Hao Yan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Hao Yan has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Chuan Lin
Southwest Jiaotong University
2 shared publications - Ningning Guo
School of Electrical Engineering, Southwest Jiaotong University, Chengdu, China
2 shared publications Anyong Qing
1 shared publication- Anyong Qing
School of Electrical Engineering, Southwest Jiaotong University, Chengdu, China
1 shared publication Chuan Lin
1 shared publicationJiefeng Zang
1 shared publication
Latest Publications
- 5 August 2025
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 127
A three-stage framework for multi-type pantograph anomaly detection under complex environments
- 5 August 2025
- Published by Elsevier in Computers and Electrical Engineering
- Vol. 127
A three-stage framework for multi-type pantograph anomaly detection under complex environments
- Open Access
- 18 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 55-60
Pantograph unsupervised anomaly detection network based on reverse distillation
The pantograph, as a crucial component for the transmission of electrical energy in trains, plays a pivotal role in ensuring the safety of train operations. In this study, we have developed an unsupervised anomaly detection network, denoted as Pantograph Anomaly Detection Network (PADN), specifically tailored for the anomaly detection of the pantograph. PADN leverages a reverse distillation architecture and incorporates structural characteristics of the pantograph through a two-phase training approach. Meanwhile, The approach utilizes a trainable dual-teacher architecture, facilitating the assimilation of a more comprehensive range of features specific to the pantograph dataset by the student network. Empirical results demonstrate that PADN surpasses the performance of the current state-of-the-art (SOTA) networks on the pantograph dataset, achieving an accuracy rate of 97.87% in the final identification of pantograph anomalies.
- 18 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 55-60
Open AccessPantograph unsupervised anomaly detection network based on reverse distillation
The pantograph, as a crucial component for the transmission of electrical energy in trains, plays a pivotal role in ensuring the safety of train operations. In this study, we have developed an unsupervised anomaly detection network, denoted as Pantograph Anomaly Detection Network (PADN), specifically tailored for the anomaly detection of the pantograph. PADN leverages a reverse distillation architecture and incorporates structural characteristics of the pantograph through a two-phase training approach. Meanwhile, The approach utilizes a trainable dual-teacher architecture, facilitating the assimilation of a more comprehensive range of features specific to the pantograph dataset by the student network. Empirical results demonstrate that PADN surpasses the performance of the current state-of-the-art (SOTA) networks on the pantograph dataset, achieving an accuracy rate of 97.87% in the final identification of pantograph anomalies.
- 27 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
Real-Time Pantograph Anomaly Detection Using Unsupervised Deep Learning and K-Nearest Neighbor Classification
An image-based real-time pantograph anomaly detection method is presented by combining unsupervised deep learning and nearest neighbor classification. The proposed method includes the following key steps. Firstly, an improved DeblurGAN-v2 deblurring algorithm is applied to the input pantograph image if there exists motion blur. Next, deep learning semantic segmentation with hybrid coding that combines lightweight convolutional neural network (CNN) and vision transformer (VIT) is employed to accurately segment the pantograph structure within the image. And multi-scale feature-dense aggregation network based on an attentional feature fusion (AFF) module has been designed to efficiently integrate information from different feature layers. Finally, a K-nearest neighbor classification algorithm with deep pre-trained features from the segmented pantograph mask image has been utilized to detect anomalies in the pantograph. Experimental results demonstrate that the proposed pantograph segmentation network outperforms several general segmentation algorithms, achieving high MIoU of 95.86% with parameter size of 7M and FPS of 81.7. And nearest neighbor classification with deep pre-trained features achieves excellent pantograph anomaly detection performance with area under the receiver operating characteristic curve of 0.987 and area under precision-recall curve of 0.998. It is verified that the proposed pantograph anomaly detection method does not rely on abnormal data, and can achieve a high anomaly detection accuracy of 98.75%.
- 27 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
Real-Time Pantograph Anomaly Detection Using Unsupervised Deep Learning and K-Nearest Neighbor Classification
An image-based real-time pantograph anomaly detection method is presented by combining unsupervised deep learning and nearest neighbor classification. The proposed method includes the following key steps. Firstly, an improved DeblurGAN-v2 deblurring algorithm is applied to the input pantograph image if there exists motion blur. Next, deep learning semantic segmentation with hybrid coding that combines lightweight convolutional neural network (CNN) and vision transformer (VIT) is employed to accurately segment the pantograph structure within the image. And multi-scale feature-dense aggregation network based on an attentional feature fusion (AFF) module has been designed to efficiently integrate information from different feature layers. Finally, a K-nearest neighbor classification algorithm with deep pre-trained features from the segmented pantograph mask image has been utilized to detect anomalies in the pantograph. Experimental results demonstrate that the proposed pantograph segmentation network outperforms several general segmentation algorithms, achieving high MIoU of 95.86% with parameter size of 7M and FPS of 81.7. And nearest neighbor classification with deep pre-trained features achieves excellent pantograph anomaly detection performance with area under the receiver operating characteristic curve of 0.987 and area under precision-recall curve of 0.998. It is verified that the proposed pantograph anomaly detection method does not rely on abnormal data, and can achieve a high anomaly detection accuracy of 98.75%.