Zezhong Li

Zezhong Li

D.Eng. Candidate @ Tianjin University / AI 4 Time Series / Anomaly Detection / Time Series Segmentation

Zezhong Li (李泽中) @ Tianjin University

I am a second-year D.Eng. candidate in the Institute of Artificial intelligence and Network Science at Tianjin University (TJU), advised by Dr. Zhongke Gao. Before that, I received my Master of Engineering degree in Electronic Information from the University of Science and Technology Beijing (USTB), advised by Dr. Ling Wang, and my Bachelor of Engineering degree in Automation from Nanjing Tech University, advised by Dr. Mouquan Shen.

Education

2023 - present: ——— D.Eng. candidate at AINS Lab, Tianjin University.

2020 - 2023: ——— M.E., Electronic Information, University of Science and Technology Beijing.

2016 - 2020: ——— B.S., Automation, Nanjing Tech University.

Research Focus

  • AI for time series.
    • Deep learning based unsupervised anomaly detection for multivariate time series.
    • Multivariate time series unsupervised segmentation (a.k.a. change point detection).
  • Autonomous marine systems (focusing on underwater gliders).

Selected Publications

The full publication list is available here

*= Equal contribution

  • [IEEE Sens J ‘25] Zezhong Li, Wei Guo, Jianpeng An, Qi Wang, Yingchun Mei, Rongshun Juan, Tianshu Wang, Yang Li, and Zhongke Gao, “AD2T: Multivariate Time Series Anomaly Detection with Association Discrepancy Dual-Decoder Transformer,” IEEE Sensors Journal (IEEE Sens J), 2025. [Collaborated with Huadian Heavy industries Co. Ltd], (link)

  • [KBS ‘24] Zezhong Li, and Ling Wang, “Adaptive Joint Segmentation for Multivariate Spatio-Temporal Data,” Knowledge-Based Systems (KBS), Under Review.

  • [TNNLS ‘24] Ling Wang*, Zezhong Li*, and Gang Wang, “Multivariate Spatio-Temporal Data Clustering With Shapelet Learning and Spatial Toeplitz Inverse Covariance Structure,” IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Revise.

  • [Kzyjc ‘24] Ling Wang, and Zezhong Li, “Adaptive greedy Gaussian segmentation algorithm based on multivariate time series”, Kongzhi yu Juece/Control and Decision (Kzyjc), 2024. (link)

  • [CJE ‘23] Ling Wang, and Zezhong Li, “Adaptive Segmentation of Multivariate Time Series with FastICA and G-G Clustering”, Tien Tzu Hsueh Pao/Acta Electronica Sinica (CJE), 2023. (link)

Work Experience

Professional Service