Computer Science and ICT

Permanent URI for this collectionhttps://repository.chuka.ac.ke/handle/chuka/430

Browse

Recent Submissions

Now showing 1 - 16 of 16
  • Item
    A Backward Regressed Capsule Neural Network for Plant Leaf Disease Detection
    (Science Publications, 2022) Jepkoech, J.; Kenduiywo, B. K.; Mugo, D. M.; Too, E. C.
    This study investigated the introduction of backward regression coupled with DenseNet features in a Capsule Neural Network (CapsNet) for plant leaf disease classification. Plant diseases are considered one of the main factors influencing food production and therefore fast crop disease detection and recognition are important in enhancing food security interventions. CapsNets have successfully been adopted for plant leaf disease classification however, backpropagation of signals to preceding layers is still a challenge due to low gradient flow. In addition, parameter and computational complexities exist due to complex features. Therefore, this study implemented a loop connectivity pattern to improve gradient flow in the convolution layer and backward regression for feature selection. We observed a 99.7% F1 score with backward regression and 87% F1 score without backward regression accuracy on testing our framework based on the standard Plant Village (PV) dataset comprising ten tomato classes with 9080 images. Additionally, CapsNet with backward regression showed relatively higher and stable accuracy when sensitivity analysis was performed by varying testing and training dataset percentages. In comparison Support Vector Machines (SVM), Artificial Neural Networks (ANN), AlexNet, ResNet, VGGNet, Inception V3, and VGG 16 deep learning approaches scored 84.5, 88.6, 99.3, 97.87, 99.14, and 98.2%, respectively. These findings indicate that the introduction of backward regression of features in the CapsNet model may be a decent and, in most cases superior and less expensive alternative for phrase categorization models based on CNNs and RNNs. Therefore, the accuracy of plant disease detection may be enhanced even further with the aid of the fusion of several classifiers and the integration of a backward regressed capsule neural network.
  • Item
    Time-Series Prediction of Gamma-Ray Counts Using XGB Algorithm
    (Open Journal for Information Technology, 2022) Mutuku, V.; Mwema, J.; Joseph, M.
    Radioactivity is spontaneous and thus not easy to predict when it will occur. The average number of decay events in a given interval can lead to accurate projection of the activity of a sample. The possibility of predicting the number of events that will occur in a given time using machine learning has been investigated. The prediction performance of the Extreme gradient boosted (XGB) regression algorithm was tested on gamma-ray counts for K-40, Pb-212 and Pb-214 photo peaks. The accuracy of the prediction over a six-minute duration was observed to improve at higher peak energies. The best performance was obtained at 1460keV photopeak energy of K-40 while the least is at 239keV peak energy of Pb-212. This could be attributed to higher number of data points at higher peak energies which are broad for NaITi detector hence the model had more features to learn from. High R-squared values in the order of 0.99 and 0.97 for K-40 and Pb-212 peaks respectively suggest model overfitting which is attributed to the small number of detector channels. Although radioactive events are spontaneous in nature and not easy to predict when they will occur, it has been established that the average number of counts during a given period of time can be modelled using the XGB algorithm. A similar study with a NaITi gamma detector of high channel numbers and modelling with other machine learning algorithms would be important to compare the findings of the current study.
  • Item
    Metrics for Evaluating Alerts in Intrusion Detection Systems
    (international journal of network security and its application, 2023-01-04) Jane Kinanu Kiruki1, 3 , Geoffrey Muchiri Muketha2 and Gabriel Kamau1
    Network intrusions compromise the network’s confidentiality, integrity and availability of resources. Intrusion detection systems (IDSs) have been implemented to prevent the problem. Although IDS technologies are promising, their ability of detecting true alerts is far from being perfect. One problem is that of producing large numbers of false alerts, which are termed as malicious by the IDS. In this paper we propose a set of metrics for evaluating the IDS alerts. The metrics will identify false, low-level and redundant alerts by mapping alerts on a vulnerability database and calculating their impact. The metrics are calculated using a metric tool that we developed. We validated the metrics using Weyuker’s properties and Kaner’s framework. The metrics can be considered as mathematically valid since they satisfied seven of the nine Weyuker’s properties. In addition, they c
  • Item
    Metrics for Evaluating Alerts in Intrusion Detection Systems
    (international journal of network security and its appplication, 2023-01-05) Jane Kinanu Kiruki1, 3, Geoffrey Muchiri Muketha2 and Gabriel Kamau1
    Network intrusions compromise the network’s confidentiality, integrity and availability of resources. Intrusion detection systems (IDSs) have been implemented to prevent the problem. Although IDS technologies are promising, their ability of detecting true alerts is far from being perfect. One problem is that of producing large numbers of false alerts, which are termed as malicious by the IDS. In this paper we propose a set of metrics for evaluating the IDS alerts. The metrics will identify false, low-level and redundant alerts by mapping alerts on a vulnerability database and calculating their impact. The metrics are calculated using a metric tool that we developed. We validated the metrics using Weyuker’s properties and Kaner’s framework. The metrics can be considered as mathematically valid since they satisfied seven of the nine Weyuker’s properties. In addition, they can be considered as workable since they satisfied all the evaluation questions from Kaner’s framework
  • Item
    Gerontechnology: remote patient monitoring
    (International Journal of Scientific and Education Research, 2018) Ndung’u, I.; Murerwa, E.G
    Gerontechnology is coined from two words; Gerontology which means the study of old age as well as Technology. Research in the field aims at identifying the needs of the people in their old age as well as encouraging and promoting technological innovations in products and services that address older peoples’ needs; in order to enhance personal independence, maintain health, prevent diseases and enhance leisure. Improvement in diet, health care as well as environment factors has seen an increase in the life expectancy of people. But as people become older challenges among them frail health arises. Traditionally families lived together such that it was expected as one grows old there will be his/her children who will take care of them. But in recent times there has been an upsurge in rural urban migration where the young move to urban areas in search of employment leaving their old parents behind. These are people who may not know when to take prescribed medications or monitor other vital signals. Left on their own health deteriorates very fast and at times results with preventable death. The importance for gerontechnology is increasing because of the high ageing population. This paper attempts to awareness on technological responses to monitoring health of old people. The use of remote monitoring tools to address health issues of the aged is considered.
  • Item
    Effect of poor software development practices on computer software security
    (Chuka university, 2018-10) Murerwa,Emily Gakii
    We are in what is known as the digital age. Almost every aspect of life is in one way or another affected by computers. There has been seen an increase in the availability of computer hardwareand software. Computer hardware has become rampant withdevices such as mobile phones, tablets and laptopsmaking it possible forpeopleto easilycarryand movewiththecomputingdevicewhich has in essence contributed to computer usage. We use computer software otherwise known as computer systems for communication, for online shopping and purchasing, for businesstransactions, for remote medical services, for government services and for education purposes among many other uses. It is right to say that computers have revolutionized the way we live. Computer systems are obtained through a process known as programming. Computer programmers also known as developers work either as individuals, as members of a team or in employment by a software development company. But as computer usage increases so has a type of criminals known as cybercriminals perpetrating what are knownas cybercrimes. Cybercrimes are intended to disrupt computer usage and cause damage to individuals, organizations and even governments. Software creators need to be keenso thattheycandevelop softwarethat is secure and which makes it hard to manipulate by criminals. This research considers some of the practices ignored or in some cases taken lightly by software developers which in return lead to less secure software. The research also recommends what software developers need to do in order to secure software.
  • Item
    Information technology innovation and its impact on job creation by SMEs in developing countries: an analysis of the literature review
    (taylor and Francis, 2019-08-06) Chege, Samwel Macharia; Wang, Daoping
    This study reviews the literature on the role of technology innovation in job creation through small businesses in developing countries. A sevenstep approach to the literature review is used for synthesising relevant data. The results show that technology innovations influence employment creation in small businesses positively and act as a driving force for economic development. The effective use of information technology in small businesses has a major impact on their competitiveness and access to international markets. Thus, the need for the government to develop technology innovative strategies for small businesses to actualise their firm performance and enhance job creation is recommended. The findings and proposed theoretical model of the study enrich existing theories and would help policymakers understand the role of information technology innovation in job creation and economic development.
  • Item
    The Effect of Adaptive Learning Rate on the Accuracy of Neural Networks
    ((IJACSA) International Journal of Advanced Computer Science and Applications, 2021) Jepkoech, Jennifer; Mugo, David Muchangi; Kenduiywo, Benson K.; Too, Edna Chebet
    Learning rates in gradient descent algorithms have significant effects especially on the accuracy of a Capsule Neural Network (CNN). Choosing an appropriate learning rate is still an issue to date. Many developers still have a problem in selecting a learning rate for CNN leading to low accuracies in classification. This gap motivated this study to assess the effect of learning rate on the accuracy of a developed (CNN). There are no predefined learning rates in CNN and therefore it is hard for researchers to know what learning rate will give good results. This work, therefore, focused on assessing the effect of learning rate on the accuracy of a CNN by using different learning rates and observing the best performance. The contribution of this work is to give an appropriate learning rate for CNNs to improve accuracy during classification. This work has assessed the effect of different learning rates and came up with the most appropriate learning rate for CNN plant leaf disease classification. Part of the images used in this work was from the PlantVillage dataset while others were from the Nepal database. The images were pre-processed then subjected to the original CNN model for classification. When the learning rate was 0.0001, the best performance was 99.4% on testing and 100% on training. When the learning rate was 0.00001, the highest performance was 97% on testing and 99.9% on training. The lowest performance observed was 81% accuracy on testing and 99% on training when the learning rate was 0.001. This work observed that CNN was able to achieve the highest accuracy with a learning rate of 0.0001. The best Convolutional Neural Network accuracy observed was 98% on testing and 100% on training when the learning rate was 0.0001.
  • Item
    Maximizing the Value of Information Communication Technologies (ICTs) and Its Implications on Library Operations in Public Universities in Kenya: Potential and Challenges
    (Centre for Democracy, Research and Development (CEDRED), Nairobi, Kenya., 2022) Guto, R.; Wasike, J.
    The advent of information age has significantly changed the environment in which libraries operate in the 21st century. Technological encroachment has forced librarians to adopt various technologies for their continued existence in line with the constant changing information seeking behaviors of varied readers and development in education and research. The purpose of this paper was to examine the value of information communication technologies (ICTs) and its implications on library operations in public universities in Kenya: Potential and Challenges. The objectives of the research were to: Establish the efficiency of emerging ICTs in public university libraries in Kenya, determine the application of ICT on performance of duties in public university libraries and evaluate the effects of ICTs on access and retrieval of information. The study employed survey research design in collecting data from 31 public universities in Kenya. The respondents were university librarians. The data was collected by use of questionnaires which was later analyzed with the aid of SPSS software (version 22). The findings of the study showed that the application and usage of information communication technologies (ICTs) had significant impacts on library service provision such as circulation, E-books, internet services, OPAC and increased work output. The study recommendation indicated that there is need for adoption of a comprehensive ICT policy to create an enabling framework for the application and development of ICTs in libraries and, train both staff and information users on how best to apply ICTs features in accessing, and retrieving information materials. The study, if adopted will enhance information provision and service delivery in university libraries.
  • Item
    WLAN SECURITY: A TRUSTED COMPUTING BASE APPROACH
    (2019-01) Mwathi, David Gitonga
    This paper identifies the gaps in IEEE 802.11 standards and supporting technologies and then proposes a conceptual architecture that can be used to develop a model for analyzing and predicting the security performance of selected WLAN security features and configurations.
  • Item
    User’s perception on ICT adoption in High schools
    (2012) Nchunge, David Mbabu; Sakwa, M.; Mwangi, W.
    Information Communication Technology (ICT) plays a crucial role in the effectiveness, efficiency and service delivery of any institution. ICT has also been credited with the potential to integrate world economies thus demolishing the barriers created by time and distance. However, despite its role in improving service delivery, it adoption in secondary schools in Kenya has remained low and limited. The study adopted a descriptive research design approach and targeted all the public and private secondary schools in Thika district in Kenya. The findings shows that the pace of ICT adoption in both public and private secondary schools in Kenya is very slow, as characterized by: user complexity perception, inadequate IT literacy, lack of psychological and technical readiness and insufficient policy guidelines. The paper concludes that inadequate technical and psychological preparedness has belated perception change which has hampered technology acceptance and use in secondary schools. This study recommends that; Psychological and technical skill readiness of teachers needs to be addressed through increasing investment in ICT facilities, resources and training so as to reverse the slow rate of ICT adoption trend and improve the pace of diffusion in secondary schools.
  • Item
    Assessment of ICT Infrastructure on ICT Adoption in Educational Institutions
    (2013-06) Nchunge, David Mbabu; Sakwa, M.; Mwangi, W.
    Globalization and liberalization have facilitated intensive business competition which in turn has increased the need for adoption of new technologies to increase the efficiency in service delivery. ICT has wide application in public services: in administration, in the educational system, in the health care sector, and in transportation. This study however focused on education sector specifically in secondary schools in Kiambu county in Kenya. Despite ICT efficiency, potential and seamless role in improving productivity and knowledge transfer in social, economic and political pillars of development, it’s adoption in High schools in Kenya has remained low and limited. The study adopted a descriptive research design approach and targeted all the public and private High schools in Thika district in Kiambu county in Kenya. The findings shows a positive association between the pace of ICT adoption and high infrastructure costs, pace of ICT adoption and inadequate internet connectivity, pace of ICT adoption and absence of clear policy guidelines in public and private High schools in Thika District leading to low ICT usage causing delay of actual technology integration in schools. This study suggests and recommends that; Basic infrastructure acquisition and support guidelines be availed to schools. Equally the School ICT infrastructure be tax waived or zero rated to address costs of ICT facilities and connectivity to enhance the ICT adoption and improve quality of services and knowledge dissemination through ICT diffusion in High schools and athwart the entire education sector.
  • Item
    A Multi-Faceted Approach to Mobile Agent Security
    (2015-06) Ngereki, Anthony M.; Kahonge, Andrew M.
    Mobile agents are increasingly becoming popular in the development of current distributed applications. However, the mobility and autonomy factors of mobile agents present a host of security challenges in a distributed environment. In an attempt to ensure security of the mobile agent against a malicious host, a security framework is proposed. Our security mechanism uses a multi-faceted approach to protect mobile agents and must be incorporated from the design stage of agent systems. We identify major security threats against mobile agents by a malicious platform and propose algorithms to counter them. We then test a multi-agent system that incorporates these algorithms against one that doesn’t and compare the results.
  • Item
    Adoption of Near Field Communication in Universities in Kenya
    (2015-09) Muthengi, Fredrick Mugambi; Njebiu, Victor Mwenda
    In our day to day life, the adoption of new technology to new innovation in various sectors is rising. Campus life has shifted from students’ carrying laptops and a bag full of pass cards to carrying Ipads or smart phones. Barcode bars on pass and identification cards have been replaced by near field communication (NFC) instructions. NFC is a technology standard for very-short-range wireless connectivity that enables quick, secure two-way interactions among electronic devices. The level of global interaction and mode of communication is changing and the adoption of Near Flied Communication is on the rise, replacing bar code and QR code. The technology is at advanced stages ranging from file transfer; access controls to paying for goods and services on NFC enabled payment points/devices or cards. The introduction of Near Field Communication in the universities has enhanced the speed of processes as well as simplifying them. The pass cards/ids students carry along and time spent on queues waiting to be served is reduced. This paper explores the advantages of near field communication over magnetic bar codes and QR codes in an academic institution. Near field communication combines several instructions which are read via NFC enabled devices: smart phones or tags. Student card is customized with NFC tag: from library card, access control card to student identification card. NFC is at early stages of implementation in Kenya but has been successfully rolled out in transport industry as Bebapay. With the rise of mobile enabled near field communication devices, its adoption in Kenyan universities will be a success.
  • Item
    School ICT Policy, a Factor Influencing Implementation of Computer Studies Curriculum in Secondary Schools.
    (2013) Murithi, Nathan 1*
    The introduction of ICT curriculum in education among schools in many countries was as a result of National ICT policy initiatives by the government. The National ICT curriculum differs from regions depending on the education system practiced in a country. In this particular study, ICT policy initiatives towards effective implementation of Computer Studies Curriculum which is offered under the 8.4.4 system of education in Kenyan secondary schools was studied. The study focused on School ICT policy towards implementation of Computer Studies Curriculum in secondary schools. Report on investigation and discussion of availability of a School ICT policy and the implementation of Computer Studies curriculum was therefore made in this paper. Questionnaire for Computer studies teachers and students as well as interview schedule for school principal were used as method of data collection including document analysis guide. Quantitative and qualitative data was analyzed by use of descriptive statistics. The findings revealed that availability of a School ICT policy encouraged implementation of Computer Studies Curriculum. The results of this study suggest that schools which had an ICT policy were able to fully implement Computer Studies curriculum.
  • Item
    Algorithm for Selection of EAP Authentic
    (2016-06) Mwathi, David Gitonga 1; Okello-Odongo, William 2 ,; Opiyo, Elisha 3
    ABSTRACT Several recent studies indicate that many implementations of authentication and access control in public WLANs are compromisable. This is because IEEE 802.11 standard leaves the choice of EAP method to use to the discretion of WLAN system implementers due to the fact that IEEE 802.11 standard cannot and does not define the upper layer authentication. Therefore, this paper presents IEEE 802.11 implementation specific issues that may contribute to poor security performance of WLAN authentication and access control implementation. It also analyses various EAP methods and presents an algorithm for selection of an Extensible authentication protocol (EAP) method for a Public WLAN.