Author name cluster

Yulin Sun

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

3 papers

2 author rows

EAAI Journal 2025 Journal Article

Unsupervised fault diagnosis method for rolling bearings based on federated universal domain adaptation

Shouqiang Kang
Yulin Sun
Xinrui Li
Yujing Wang
Qingyan Wang
Xintao Liang

To address the issues of low diagnostic model accuracy caused by non-sharing of rolling bearing private data, distribution differences, and label space discrepancies across multiple clients, as well as the challenges that certain clients face in obtaining labeled data, an unsupervised fault diagnosis method is proposed for rolling bearings based on federated universal domain adaptation (FUDA). First, privacy protection during the transmission process in federated learning is ensured by implementing random mapping at local clients. Second, the central server employs the proposed mixed radial basis kernel-maximum mean discrepancy (MR-MMD) method to further mitigate distributional disparities between the feature spaces of source and target clients. This achieves unsupervised features alignment between these features. Third, margin vectors are introduced to tackle label space disparities between source and target clients, enabling effective separation of unknown class samples in the dataset of the target client. Finally, a dynamic weighted loss fusion strategy is designed to adaptively optimize the weight ratios of different losses. This enhancement facilitates the learning efficiency of the model. Experimental validation on two datasets demonstrates that the proposed approach can achieve average accuracies of 95. 6 % and 87. 7 % for the respective datasets. Compared with other methods, it represents improvements of 6. 5 % and 8. 1 %, while training time is reduced by at least 27 %. These results validate the effectiveness of the proposed method.

Details DOI

JBHI Journal 2022 Journal Article

Continuous Seizure Detection Based on Transformer and Long-Term iEEG

Yulin Sun
Weipeng Jin
Xiaopeng Si
Xingjian Zhang
Jiale Cao
Le Wang
Shaoya Yin
Dong Ming

Automatic seizure detection algorithms are necessary for patients with refractory epilepsy. Many excellent algorithms have achieved good results in seizure detection. Still, most of them are based on discontinuous intracranial electroencephalogram (iEEG) and ignore the impact of different channels on detection. This study aimed to evaluate the proposed algorithm using continuous, long-term iEEG to show its applicability in clinical routine. In this study, we introduced the ability of the transformer network to calculate the attention between the channels of input signals into seizure detection. We proposed an end-to-end model that included convolution and transformer layers. The model did not need feature engineering or format transformation of the original multi-channel time series. Through evaluation on two datasets, we demonstrated experimentally that the transformer layer could improve the performance of the seizure detection algorithm. For the SWEC-ETHZ iEEG dataset, we achieved 97. 5% event-based sensitivity, 0. 06/h FDR, and 13. 7 s latency. For the TJU-HH iEEG dataset, we achieved 98. 1% event-based sensitivity, 0. 22/h FDR, and 9. 9 s latency. In addition, statistics showed that the model allocated more attention to the channels close to the seizure onset zone within 20 s after the seizure onset, which improved the explainability of the model. This paper provides a new method to improve the performance and explainability of automatic seizure detection.

Details DOI

ECAI Conference 2020 Conference Paper

Convolutional Dictionary Pair Learning Network for Image Representation Learning

Zhao Zhang 0001
Yulin Sun
Yang Wang 0023
Zheng-Jun Zha
Shuicheng Yan
Meng Wang 0001

Both the Dictionary Learning (DL) and Convolutional Neural Networks (CNN) are powerful image representation learning systems based on different mechanisms and principles, however whether we can seamlessly integrate them to improve the performance is noteworthy exploring. To address this issue, we propose a novel generalized end-to-end representation learning architecture, dubbed Convolutional Dictionary Pair Learning Network (CDPL-Net) in this paper, which integrates the learning schemes of the CNN and dictionary pair learning into a unified framework. Generally, the architecture of CDPL-Net includes two convolutional/pooling layers and two dictionary pair learning (DPL) layers in the representation learning module. Besides, it uses two fully-connected layers as the multi-layer perception layer in the nonlinear classification module. In particular, the DPL layer can jointly formulate the discriminative synthesis and analysis representations driven by minimizing the batch based reconstruction error over the flatted feature maps from the convolution/pooling layer. Moreover, DPL layer uses l1-norm on the analysis dictionary so that sparse representation can be delivered, and the embedding process will also be robust to noise. To speed up the training process of DPL layer, the efficient stochastic gradient descent is used. Extensive simulations on real databases show that our CDPL-Net can deliver enhanced performance over other state-of-the-art methods.

Details