QIN Chengjin

Qin C. is a researcher at the School of Mechanical Engineering, Shanghai University of Electric Power, with a strong focus on signal processing, machine learning, and their applications in mechanical and biomedical engineering. His research spans a wide range of topics, including vibration control, fault diagnosis, signal decomposition, and health monitoring of mechanical systems, as well as the application of deep learning in medical signal analysis and disease diagnosis. Qin has made significant contributions to the development of advanced signal processing techniques, such as time-frequency analysis, chirplet transform, and adaptive decomposition methods, which have been widely applied in the fields of robotics, machining, and biomedical engineering. His work has been published in numerous high-impact journals, including *Mechanical Systems and Signal Processing*, *IEEE Transactions on Instrumentation and Measurement*, *Applied Sciences*, and *iScience*, among others. Qin's research has been recognized for its innovation and practical significance, with several papers being selected as ESI highly cited or hot papers. He is also actively involved in the development of intelligent systems and has contributed to the advancement of domain adaptation, transfer learning, and neural network-based methods for fault diagnosis and remaining useful life prediction. His work continues to push the boundaries of signal processing and machine learning in both academic and industrial applications.

Chengjin Qin is a researcher in the School of Mechanical Engineering at Shanghai Jiao Tong University, specializing in PHM, deep learning, signal processing, and dynamics. Their work focuses on applying deep learning techniques to mechanical systems for fault diagnosis, torque prediction, and signal processing. Qin's research includes developing hybrid neural networks for precise cutterhead torque prediction in shield tunneling machines, as well as using transfer learning and attention mechanisms for motor fault diagnosis. They also explore ECG heartbeat classification and arrhythmia detection using deep neural networks. Their contributions emphasize real-time monitoring, noise reduction, and adaptive signal processing in complex mechanical and biomedical systems.