Department of Computer Science

Permanent URI for this collectionhttp://localhost:4000/handle/20.500.12092/1648

Browse

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Students Selection for University Course Admission at the Joint Admissions Board (Kenya) Using Trained Neural Networks
    (2011) Wabwoba, Franklin; Mwakondo, Fullgence M.
    Every year, the Joint Admission Board (JAB) is tasked to determine those students who are expected to join various Kenyan public universities under the government sponsorship scheme. This exercise is usually extensive because of the large number of qualified students compared to the very limited number of slots at various institutions and the shortage of funding from the government. Further, this is made complex by the fact that the selections are done against a predefined cluster subjects vis a vis the student’s preferred and applied for academic courses. Minimum requirements exist for each course and only students having the prescribed grades in specific subjects are eligible to join that course. Due to this, students are often admitted to courses they consider irrelevant to their career prospects and not their preferred choices. This process is tiresome, costly, and prone to bias, errors, or favour, leading to disadvantaging innocent students. This paper examines the potential use of artificial neural networks at the JAB for the process of selecting students for university courses. Based on the fact that Artificial Neural Networks (ANNs) have been tested and used in classification, the paper explains how a trained neural network can be used to perform the students’ placement effectively and efficiently. JAB will be able, therefore, to undertake the students’ placement thoroughly and be able to accomplish it with minimal wastage of time and resources respectively without having to utilise unnecessary effort. The paper outlines how the various metrics can be coded and used as input to the ANNs. Ultimately, the paper underscores the various merits that would accompany the adoption of this technique. By making use of neural networks in the university career choices, student placement at JAB will enhance the chances of students being placed into courses they prefer as part of their career choice. This is likely to motivate the students, making them work harder and leading to improved performance and improved completion rate. The ANN application may also reduce the cost spend on the application processing and the time the applicants have to wait for the outcome. The ANN application could further increase the chances of high quality applicants getting admis sion to career courses for which they qualify.
  • Thumbnail Image
    Item
    Deep Transfer Learning Optimization Techniques for Medical Image Classification: A Review
    (2022) Kariuki, Paul Wahome; Gikunda, Patrick Kinyua; Wandeto, John Mwangi
    Medical image classification is a complex and challenging task due to the heterogeneous nature of medical data. Deep transfer learning has emerged as a promising technique for medical image classification, allowing the leveraging of knowledge from pre-trained models learned from large-scale datasets, resulting in improved performance with minimal training and overcoming the disadvantage of small data sets. This paper concisely overviews cutting-edge deep transfer learning optimization approaches for medical image classification. The study covers convolutional neural networks and transfer learning techniques, including relation-based, feature-based, parameter-based, and instance-based transfer learning. Classical classifiers such as Resnet, VGG, Alexnet, Googlenet, and Inception are examined, and their performance on medical image classification tasks is compared. The paper also discusses optimization techniques, such as batch normalization, regularization, and weight initialization, as well as data augmentation and kernel mathematical formulations. The study concludes by identifying challenges when using deep transfer learning for medical image classification and proposing potential future approaches for this field.
  • Thumbnail Image
    Item
    Factors Inhibiting the Implementation of Digital Villages in Kenya
    (2017) Karume, Simon; Shisoka, Dorcus Arshley
    The achievement of an information-based society is one of the main priorities of the Government of Kenya (GoK) towards the realization of national development goals and objectives for wealth and employment creation. However, even in their efforts the ICT sector is still currently more active in urban areas, resulting in wide regional disparities in the distribution of ICT facilities. In order to address this disparity, the Kenya ICT Board (KICTB) supported the roll out of new “electronic centre’s” which were named Pasha Centre’s (and are also commonly referred to as Digital Villages).The Digital village’s initiatives in Kenya commenced with a lot of optimism in 2009 however five years down the line it cannot be recorded that they have been successful. The purpose of this study was to establish the factors that have hindered the successful implementation of digital villages in Kenya. For this study desk research methodology was adopted. The secondary data from published reports was discussed with emphasis on the area of interest to this study. The findings of this study indicated that there were various factors that hindered the successful implementation of digital villages in Kenya. The study recommended need for having a government policy for the digital village project. This policy if developed will serve to protect such projects in future enabling them to take off and function independently.
©Karatina University