Kula Kakeba Tune

Work place: Department of Software Engineering, CoE for HPC and BDA, AASTU, Addis Ababa, Ethiopia

E-mail: kula.kakeba@aastu.edu.et

Website:

Research Interests:

Biography

Kula Kekeba Tune, Ph.D., he is an Assistant Professor and Senior Instructor at the Department of Software Engineering, Addis Ababa Science and Technology University (AASTU), Ethiopia. He has been also serving as a Senior Researcher and Head of the HPC and Big Data Analytics Centre of Excellence at AASTU. Dr. Kula had specialized in Computer Science and Engineering and earned his Ph.D. in CSE from the International Institute of Information Technology (IIIT- Hyderabad, India) in 2015. He earned his BSc and MSc in Information Science from Addis Ababa University (AAU), where had served in various academic and administrative positions including Head of the Department of Information Science. He has also served on various University and College level committees including Department Graduate Committee (DGC), Curriculum Development and Review Taskforces, Research and Technology Transfer Committee (RTTC), and Local Articles Reputability Assessment Committee. Dr. Kula has taught and supervised many MSc and Ph.D. courses and research projects related application of AI, NLP, Information Retrieval, Business Intelligence, and Data Analytics. He has published several research papers in academic journals and professional conference proceedings. He is the author or co-author of more than 12 research papers in international refereed journals and conference contributions. Most of his research works have been focused on the development of multilingual information access technologies for indigenous Ethiopian Languages.

Author Articles
Transfer Learning based Breast Cancer Classification via Deep Convolutional Neural Network

By Markos Wondim Walle Kula Kakeba Tune Natnael Tilahun Sinshaw Sudhir Kumar Mohapatra

DOI: https://doi.org/10.5815/ijem.2023.04.04, Pub. Date: 8 Aug. 2023

Breast cancer is a leading cause of death among women, and the subjectivity of human visual perception and lack of automated detection methods can lead to misclassification of breast cancer images. In this study, a breast cancer classification model using a Convolutional Neural Network (CNN) deep learning algorithm was proposed. The model demonstrated high accuracy in classifying breast images as benign or malignant, with a classification accuracy of 97.1%. The model was also able to run on low computational resources. The study used a dataset of 2009 breast images labeled by two radiologists and included six scenarios based on different hyperparameters, augmentation values, pretrained models, and models built from scratch. While the performance of the proposed model was promising, further improvement may be achieved by using a larger breast image dataset and a machine with more powerful GPU hardware.

[...] Read more.
Other Articles