and hence enhance M-Commerce adoption.
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%.
Customers Perception on Prior Knowledge of Technology and Its Effect on Usage of Internet Banking in Commercial Banks in Kenya
(Paper Publications, 2015) Waithaka, Stephen Titus; Muthengi, Kilembwa; Nzeveka, Joseph
Internet banking allows banks to provide information and offer services to their customers conveniently using the internet technology. However, studies have shown that customers have perceptions that impact on the uptake and continuous usage of the platform. The purpose of this study is to understand the effect of customer perceptions on usage of internet banking in commercial banks in Kenya. This study used descriptive research design while a stratified random sampling technique was used to select subjects to represent the target population which was made up of 1,837,312 customers of commercial banks within Nairobi County. An estimated 384 respondents were targeted to participate in the study. 272 questionnaires representing a 71% response rate were received and analysed. Based on the findings of the research it was concluded that customers perceptions have an effect on usage of internet banking. Prior knowledge of technology was forund to have an impediment in using internet banking by customers. Not all customers are well versed in using systems used in accessing internet banking- both software and hard ware.
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
The Effect of Customers Perception on Security and Privacy of Internet Banking on Its Usage in Commercial Banks in Kenya
(Paper Publications, 2015) Waithaka, Stephen Titus; Muthengi, Kilembwa; Nzeveka, Joseph
Internet banking allows banks to provide information and offer services to their customers conveniently using the internet technology. However, studies have shown that customers have perceptions that impact on the uptake and continuous usage of the platform. The purpose of this study is to understand the effect of customer perceptions on usage of internet banking in commercial banks in Kenya. This study used descriptive research design while a stratified random sampling technique was used to select subjects to represent the target population which was made up of 1,837,312 customers of commercial banks within Nairobi County. An estimated 384 respondents were targeted to participate in the study. 272 questionnaires representing a 71% response rate were received and analysed. Based on the findings of the research it was concluded that customers have perception that have an effect on usage of internet banking. Customers both users and potential, are still apprehensive about the security of internet banking transactions and privacy of their sessions while online. Due to increased phishing, on online scams and frauds perpetrated online customers are reluctant to adopt or continue using internet banking. It is the responsibility of commercial banks to sensitize their customers and assure them that it is safe to access internet banking from both a private and public network. They should provide customers with guidelines on how to safe guard their information and secure their log on credential while using both private and public network
An Enhanced Service Flow Management Scheme for IEEE 802.16 Broadband Wireless Access Systems
(International Journal of Computer Theory and Engineering, 2012-08) Musau, Felix; Kipkorir, Sang; Mwamafundo, Juma Modie
 Abstract—While the protocols have been proposed to support QoS (quality of service) guarantees for a variety of applications, the WiMax/IEEE 802.16 standard does not specify a mandatory scheduling architecture to fulfill stringent QoS requirement for the different classes of traffic. Only the framework is established in the standard which provides an opportunity for developers to design efficient scheduling mechanism to fulfill stringent QoS requirement for the different classes of traffic. The scheduling scheme requires catering for rigorous QoS guarantee for all types of service flows as specified in the standard, enabling fairness and facilitating the traffic of lower priority. In this paper, we propose a Service Flow Management Scheme for the IEEE 802.16 Broadband Wireless Access systems that can provide QOS support that enhances performance through a scheduler that performs optimally and efficient
Enhancing Exploratory Learning Using Computer Simulation in an E-learning Environment: A Literature Review
(Center for Open Access in Science, 2020) Kanyaru, Paul; Maina, Elizaphan
Computer simulation has been shown to elicit exploratory behavior and creativity in learners. Various researches have indicated that during an exploratory learning process students can acquire knowledge either through inquiring or exploring an open learning environment. Further, the research shows that as opposed to instruction-based learning, exploratory learning is mainly based on self-motivation by learners. Therefore, computer simulation when used to enhance exploratory learning concept especially in an e-learning platform, has been seen to achieve the learning objectives as explained by Bloom taxonomy. In this regard, computer simulation has been seen to help learners conceptualize important concepts especially in science subjects. Additionally, the use of simulation is regarded as an aid to improving understanding of various concepts as well, as helping increase breadth of knowledge.
Evaluation of intelligent grouping based on learners’ collaboration competence level in online collaborative learning environment
(Athabasca University, 2016-02) Maina, E.M.; Oboko, R.; Waiganjo, P.W.
In this paper we explore the impact of an intelligent grouping algorithm based on learners’ collaborative competency when compared with (a) instructor based Grade Point Average (GPA) method level and (b) random method, on group outcomes and group collaboration problems in an online collaborative learning environment. An intelligent grouping algorithm has been added in a Learning Management System (LMS) which is capable of forming heterogeneous groups based on learners’ collaborative competency level. True experiment design methodology was deployed to examine whether there is any association between group formation method and group scores, learning experiences and group problems. From the findings, all groups had almost similar mean scores in all group tests, and shared many similar group collaboration problems and learning experiences. However, with the understanding that GPA group formation method involves the instructor, may not be dynamic, and the random method does not guarantee heterogeneity based on learner’s collaboration competence level, instructors are more likely to adopt our intelligent grouping method as the findings show that it has similar results. Furthermore, it provides an added advantage in supporting group formation due to its guarantee on heterogeneity, dynamism, and less instructor involvement.
Facilitating Group Learner Participation using Intelligent Agents in Collaborative M-Learning
(IEEE, 2018) Njenga, Stephen; Oboko, Robert; Omwenga, Elijah; Maina, Elizaphan
Most Leaning Management Systems provide a facility for online group discussions. Grouping members together does not give a surety of their participation in those online discussions. However, intelligent agents can facilitate group participation to motivate members to participate effectively in group discussions leading to enhanced levels of group knowledge construction. This paper discusses an experimental design for evaluating agent-based facilitated group learner participation for online group discussions in mobile learning environments. The experiment uses two treatment groups and one control group. We compared the levels of group knowledge construction amongst the three groups. The findings showed improved levels of group knowledge construction in the treatment groups compared to the control group. Thus, we recommend the use of intelligent agents in facilitating group participation and subsequently improving the group knowledge construction in collaborative m-learning.
Gamification Model for E-Learning Platforms
(IST-Africa, 2019) Kamunya, Samuel; Maina, Elizaphan; Oboko, Robert
The use of gamification in education has been viewed as an innovative approach to introduce benefits of games in a non gaming context. Instructively, for a successful gamification process in learning, motivational theories and behavioral outcomes for the learner have to be incorporated in design framework. Observably gamification projects particularly within the education domain for e-learning platforms have encountered challenges key amongst them, emanating from lack of appropriate gamification design framework. Subsequently the study sought through systematic literature review to investigate types of gamification design frameworks. 16 design frameworks were evaluated and only 2 frameworks were designed for gamification within an e-learning environment. However the two frameworks did not address motivational affordances, behavioral Outcomes and evaluations rigor. In view of this the study proposes a framework identifying games elements as motivational affordances that influence behavioral outcome of the learner
Gamified Blood Donors System Based on Intelligent Agents
(OJIT, 2021) Karanja, James Mugi; Njoroge, Harrison
The population of the country of Kenya is drastically increasing thus causing the number of possible blood donors to rise. Despite this, the blood collected and stored in most blood banks is not enough to cater for the huge demand. The demand has been due to increase of number of accidents experienced in the country and the advancement in medical procedures which calls for organ transplant and blood transfusion. Even though systems have been developed which can connect the donors and recipients and location tracking, most people are dying because they don`t get this vital commodity in good time. The process of donating blood has not been enticing. There is nothing that prompts a person to donate blood. This call for developing a gamified blood donor management system based on intelligent agents so as to increase the number of donors and keep the system performance at optimal level. The project adopts Goal-Oriented Methodology in the system development process. Two agents are developed: donors’ agent and the blood admin agent. The intelligent agents help in profiles personalization thus improving the system performance. Gamification technique is implemented in the system so as to increase the traffic of blood donors interacting with the system and participating in the donation exercise. This increase the number of blood donors hence enough blood is collected to cater for the huge demand
Hospital Information Systems Capability and End-User Satisfaction in Hospitals of Nairobi County, Kenya
(IAJIST, 2018) Omune, Onyando George; Kandiri, John M.
Hospitals in Nairobi County, Kenya continue to automate their processes to improve service delivery to their clients by implementing hospital Information Systems (HIS). As studies have revealed, end user satisfaction plays an important role in information systems acceptance, and ultimate success. The study focused on HIS capability and how it affects end user satisfaction in the hospitals by use of descriptive and observations techniques. The scope of this study was hospitals in Nairobi County, Kenya with bed capacity of at least 100 and had used HIS for a period of not less than a year. Stratified sampling method was preferred for sampling of study respondents from the selected ten hospitals of Nairobi County that met inclusion criteria and simple random sampling technique, to select respondents respectively. Semi structured questionnaires were used to collect primary data from a population of 374 respondents. The data collected was analyzed quantitatively using descriptive statistics comprising of the mean, standard deviation and P-values. Statistical Package for Social Sciences (SPSS) version 22, Microsoft Office Excel 2013 and descriptive statistics were the main tools used to analyze the data. The results have shown that systems quality, information quality and service quality of HIS positively affect end user satisfaction.
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.
Influence processes of implementation effectiveness in challenged information technology projects in Africa.
(Emerald, 2014) Ochara, N.M.; Kandiri, J.; Johnson, R.
Purpose – This research reports on how influence processes (IP) impact on the implementation effectiveness of information technology (IT) projects. Drawing on an innovation perspective that elevate the interplay of factors related to innovations framing, innovations environment and innovation attributes, the study focused on IT projects based in Africa that are generally classified as “challenged” due to the conditions in the environment. The purpose of this paper is to assess how IP related to innovation framing, innovation environment and innovation attributes can be used to determine implementation effectiveness. Design/methodology/approach – Using a interpretive approach, a case study of institutions under a partnership that has been implementing various educational technologies in five African countries formed the sample. In all, 25 interviews of top-management representatives, project leaders and user representatives were conducted between 2012 and 2013 to assess the implementation effectiveness of these projects. Theoretical thematic analysis, based on a deductive approach, was employed to analyse the data. Findings – The results show that a majority of these development-oriented projects are “mandated failures” characterized by high framing, a bad internal environment and typically negative innovation attributes. That typically, the institutions engage symbolically in such innovations initiatives which are regarded as “show” projects. Such behaviour can be construed to be a pattern of cynical technology adoption linked to the appeasement of external stakeholders. In addition, participation in initiatives was largely symbolic and is considered as a mere demonstration of a modern organization that is technologically aware, yet the requisite innovation environment is lacking for effective appropriation of the technology. Third, mandated failures result in low morale of employees, who regard themselves as pawns in the process which make them grudgingly participate in the implementation process. Practical implications – These findings have implications for managing innovations in such challenged environments: the first proposition is that projects in challenged environment for innovation adopting organizations need to be considered as technology transfer projects. Second, the innovation environment and attributes can only be improved during implementation of the conditions related to absorptive capacity of the organization and the individual are addressed. Originality/value – The research reported in this paper, provides an empirical determination of the concept of implementation effectiveness by using three constructs of innovations framing, environment and attributes. On the basis of the empirical findings, an original contribution is claimed, especially in “challenged” IT project environments where the concept of success if fluid and outcomes uncertain.
Intelligent Conversational Agent for Enhancement of Online Communication in Universities: An Overview of Kenyatta University
(COAS, 2021) Kuria, Isaac; Njoroge, Harrison
University websites and online portals are the primary means through which potential students and other stakeholders find important information about an institution. University websites are essential to these organizations’ marketing and communication efforts. In this paper, focus has been put on the need to complement these websites with the use of an AI Chatbot (UniBot) in order to serve more efficiently. This study aims at performing an extensive literature survey on intelligent conversational agents and the feasibility of applying them in enhancing online communication in universities. The study utilizes an iterative – incremental methodology to aid in design and development of UniBot, using AIML (Artificial Intelligent Markup Language) Pattern matching algorithm on the Pandorabot (AIAAS) platform, to generate high quality training data, with which, the agents Natural Language Understanding (NLU) model is trained. The study also provides for training and testing the agent using data which is acquired from Online Communication, University Website department at Kenyatta University.
Learner Experience of E-learning Mode in Institutions of Higher Learning: A Case of Kenyan Universities
(IEEE, 2017) Maina, Elizaphan Muuro; Kihoro, John M.
This paper investigates learner experiences of e-learning mode in Institutions of Higher Learning (IHL) through a survey which was conducted in three public Universities. Through purposive sampling a questionnaire was distributed online to 300 students and 198 students responded. Based on descriptive analysis it was noted that students still preferred e-learning mode because of its convenience and flexibility. However, students still experienced some challenges such as inadequate lecturer facilitation, inadequate learning materials, lack of feedback from instructors, slow internet connectivity, and high internet rates. There was also significant difference between (i) gender ( =0.021), (ii) Age ( =0.030) and (iii) programme level ( =0.001) and students’ attitude towards e-learning mode. In view of these challenges students suggested that e-learning facilitators should; avail adequate quality learning materials, interact with students more frequently, introduce other modes of delivery such as U tube, Skype, and Video, increase internet bandwidth and consider introducing more courses online.
A Literature Review on Automatic Generation of Examinations
(COAS, 2021) Ndirangu, Peter Ndegwa; Muuro, Elizaphan Maina
The examination is a key activity in determining what the learner has gained from the study. Institutions of higher learning (IHL) perform this activity through various assessment methods (test/examination, practical, etc.). The world today is focused on automation of exam generation which is ongoing with dire need during this period of the COVID-19 pandemic when education is greatly affected, leading to embracing online learning and examination. A text/exam comprises questions and answers that focus on evaluation to determine the student’s conversant level in the area of study. Each question has a cognitive level as described by (Armstrong, 2016) in the revised Bloom’s taxonomy. Questions chosen have cognitive levels based on the level of study and standardization of the exam. There is, therefore, a need to consider the question’s cognitive level along with other factors when generating an examination by incorporating deep learning algorithms.
Machine Learning Techniques, Features, Datasets, and Algorithm Performance Parameters for Sentiment Analysis: a Systematic Review
(COAS, 2022) Ondara, Bernard; Waithaka, Stephen; Kandiri, John
The purpose of this paper is to review various studies on current machine learning techniques used in sentiment analysis with the primary focus on finding the most suitable combinations of the techniques, datasets, data features, and algorithm performance parameters used in most applications. To accomplish this, we performed a systematic review of 24 articles published between 2013 and 2020 covering machine learning techniques for sentiment analysis. The review shows that Support Vector Machine as well as Naïve Bayes techniques are the most popular machine learning techniques; word stem and n-grams are the most extensively applied features, and the Twitter dataset is the most predominant. This review further revealed that machine learning algorithms' performance depends on many factors, including the dataset, extracted features, and size of data used. Accuracy is the most commonly used algorithm performance metric. These findings offer important information for researchers and businesses to use when selecting suitable techniques, features, and datasets for sentiment analysis for various business applications such as brand reputation monitoring.
Multi-Agent Adaptive E-Learning System Based On Learning Styles
(Center for Open Access in Science, 2021) Kivuva, Faith Ngami; Maina, Elizaphan
Most traditional e-learning system fails to provide the intelligence that a learner may require during their learning process. Different learners have different learning styles but the current elearning systems are not able to provide personalized learning. In this paper, we discuss how intelligent agents can aid learners in their learning process. Three agents have been developed namely, learner agent, information agent, and tutor agents that will be integrated into a learning management system (Moodle). Learners are provided with a personalized recommendation based on the learning styles.
Multiplier Design using Machine Learning Alogorithms for Energy Efficiency
(VLSI, 2023) Juma, Jane; Mdodo, R.M.; Gichoya, David
Designers primary goal is to develop the Adder cell with improved performance viz. speed, fixed rise and fall time, as it the fundamental block in VLSI design process. The dynamic logic circuits are far better than the static logic circuits because it consumes less power and speed performance also increased. But, cascading of several blocks in dynamic logic is found to be a wrong analysis. This drawback of increased complexity with mismatched cascading is overcome by using domino logic circuits. By using domino logic circuits, the reduction of noise margins and increase the speed performance of the circuit is achieved. In this paper, domino logic based Manchester carry chain adder (MCC) is designed using FinFET 18nm technology in Cadence virtuoso. It is noticed that 4-bit and an 8-bit Manchester Carry Chain Adder (MCC) using domino logic design consumes less power and reduction in the delay of the proposed circuit compared with the previous architecture. Implementation results reveal that the 4-Bit MCC Adder has delay of 79.45% less compared to the existed standard design and power consumption also reduced to 94.15%.

Browse

Browsing RP-Department of Computing & Information Technology by Title

Results Per Page

Sort Options