People › Dr. Shuo Feng
Shuo Feng

Dr. Shuo Feng

馮朔 PhD Graduate (2021) Ph.D (CityU, HK)
教員鄭州大學FacultySchool of Information EngineeringZhengzhou University, Zhengzhou, China
Personal website ↗ORCID ↗

About

Dr. Shuo Feng is a PhD graduate in the Department of Computer Science, City University of Hong Kong.

Shuo Feng received his PhD from the Department of Computer Science at City University of Hong Kong and is now a Faculty member in the School of Information Engineering at Zhengzhou University. His research addresses the class imbalance problem in software defect prediction and empirical software engineering. He introduced COSTE, a complexity based oversampling technique that generates synthetic defective instances from pairs of similar complexity, achieving low false alarm and high detection simultaneously across 23 releases of 10 projects. He then investigated the impact of the distance metric and measure on SMOTE based techniques. He also showed that SMOTE based oversampling is highly unstable, with performance differences up to 204.2% in MCC, and proposed stable variants as drop in replacements. His work helps practitioners build defect prediction models that balance detection accuracy with realistic inspection effort.

Research Interests

Publications (10)