Linshan Jia
Xi'an Jiaotong University
5 Papers
Linshan Jia is an academic researcher from Xi'an Jiaotong University. The author has contributed to research in topics: Pattern recognition (psychology) & Computer science. The author has an hindex of 1, co-authored 1 publications.
Chat about Author
Papers
GTFE-Net: A Gramian Time Frequency Enhancement CNN for bearing fault diagnosis
TL;DR: In this article , the authors proposed a simple but efficient Gramian-based noise reduction strategy called Gramian Noise Reduction (GNR) based on the periodic self-similarity of vibrational signals.
76
Multiscale Residual Attention Convolutional Neural Network for Bearing Fault Diagnosis
TL;DR: The results show that the proposed method can learn more effective features from vibrational signals and deliver much higher accuracy than the seven state-of-the-art methods under highly noisy environments.
57
Causal Disentanglement Domain Generalization for time-series signal fault diagnosis.
Linshan Jia,Tommy W. S. Chow,Yixuan Yuan +2 more
TL;DR: This paper proposes Causal Disentanglement Domain Generalization (CDDG) for time-series signal fault diagnosis, which disentangles data into causal and non-causal factors using a structural causal model, and outperforms eight state-of-the-art methods on five vibrational and three acoustical cases.
18
Multiscale noise suppression and feature frequency extraction in SSVEP based on underdamped second-order stochastic resonance.
Pulin Yao,Guanghua Xu,Linshan Jia,Jinjin Duan,Chengcheng Han,Tangfei Tao,Yi Wang,Sicong Zhang +7 more
TL;DR: A novel method based on underdamped second-order stochastic resonance (USSR) is proposed, which effectively improves the information transmission rate (ITR) of SSVEP-based BCI and is compared with the widely-used canonical coefficient analysis and multivariate synchronization index.
14
Dynamic Balanced Dual Prototypical Domain Generalization for Cross-Machine Fault Diagnosis
TL;DR: In DBDP-Net, the dual prototype loss based on class and domain prototypes is designed to learn domain-invariant feature representation by reducing distribution discrepancy at class and domain levels, and a dynamic weighted strategy to balance the feature learning process of different domains is proposed.
3