School of Technology

Permanent URI for this collectionhttp://192.168.8.146:4000/handle/123456789/70

Browse

Now showing 1 - 20 of 32

3-Category pedagogical framework for context based ambient learning
(IEEE, 2013) Mwendia, Simon N.; Waiganjo, Peter; Oboko, Robert
Mobile phones have taken centre stage in transforming people’s lives in all sectors of African economies. With regard to Education sector, studies show that, there is high prevalence of mobile phones among learners in African universities but no computer prevalence. However, E-learning technologies are not readily available among learners. Learners are therefore forced to access content from few fixed locations with internet connectivity such as cyber cafes and workplace, eliminating access flexibility in learning. The ‘Mobile phone rich’ but ‘computer poor’ context prevailing in African universities presents an opportunity to establish an appropriate type of learning that utilizes mobile phones rather than computers. This paper explores existing categories of m-learning projects and proposes a 3-category framework to provide better understanding of ambient learning and allow integration of future ambient learning projects situated in different learning environments.
A contextualized and personalized model to predict user interest using location-based social networks
(Elsevier Ltd., 2016) Mburu, Lucy W.; Li, Ming; Sagl, Günther; Fan, Hongchao
The accurate determination of user interest in terms of geographic information is essential to numerous mobile applications, such as recommender systems and mobile advertising. User interest is greatly influenced by the usage context and varies across individuals; therefore, a user interest model should incorporate these individual needs and propensities. In this paper, we present an approach to model user interest in a contextualized and personalized manner based on location-based social networks. Multinomial logistic regression is employed to quantify the relationship between user interest and usage context at both the aggregate and individual levels. The proposed approach is tested in a real-world application using Foursquare check-ins issued between February and June 2014 in the three major cities of Chicago, Los Angeles and New York. Results demonstrate the capability of the contextualization process for capturing contextual influences on user interest, and that such influences can be observed at a fine-grained scale at the individual level through the personalization process. The proposed approach therefore enables contextualized and personalized estimation of user interest, thereby contributing useful information to follow-up mobile applications.
A knowledge-as-a-service support framework for ambient learning in Kenya
(13th IADIS International Conference Information Systems, 2020) Mburu, Lucy W.; Karanja, Richard; Nyaga, Simon M.
Knowledge as a Service (KaaS) is a relatively new model, albeit one that is rapidly gaining popularity within cloud computing environments. Over the recent years, learners have experienced a constant need to access on demand knowledge that is fully aligned with the paradigm of cloud computing. This need stems from the knowledge that users will be able to access applications and the information therein on demand, without the restrictions that are usually imposed by time and space. The KaaS model terms knowledge as the understanding of information based on its relevance to a specific context and problem area, thus forming a valuable resource for the human decision-making process. As motivated by the global sustainable development goal of ensuring inclusive and equitable quality education to promote learning opportunities for all, this research has developed a framework that is hinged on KaaS and utilizes knowledge from ambient learning systems. The main aim is to provide a platform for disseminating and exploiting the available knowledge to aid the learning process and, thus, to improve the quality of education on the ambient learning system. The research further explores how collaborative effort can be used to form a knowledge network that allows access to heterogeneous sources of knowledge. The research outcomes will benefit knowledge consumers such as the developers of ambient learning systems.
Ambient learning - knowledge as a service model: towards the achievement of sustainable development goal four
(IEEE, 2018) Mwendia, Simon N.; Karanja, Richard G.
Studies show that United Nations Sustainable Development Goal Four is yet to be achieved. This paper presents an artefact named “Ambient learning- Knowledge as a Service model” for describing how actionable knowledge can be extracted from ambient learning systems to support improvement and consequently facilitate the achievement of Sustainable Development Goal Four. A creative process was adopted to guide the development of the model. The process involved carrying out problem analysis through literature review, designing the model by combining ambient learning and Knowledge as a Service concept and demonstrating its application by developing a prototype. Evaluation results revealed that C4.5 algorithm that is implemented in Waikato Environment for Knowledge Analysis (WEKA) software is suitable for extracting knowledge from ambient learning systems while Swi-prolog software can be applied to create a tool for knowledge delivery.
Ambient learning conceptual framework for bridging digital divide in higher education
(IGI Global, 2014) Mwendia, Simon N.; Wagacha, Peter W.; Oboko, Robert
According to ITU (2012), digital divide is the difference between countries in terms of levels of ICT development. This difference remains significant. In 2011, the ICT Development Index (IDI) value of developed countries (6.52) was twice as high as that of developing countries (3.24). The need to link the digital divide for universal broadband Internet access is within the key international development goals, which include World Summit on the Information Society (WSIS) goals and Millennium Development Goals (MDGs). Ambient learning is the next generation of M-learning (Bick, Kummer, Pawlowski, & Veith, 2007), which allows flexible content access by considering learner's current situation and learning context (Kofod-Petersen, et al., 2008). However, ambient learning has not yet attained a state of common understanding (Winker, Scharf, Hahn, & Herczeg, 2011) and is not widely used or adopted (Bick, et al., 2007). This chapter presents a theoretical conceptual framework to foster creativity for innovative ambient learning applications, which can be used to bridge the digital gap between universities in developed and developing countries.
An empirical approach to mobile learning on mobile ad hoc networks
(Institute of Electrical and Electronics Engineers (IEEE), 2020) Mwendia, Simon N.; Ichaba, Mutuma; Musau, Felix
Mobile Ad hoc Networks (MANETs) are made up of mobile nodes that are interconnected wirelessly, while topology changes as mobile nodes join and leave the network. MANETs do not depend on fixed infrastructure. Due to their dynamism and low cost (no infrastructure is needed), MANETs have been proposed as a mechanism suitable for carrying out mobile learning (m-Leaning) in developing countries. However, systematic literature review indicates that the existing MANETs-based m-Learning models are disadvantaged because they fail to identify possible routing protocols able to support such models. As a result, it becomes very difficult to implement the existing MANET-based m-Learning models. This paper characterizes MANETs-based m-Learning proposed by [1]. Thereafter, it uses area, nodes, and data packets information as basic scalar parameters on Zone Routing Protocol (ZRP) simulated on NS-2 and ZRP code supplemented with positional and directional information of nodes in the Intrazonal Routing Protocol (IARP) on OMNET++. According to simulation results, a directional-positional enhanced ZRP outperforms regular ZRP on packet delivery ratio, delay and overall data packet throughput. Results from the simulation suggests that a supplemented ZRP is a feasible routing protocol for supporting m-Learning in a typical university campus based on the identified basic scalar parameters and characterization of [1].
Analysis of community properties and node properties to understand the structure of the bus transport network
(ScienceDirect, 2016) Mburu, Lucy W.; Sun, Yeran; Wang, Shaohua
Akin to most infrastructures, intraurban bus networks are large and highly complex. Understanding the composition of such networks requires an intricate decomposition of the network into modules, taking into account the manner in which network links are distributed among the nodes. There exists for each set of highly interlinked nodes little connectivity with the next set of highly interlinked nodes. This inherent property of nodes makes community detection a popular approach for analyzing the structure of complex networks. In this study, we attempt to understand the structure of the intraurban bus network of Ireland’s capital city, Dublin in a two-step approach. We first analyze the modular structure of the network by identifying potential communities. Secondly, we assess the prominence of each network node by examining the module-based topological properties of the nodes. Results of this empirical study reveal a clear pattern of independent communities, indicating thus, an implicit multi-community structure of the intraurban bus network. Examination of the geographic characteristics of the identified communities shows a degree of socio-economic divisions of the Dublin city. Furthermore, a large majority of the important nodes (vital transportation hubs) are located at the city center, implying that most of the bus lines in Dublin city tend to intersect the city’s core.
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.
Communities as neighborhood guardians: A spatio-temporal analysis of community policing in Nairobi's suburbs
(Springer, 2017) Mburu, Lucy W.; Helbich, Marco
The efficacy of citizens to participate in neighborhood-watch activities and report signs of trouble is important for safeguarding communities against crime. Community policing is a key policing strategy for utilizing the capability of residents to solve local crime-related problems. However, variability in social cohesion among communities profoundly affects the contribution of individuals towards policing. After 7 years of a community policing intervention in suburban Nairobi, Kenya, this study assesses the program as a state-initiated and community-sustained security venture. We compare micro-scaled concentrations of different property and violent crimes to identify geographic variations over time using kernel density estimates and spatio-temporal scan statistics. Multi-level regression models assess the direct and conditioned perceptions of individuals and their neighbors, and how these perceptions influenced crime variation during the pre- and post-intervention periods of community policing. Both the density estimates and the scan statistics pinpoint a disproportionate crime reduction across neighborhoods. The research findings also depict an interaction between the communal willingness to participate in neighborhood-watch activities and the relative crime decline. In particular, those communities that have good relations with the police are more inclined to involve themselves in community policing. The findings of this study are discussed in terms of their implications for policy.
Contextual factors and public value of e-government services in kenya
(Global Scientific Journals, 2017) Kamau, Gabriel; Wausi, Agnes; Njihia, James
Abstract E-government research has been skewed towards technological deterministic perspective mainly centering on technological issues. This provides no explicit guidance to the design and practice of e-government programs that result to increased uptake of e-government services. Theoretical discourse reveals undisputed consensus among e-government researchers that e-government uptake may be influenced by others contextual factors such as administrative and political consequences and should not be overlooked as they are valued. This study filled this gap by conducting an empirical investigated of the influence of contextual factors: ICT infrastructure, human capital and governance and the public value of e-government services. The study employed a mixed method exploratory, descriptive cross-sectional approach to realize the research objectives. Structural Equation Modeling was used to conduct statistical analysis of data collected. The study findings demonstrated that ICT infrastructure insignificantly contributed to public value of e-government services. However, the study revealed significantly contribution of human capital as well as governance to public value of e-government services.
Crime risk estimation with a commuter- harmonized ambient population
(Taylor & Francis Group, 2016) Mburu, Lucy W.; Helbich, Marco
Residential population data are frequently employed to link the crime incidence of an area with the number of residents to estimate the underlying risk. Human mobility patterns cause shifts in the baseline population, however, that can potentially influence the crime statistics. This study therefore employed an ambient population that combined residential population data with data depicting the commuting activity in small administrative areas. The effects of the commuter-harmonized ambient population on crime were then evaluated in a series of negative binomial regression models. The models also controlled for criminogenic factors and incorporated eigenvector spatial filtering to adjust for spatial effects. The results show significant effects of commuting patterns on crime outcomes. For certain crimes, such as violence, theft, and disorder, the inbound commuters are significantly associated with high risk. It was further discovered that an offset variable comprising the commuter-harmonized ambient population data models the crime outcomes more reliably than when residential population data are used. Spatial filtering was found to effectively eradicate residual spatial autocorrelation after accounting for effects of the predictor variables. We conclude that calculating crime rates using the residential population does not constitute an accurate risk measure and that the ambient population has crucial implications for realistic and reliable target representation and crime modeling.
Culture aware M-learning classification framework for African countries
(IGI Global, 2014) Mwendia, Simon N.; Wagacha, Peter W.; Oboko, Robert
African countries are currently experiencing proliferation of mobile phone subscriptions but no prevalence of personal computers or electricity (Parker, 2011). It is estimated that, by the end of 2015 in Sub-Saharan Africa, the percentage of people with mobile network access will surpass that of access to electricity in homes (Rao, 2011). This phenomenon is also experienced in learning institutions, particularly universi- ties, where almost every student owns a mobile phone (Kashorda & Waema, 2009). Although there is a great potential for Mobile Learning (M-Learning) in education, the formal integration of M-Learning in the education systems is in its infancy since there is limited number of M-Learning projects in the region. This is in contrast with the rapid increase and integration of mobile phones in the daily lives of the population in the region (Isaacs, 2012). According to Olaniran (2009), online learning needs to be culturally aware and investigate the dimensions of cultural variability as well as its influence on learning within global education. In an attempt to address this need, this chapter focuses on the African region in describing dimensions of cultural variability and proposes four categories for M-Learning projects as well as their influences on dimensions of cultural variability.
Detecting Data Exfiltration Anomalies in Academic Networks Using the Isolation Forest Algorithm
(KCA University, 2025) Arusei, Mike K.; Dr. Njenga, Stephen
Academic 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.
Developing an e-learning theory for interaction and collaboration using grounded theory: a methodological approach
(The Qualitative Report at NSUWorks, 2021) Kibuku, Rachael N.; Ochieng, Daniel O.; Wausi, Agnes N.
Grounded Theory (GT) is becoming an increasingly prevalent research methodology in many fields. Although researchers use it in qualitative and quantitative studies, it is more popular with qualitative studies, as evidenced by the citations from previous research. This paper aims to document and present how we used GT in our qualitative research to construct an e-learning theory for interaction and collaboration. It also includes the justification of GT. We adopted and adapted the constructivist GT (CGT). Therefore, this paper discusses the CGT methodology, its philosophical, ontological and epistemological perspectives. It also includes the research design that captures how we sampled the participants, collected, analyzed and interpreted the data, and how we documented the research findings in the context of CGT. It also includes the justification of the decisions we made and the extent to which they align with CGT. Using CGT, we listened to, observed and captured e-learners’ and e-tutors’ stories and experiences which yielded rich and insightful data that informed the development of the e-learning theory for interaction and collaboration. We also present the challenges we experienced when using CGT and the strategies we used to overcome them. Finally, we have included the methodological insights we drew from using CGT in our research. This paper has presented the CGT design strategy; thus, it will be helpful, especially to novice and future researchers aspiring to use the methodology to conduct their research.
Directing attention through gaze hints improves task solving in human-humanoid interaction
(pubMed, 2018) Mwangi, Eunice; Barakova, Emilia I; Díaz-Boladeras, Marta; Català Mallofré, Andreu; Rauterberg, Matthias
Abstract In this paper, we report an experimental study designed to examine how participants perceive and interpret social hints from gaze exhibited by either a robot or a human tutor when carrying out a matching task. The underlying notion is that knowing where an agent is looking at provides cues that can direct attention to an object of interest during the activity. In this regard, we asked human participants to play a card matching game in the presence of either a human or a robotic tutor under two conditions. In one case, the tutor gave hints to help the participant find the matching cards by gazing toward the correct match, in the other case, the tutor only looked at the participants and did not give them any help. The performance was measured based on the time and the number of tries taken to complete the game. Results show that gaze hints (helping tutor) made the matching task significantly easier (fewer tries) with the robot tutor. Furthermore, we found out that the robots' gaze hints were recognized significantly more often than the human tutor gaze hints, and consequently, the participants performed significantly better with the robot tutor. The reported study provides new findings towards the use of non-verbal gaze hints in human-robot interaction, and lays out new design implications, especially for robot-based educative interventions.
Dynamic heuristics greedy search: a mobile information retrieval algorithm for ambient learning systems
(ACM Digital Library, 2016) Mwendia, Simon N.; Oboko, Robert; Wagacha, Peter Waiganjo
Dynamics of technology transfer for innovation processes in a constrained resource settings :
(Scientific & Academic Publishing Co., 2018) Kiarie, Peter; Mwangi, Henry; Rong, Chunming
Abstract Technology transfer, defined as the movement of scientific inventions from an enterprise to the market place, is often a difficult and frustrating process. Stakeholders in this area of study are usually at different levels of understanding due to many factors involved and speak different languages. There are number of problems associated with technology transfer processes in constrained resource settings such as lack of researchers in specific domains, motivation, bureaucratic climate, inability to make effective public investments, funding and inappropriate infrastructure, culture among many others. This research explores the above problems and others discussed by varies researchers in technology transfer and particularly those in Technology-Organization-Environment (TOE) framework using Data analytics and System Dynamics modeling approaches. Data analytics will facilitate in developing a more promising and data rich System Dynamics model. The study will shed light on technical and social factors that lead to formulation of policies which enable accelerated technology transfers in constrained resource settings.
E-learners’ challenges and coping strategies in interactive and collaborative e-learning in Kenya
(Journal of Education and Training Studies, 2020) Kibuku, Rachael N.; Ochieng, Daniel O.; Wausi, Agnes N
Some universities in Kenya have taken up e-learning to flexibly deliver learning and bridge the educational access gap. Despite the benefits that e-learning offers to the e-learners, there are challenges that they must cope with. The aim of this paper is to present the challenges that emerged from research that was undertaken in two Institutions of Higher Learning (IHLs). It also presents the coping strategies that e-learners used to overcome the challenges. The research used the constructivist version of Grounded Theory (GT) methodology. It used in-depth interviews and participant observations to gather data from the e-learners, e-tutors, e-learning managers and e-learning platforms. Therefore, the research yielded qualitative data which was analyzed using Atlas.ti software. Data was analyzed thematically to establish the patterns of challenges and the equivalent coping strategies. The results are presented using the Gioia technique and the discussion used the vignettes technique from participants in order to preserve their voice. The challenges that emerged relate to: e-content, coursework, internet access, e-learning technology, Information and Communication Technology (ICT) skills and training, interaction and collaboration, personal issues, teaching of Science, Technology, Engineering and Mathematics (STEM) courses and the tutorials. Recommendations on how to tackle these challenges have also been suggested. An understanding of these challenges is important to the e-learning players so that they can adopt interventions to mitigate them and hence improve interaction and collaboration. The results presented in this paper are part of the larger research whose main objective was to develop an e-learning theory for interaction and collaboration.
E-learning challenges faced by universities in Kenya: a literature review
(2020) Kibuku, Rachael N.; Ochieng, Daniel O.; Wausi, Agnes N.
Some institutions of higher education in Kenya have adopted e-Learning with the aim of coping with the increased demand for university education and to widen access to university training and education. Though there are advantages that accrue from adopting e-Learning; its implementation and provision has not been smooth sailing. It has had to contend with certain national, organisational, technical and social challenges that undermine its successful implementation. This paper therefore aims to present a literature review of the challenges faced in the implementation and provision of e-Learning in universities in Kenya. The scoping review method was used to identify and analyze the literature of the e-Learning challenges. Some of the challenges revealed include: lack of adequate e-Learning policies, inadequate Information and Communication Technology (ICT) infrastructure, the ever evolving technologies, lack of technical and pedagogical competencies and training for e-tutors and e-learners, lack of an e-Learning theory to underpin the e-Learning practice, budgetary constraints and sustainability issues, negative perceptions towards e-Learning, quality issues, domination of e-Learning aims by technology and market forces and lack of collaboration among the e-Learning participants. These challenges need to be addressed to minimise their impact on implementation and delivery of e- Learning initiatives in institutions of higher education in Kenya. This analysis of the e-Learning challenges forms the basis for the ongoing research that seeks to explore and establish possible strategies to address some of these challenges.
Efficiency Factors For Linear Contrasts In Confounded Asymmetrical Factorial Designs
(Pushpa Publishing House, 2019) Wanyoike, John N.; Manene, M.; Njui, F.