Department of Computer Science

Permanent URI for this collectionhttp://localhost:4000/handle/20.500.12092/1765

Browse

Filters

20233

Settings

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Identification of Maize leaf diseases based on Support Vector Macina and Convolutional Neural Networks Alex Net and ResNet
    (Karatina University, 2023) Murimi, Micheni Maurice
    Protecting maize crops from devastating plant diseases ensures global food security. Accurate disease identification is essential for implementing effective control measures. However, traditional visual analysis of symptomatic leaves used by maize farmers in Kenya is time consuming, costly, subjective and prone to errors. Embracing computer vision technologies, such as deep learning and machine learning, offers promising solutions to these challenges, enhancing crop productivity. The general objective of this study was to develop models for maize lethal necrosis (MLN) disease, maize streak disease (MSD) and Gray leaf spot diseases (GLS) detection and classification using AlexNet and ResNet 50 convolutional neural networks (CNN) architectures and machine learning Support Vector Machine (SVM). The specific objectives of this study were to: identify maize leaf disease (MLN, MSD and GLS) using AlexNet, ResNet-0 and SVM models, to evaluate the performance of the AlexNet, ResNet-50 and SVM models in the classification of MLN, MSD and GLS. Digital maize leaf disease images were collected from maize farms in Embu County, resulting in a dataset of 3200 images, with 800 images for each disease category. The results indicate that AlexNet and ResNet50 achieved high accuracy in identifying maize leaf diseases, recording average accuracies of 98.3% and 96.6%, respectively. In contrast, the SVM model exhibited the lowest average accuracy of 85.5%. AlexNet demonstrated exceptional accuracy in classifying Maize Streak Virus (MSV) with a rate of 99.85%, followed by ResNet50 at 99.2%. Conversely, SVM had a lower recall value of 81.7% for Grey Leaf Spot disease. By incorporating these advanced models, farmers and stakeholders in maize crop protection can identify diseases early, allowing for timely interventions and improved disease management strategies. Consequently, this will lead to increased maize productivity and enhanced crop quality. Early disease detection also facilitates the judicious use of pesticides, safeguarding the environment and human health. The findings underscore the importance of leveraging these technologies to enhance food security, optimize agricultural practices, and promote sustainable maize production.
  • Thumbnail Image
    Item
  • Thumbnail Image
    Item
    UTILIZATION OF MOBILE DEVICES IN ACCESSING INFORMATION BY LECTURERS AND STUDENTS IN PUBLIC UNIVERSITIES IN KENYA
    (Karatina University, 2023-11) Burudi, Peter Shibonje
    The application of mobile devices is essential in the dissemination of information. In institutions of higher learning, apart from providing convenience, mobile devices open up new avenues for academic libraries to enhance access to information. However, more studies need to be carried out that directly look at the use of mobile devices in enhancing access and use of information. This study aimed at assessing the utilization of mobile devices in libraries in public universities in Kenya. The objectives that guided the study were: to identify various mobile devices available in the libraries; to determine the different ways in which mobile devices are utilized; to examine the benefits of mobile device utilization; to evaluate the challenges faced in the utilization of mobile devices, and to determine viable ways of enhancing utilization of mobile devices in public university libraries in Kenya. The study was guided by the Technology Acceptance Model. The study adopted the descriptive research design. The study targeted 1620 students, 57 teaching staff from three academic departments, 91 library staff, and 38 ICT staff from KU and UoN universities. The study sample size was determined using 10% of the target hence 162 students and six teaching staff were sampled using stratified random sampling while nine library staff and four ICT staff were sampled using purposive sampling. Questionnaires and document analysis were used to collect both primary and secondary data. Descriptive (frequency, percentage, and mean) and inferential statistics (Chi-Square test and Fisher’s test) were used in analyzing data. The Statistical Package for Social Sciences (SPSS, ver. 28) was used for data analysis. The study found that the majority of university students access libraries via mobile devices and that they were mostly used for accessing e-resources, and online searches for educational materials. The study found a strong correlation between the use of mobile devices and ease of access to library resources, exposure to diverse content, convenience of utilization of study materials, and interactive usability of study materials. The study established the shortage of power outlets for charging mobile devices, lack of technical assistance, and inadequate internet access were some of the challenges faced in the utilization of mobile devices in public university libraries. The study concluded that using mobile devices in university libraries benefits users significantly and relieves pressure on more traditional library services. The findings of the study will be useful to policymakers and library managers in improving access to information in libraries.
©Karatina University