Dr. Myeongsu Kang (Ph.D., University of Ulsan, 2015) is a Research Scientist of the CALCE Prognostics and Health Management (PHM) Group at the University of Maryland, College Park, MD, USA. His research interests include data-driven anomaly detection, diagnostics, and prognostics of
complex systems, such as automotive, railway transportation, and avionics, for which failure would be catastrophic. He has expertise in data analytics, machine learning (deep learning), system modeling, and statistics for PHM.



Recent Publications

Deep Residual Networks With Dynamically Weighted Wavelet Coefficients for Fault Diagnosis of Planetary Gearboxes, Minghang Zhao, Baoping Tang , Myeongsu Kang, Michael Pecht, IEEE Transactions on Industrial Electronics, Volume: 65, Issue: 5, May 2018, DOI: 10.1109/TIE.2017.2762639.

Detection of Generalized-Roughness and Single-Point Bearing Faults Using Linear Prediction-Based Current Noise Cancellation, Fardin Dalvand, Myeongsu Kang, Satar Dalvand, and Michael Pecht IEEE Transactions on Industrial Electronics , 2018.

A Comparative Study on Anomaly Detection of the Combustion System in Gas Turbine, Jiao Liu, Myeongsu Kang, Jinfu Liu, Zhongqi Wang, Daren Yu,and Michael G. Pecht Proceedings of the Society for Machinery Failure Prevention Technology Conference, May 15-18, 2017, Virginia Beach, VA.

Current Noise Cancellation for Bearing Fault Diagnosis Using Time Shifting, Fardin Dalvand, Satar Dalvand, Fatemeh Sharafi, and Michael Pecht, IEEE Transactions on Industrial Electronics, Vol. 64, No. 10, October 2017.

A Massively Parallel Approach to Real-Time Bearing Fault Detection Using Sub-Band Analysis on an FPGA-Based Multicore System, Myeongsu Kang, Jaeyoung Kim, In-Kyu Jeong, Jong-Myon Kim and Michael Pecht, IEEE Transactions on Industrial Electronics, Vol. 63, no.10, pp 6325-6335, October 2016, doi:10.1109/TIE.2016.2574986.

A fusion prognostics-based qualification test methodology for microelectronic products, Michael Pecht, Tadahiro Shibutani, Myeongsu Kang, Melinda Hodkiewicz, and Edward Cripps, Microelectronics Reliability, Vol. 63, pp 320-324, August 2016, DOI:10.1016/j.microrel.2016.04.002.

A Sequential k-Nearest Neighbor Classification Approach for Data-Driven Fault Diagnosis Using Distance- and Density-Based Affinity Measures, Myeongsu Kang, Gopala Krishnan Ramaswami, Melinda Hodkiewicz, Edward Cripps, Jong-Myon Kim and Michael Pecht, Springer International Publishing Switzerland, Vol. 9714, pp 253-261, June 2016.

A Hybrid Feature Selection Scheme for Reducing Diagnostic Performance Deterioration Caused by Outliers in Data-Driven Diagnostics , Myeongsu Kang, Md. Rashedul Islam, Jaeyong Kim, Jong-Myon Kim, and Michael Pecht, IEEE Transactions on Industrial Electronics, Vol. 63, No. 5, May 2016 .