School of Electronics and Information Engineering, Harbin Institute of Technology, Harbin 150001, China
Summary
Gongjian Zhou was born in China, in 1979. He received the B.E., M.E., and Ph.D. degrees in information and communication engineering from Harbin Institute of Technology, Harbin, China, in 2000, 2002, and 2008, respectively. From February 2009 to March 2011, he held a Postdoctoral Fellowship at the Department of Aerospace Engineering, Harbin Institute of Technology. From April 2011 to May 2012, he was a Visiting Professor with the Department of Electrical and Computer Engineering, McMaster University, Hamilton, ON, Canada. He is currently a Professor with the Department of Electronic Engineering, Harbin Institute of Technology. He is also a Longjiang Young Scholar. His research interests include estimation, tracking, detection, information fusion, and signal processing.
To address the performance degradation of traditional data association algorithms caused by unknown target motion models, environmental interference, and strong maneuvering behaviors in complex dynamic scenarios, this paper proposes an innovative fusion algorithm that integrates reinforcement learning and deep learning. By constructing a policy network that combines Long Short-Term Memory (LSTM) memory units and reinforcement learning dynamic decision-making, a dynamic prediction model for "measurement-target" association probability is established. Additionally, a hybrid predictor incorporating Bayesian networks and multi-order curve fitting is designed to formulate the reward function. To... More >
Graphical Abstract
Free Access
|
Research Article
| 30 September 2024
| Cited: 2
In the realm of industrial defect detection, unsupervised anomaly detection methods draw considerable attention as a result of their exceptional accomplishments. Among these, knowledge distillation-based methods have emerged as a prominent research focus, favored for their streamlined architecture, precision, and efficiency. However, the challenge of characterizing the variability in anomaly samples hinders the accuracy of detection. To address this issue, our research presents a novel approach for anomaly detection and localization, leveraging the concept of inverse knowledge distillation as its cornerstone. We employ the encoder as the guiding teacher model and designate the decoder as the... More >
Graphical Abstract
We use cookies
Our website uses cookies that are essential for its operation and additional cookies to track performance, or to improve and personalize our services. By clicking "Allow all cookies", you agree to the storing of cookies on your device. For more information on how we use cookies, please see our Cookie Policy.
