Biography
Dr. Kabir received the Ph.D in Computer Science from the City University of Hong Kong under Dr. Jacky Keung. He was a faculty member in the Department of Software Engineering at Daffodil International University prior to joining AIUB. Currently, he is a postdoctoral research fellow in Artificial Intelligence and Intelligent Systems research group at Mälardalen University, Sweden.
He is an active software engineering researcher, and his research lies at the intersection of empirical software engineering and AI. Recently, he has been trying to employ the knowledge of data stream mining, statistical modeling, and empirical investigation to produce more reliable defect prediction models. His research work has been published in prestigious journals, including Information and Software Technology, Applied Soft Computing, and other leading conferences. His Ph.D research publications have been supported by software companies and Hong Kong Government research funds.
He has received a prestigious postgraduate studentship for his Ph.D studies at the City University of Hong Kong from 2018 to 2021.
Research Interests/ Areas:
Trustworthiness of Deep Learning Models
Empirical Software Engineering
Software Analytics
Dr. Kabir's mission is to help the community towards engineering high-quality and secure software systems for social good. If you share the same value, please reach out for collaborations. For updates, please check - https://makabir4.github.io/
Selected Publications:
1. Kabir, M. A., Keung, J., Turhan, B., & Bennin, K. E. (2021). Inter-release defect prediction with feature selection using temporal chunk-based learning: An empirical study. Applied Soft Computing, 113, 107870. (Q1; Impact Factor: 8.263)
2. Yang, Z., Keung, J., Kabir, M. A., Yu, X., Tang, Y., Zhang, M., & Feng, S. (2021). AComNN: Attention enhanced Compound Neural Network for financial time-series forecasting with cross-regional features. (Q1; Impact Factor: 8.263)
3. Kabir, M. A., Keung, J. W., Bennin, K. E., & Zhang, M. (2020, July). A drift propensity detection technique to improve the performance for cross-version software defect prediction. In 2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC) (pp. 882-891). IEEE. (Core Rank: B)
4. Kabir, M. A., Keung, J. W., Bennin, K. E., & Zhang, M. (2019, July). Assessing the significant impact of concept drift in software defect prediction. In 2019 IEEE 43rd Annual Computer Software and Applications Conference (COMPSAC) (Vol. 1, pp. 53-58). IEEE. (Core Rank: B)