Xing Shao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xing Shao has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Cuixiang Wang
Yancheng Institute of Technology
7 shared publicationsJun Gao
School of Information Engineering, Yancheng Institute of Technology, Yancheng, China
5 shared publicationsChuanxin Zhao
College of Computer and Information, Anhui Normal University, Wuhu, China
2 shared publications- Jun Gao
Yancheng Institute of Technology
2 shared publications Chen Qian
School of Information Engineering, Yancheng Institute of Technology, Yancheng, China
1 shared publicationChengfei Yang
School of Information Engineering, Yancheng Institute of Technology, Yancheng, China
1 shared publication
Latest Publications
- 22 May 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (21) , 216107
Cross-condition few-shot bearing fault diagnosis via learnable diagonal metric and transformer representation
To address the challenges of distribution shift and limited fault samples in cross-condition bearing fault diagnosis, this paper proposes a cross-condition few-shot diagnosis method based on a learnable diagonal metric (DMT) and structured optimization, termed DMT-ML. First, to reduce the dependence of conventional methods on time-frequency image preprocessing and improve end-to-end modeling capability, a metric-based meta-learning framework is developed directly on raw one-dimensional vibration signals, in which a 1D tokenizer and a transformer encoder are introduced to capture long-range dependencies and more stable discriminative patterns across operating conditions. Second, to overcome the limitation of fixed Euclidean distance in prototypical inference under anisotropic cross-condition feature distributions and unequal dimensional importance, a learnable DMT module is designed to adaptively reweight feature dimensions, thereby improving the robustness and discriminative reliability of prototype matching. Furthermore, to address the unstable decision boundaries caused by intra-class dispersion and inter-class overlap in the embedding space under few-shot settings, a joint objective combining cross-entropy loss with intra-class and inter-class optimization is introduced to enhance intra-class compactness and inter-class separability. Finally, experiments are conducted on the Case Western Reserve University, Jiangnan University, and Paderborn University datasets under a strict condition-wise episodic evaluation protocol. The results show that the proposed method achieves strong diagnostic accuracy and stability under most cross-condition few-shot task settings. These findings confirm the effectiveness of the proposed method for cross-condition few-shot bearing fault diagnosis.
- 22 May 2026
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (21) , 216107
Cross-condition few-shot bearing fault diagnosis via learnable diagonal metric and transformer representation
To address the challenges of distribution shift and limited fault samples in cross-condition bearing fault diagnosis, this paper proposes a cross-condition few-shot diagnosis method based on a learnable diagonal metric (DMT) and structured optimization, termed DMT-ML. First, to reduce the dependence of conventional methods on time-frequency image preprocessing and improve end-to-end modeling capability, a metric-based meta-learning framework is developed directly on raw one-dimensional vibration signals, in which a 1D tokenizer and a transformer encoder are introduced to capture long-range dependencies and more stable discriminative patterns across operating conditions. Second, to overcome the limitation of fixed Euclidean distance in prototypical inference under anisotropic cross-condition feature distributions and unequal dimensional importance, a learnable DMT module is designed to adaptively reweight feature dimensions, thereby improving the robustness and discriminative reliability of prototype matching. Furthermore, to address the unstable decision boundaries caused by intra-class dispersion and inter-class overlap in the embedding space under few-shot settings, a joint objective combining cross-entropy loss with intra-class and inter-class optimization is introduced to enhance intra-class compactness and inter-class separability. Finally, experiments are conducted on the Case Western Reserve University, Jiangnan University, and Paderborn University datasets under a strict condition-wise episodic evaluation protocol. The results show that the proposed method achieves strong diagnostic accuracy and stability under most cross-condition few-shot task settings. These findings confirm the effectiveness of the proposed method for cross-condition few-shot bearing fault diagnosis.
- 31 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 19938-19948
MTRT: Multitask Reconstruction Transformer for Sleep Stage Classification Based on Internet-of-Things-Enabled Wearable Devices
Sleep stage classification is an effective approach for diagnosing sleep disorders and holds significant importance in sleep research and biomedical studies. In recent years, sleep stage classification models based on machine learning and deep learning have achieved remarkable progress. However, several challenges remain. First, conventional deep learning-based sleep stage classification models struggle to effectively handle noise and artifacts, leading to inaccurate feature extraction. Second, the scarcity of minority class data, such as deep sleep and rapid eye movement (REM) stages, prevents models from learning crucial features of these stages. In addition, computational resource limitations hinder the deployment of previous models on wearable devices. To address these issues, we propose a multitask reconstruction Transformer (MTRT) for sleep stage classification based on the Internet-of-Things and wearable devices. MTRT integrates multiple advanced techniques, including masked autoencoders, Transformer networks, focal loss, and model pruning, to enhance classification performance and applicability. By introducing a masked autoencoder within a multitask learning framework, the model effectively removes noise and artifacts from electroencephalogram (EEG) signals, enabling the extraction of high-quality signal representations, thereby improving classification robustness and accuracy. The combination of signal reconstruction and sleep stage classification tasks facilitates feature sharing between the encoder and decoder, enhancing the model’s ability to learn from minority class samples and improving generalization. Moreover, model pruning reduces complexity, minimizing computational and memory requirements, making MTRT more suitable for real-time applications on wearable devices. Extensive experiments on real-world datasets demonstrate the superior performance of the proposed MTRT model.
- 31 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (10) , 19938-19948
MTRT: Multitask Reconstruction Transformer for Sleep Stage Classification Based on Internet-of-Things-Enabled Wearable Devices
Sleep stage classification is an effective approach for diagnosing sleep disorders and holds significant importance in sleep research and biomedical studies. In recent years, sleep stage classification models based on machine learning and deep learning have achieved remarkable progress. However, several challenges remain. First, conventional deep learning-based sleep stage classification models struggle to effectively handle noise and artifacts, leading to inaccurate feature extraction. Second, the scarcity of minority class data, such as deep sleep and rapid eye movement (REM) stages, prevents models from learning crucial features of these stages. In addition, computational resource limitations hinder the deployment of previous models on wearable devices. To address these issues, we propose a multitask reconstruction Transformer (MTRT) for sleep stage classification based on the Internet-of-Things and wearable devices. MTRT integrates multiple advanced techniques, including masked autoencoders, Transformer networks, focal loss, and model pruning, to enhance classification performance and applicability. By introducing a masked autoencoder within a multitask learning framework, the model effectively removes noise and artifacts from electroencephalogram (EEG) signals, enabling the extraction of high-quality signal representations, thereby improving classification robustness and accuracy. The combination of signal reconstruction and sleep stage classification tasks facilitates feature sharing between the encoder and decoder, enhancing the model’s ability to learn from minority class samples and improving generalization. Moreover, model pruning reduces complexity, minimizing computational and memory requirements, making MTRT more suitable for real-time applications on wearable devices. Extensive experiments on real-world datasets demonstrate the superior performance of the proposed MTRT model.
- 29 November 2025
- Published by Elsevier in Electric Power Systems Research
- Vol. 253
Residual-corrected TSMixer with a RIME-enhanced decomposition strategy for photovoltaic power prediction
- 29 November 2025
- Published by Elsevier in Electric Power Systems Research
- Vol. 253
Residual-corrected TSMixer with a RIME-enhanced decomposition strategy for photovoltaic power prediction
- 23 June 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (9) , 1-12
Bearing fault diagnosis method based on multi-scale residual and multi task depthwise separable network
- 23 June 2025
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 19 (9) , 1-12
Bearing fault diagnosis method based on multi-scale residual and multi task depthwise separable network
- 5 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (22) , 36066-36083
SAC-RSM: A High-Performance UAV-Side Road Surveillance Model Based on Super-Resolution Assisted Learning
Efficiently and precisely identifying small items on traffic highways using unmanned aerial vehicle (UAV) platforms with limited resources is a crucial yet challenging job. This research suggests a speedy, accurate, and component-optimized road surveillance model (SAC-RSM) for UAVs. This model addresses slow detection speed, limited detection of small objects, and deployment difficulties. Firstly, we designed a super-resolution-assisted learning branch in the network to balance the model’s detection speed and accuracy. This branch learns the feature representation from low to high resolution. This branch uses multi-scale feature fusion in the encoding stage to enhance the feature representation of small objects, thereby enhancing their detection accuracy. Secondly, to avoid the problem of cross-layer convolution, which results in the loss of fine-grained information and low learning efficiency, we propose using the convolution-to-space-convolution (CSPC) module in the backbone network to improve model detection’s robustness. Thirdly, to achieve real-time detection, we realized the model using the Huawei Ascend compute architecture for neural networks (CANN) framework to enable automatic quantization and parallel inference acceleration. Finally, we deployed the accelerated model to the embedded platform Atlas 200I Developer Kit (DK) A2. Compared to the baseline model, the proposed method shows significant increases in mean average precision (mAP) values for the VisDrone and DroneVehicle datasets, with increases of 17.4% and 9.4%, respectively. The proposed method achieves frames per second (FPS) of 38.3, which is 2.1 times faster than the baseline model, meeting the requirement for high-performance real-time detection in a UAV environment.
- 5 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (22) , 36066-36083
SAC-RSM: A High-Performance UAV-Side Road Surveillance Model Based on Super-Resolution Assisted Learning
Efficiently and precisely identifying small items on traffic highways using unmanned aerial vehicle (UAV) platforms with limited resources is a crucial yet challenging job. This research suggests a speedy, accurate, and component-optimized road surveillance model (SAC-RSM) for UAVs. This model addresses slow detection speed, limited detection of small objects, and deployment difficulties. Firstly, we designed a super-resolution-assisted learning branch in the network to balance the model’s detection speed and accuracy. This branch learns the feature representation from low to high resolution. This branch uses multi-scale feature fusion in the encoding stage to enhance the feature representation of small objects, thereby enhancing their detection accuracy. Secondly, to avoid the problem of cross-layer convolution, which results in the loss of fine-grained information and low learning efficiency, we propose using the convolution-to-space-convolution (CSPC) module in the backbone network to improve model detection’s robustness. Thirdly, to achieve real-time detection, we realized the model using the Huawei Ascend compute architecture for neural networks (CANN) framework to enable automatic quantization and parallel inference acceleration. Finally, we deployed the accelerated model to the embedded platform Atlas 200I Developer Kit (DK) A2. Compared to the baseline model, the proposed method shows significant increases in mean average precision (mAP) values for the VisDrone and DroneVehicle datasets, with increases of 17.4% and 9.4%, respectively. The proposed method achieves frames per second (FPS) of 38.3, which is 2.1 times faster than the baseline model, meeting the requirement for high-performance real-time detection in a UAV environment.
- Open Access
- 11 January 2024
- Published by Springer Nature in EURASIP Journal on Advances in Signal Processing
- Vol. 2024 (1) , 1-19
Unsupervised domain adaptive bearing fault diagnosis based on maximum domain discrepancy
In the existing domain adaptation-based bearing fault diagnosis methods, the data difference between the source domain and the target domain is not obvious. Besides, parameters of target domain feature extractor gradually approach that of source domain feature extractor to cheat discriminator which results in similar feature distribution of source domain and target domain. These issues make it difficult for the domain adaptation-based bearing fault diagnosis methods to achieve satisfactory performance. An unsupervised domain adaptive bearing fault diagnosis method based on maximum domain discrepancy (UDA-BFD-MDD) is proposed in this paper. In UDA-BFD-MDD, maximum domain discrepancy is exploited to maximize the feature difference between the source domain and target domain, while the output feature of target domain feature extractor can cheat the discriminator. The performance of UDA-BFD-MDD is verified through comprehensive experiments using the bearing dataset of Case Western Reserve University. The experimental results demonstrate that UDA-BFD-MDD is more stable during training process and can achieve higher accuracy rate.
- 11 January 2024
- Published by Springer Nature in EURASIP Journal on Advances in Signal Processing
- Vol. 2024 (1) , 1-19
Open AccessUnsupervised domain adaptive bearing fault diagnosis based on maximum domain discrepancy
In the existing domain adaptation-based bearing fault diagnosis methods, the data difference between the source domain and the target domain is not obvious. Besides, parameters of target domain feature extractor gradually approach that of source domain feature extractor to cheat discriminator which results in similar feature distribution of source domain and target domain. These issues make it difficult for the domain adaptation-based bearing fault diagnosis methods to achieve satisfactory performance. An unsupervised domain adaptive bearing fault diagnosis method based on maximum domain discrepancy (UDA-BFD-MDD) is proposed in this paper. In UDA-BFD-MDD, maximum domain discrepancy is exploited to maximize the feature difference between the source domain and target domain, while the output feature of target domain feature extractor can cheat the discriminator. The performance of UDA-BFD-MDD is verified through comprehensive experiments using the bearing dataset of Case Western Reserve University. The experimental results demonstrate that UDA-BFD-MDD is more stable during training process and can achieve higher accuracy rate.
- Open Access
- 1 January 2020
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 66 (1) , 931-945
A Physical Layer Network Coding Based Tag Anti-collision Algorithm for RFID System
In RFID (Radio Frequency IDentification) system, when multiple tags are in the operating range of one reader and send their information to the reader simultaneously, the signals of these tags are superimposed in the air, which results in a collision and leads to the degrading of tags identifying efficiency. To improve the multiple tags’ identifying efficiency due to collision, a physical layer network coding based binary search tree algorithm (PNBA) is proposed in this paper. PNBA pushes the conflicting signal information of multiple tags into a stack, which is discarded by the traditional anti-collision algorithm. In addition, physical layer network coding is exploited by PNBA to obtain unread tag information through the decoding operation of physical layer network coding using the con- flicting information in the stack. Therefore, PNBA reduces the number of interactions between reader and tags, and improves the tags identification efficiency. Theoretical analysis and simulation results using MATLAB demonstrate that PNBA reduces the number of readings, and improve RFID identification effi- ciency. Especially, when the number of tags to be identified is 100, the average needed reading number of PNBA is 83% lower than the basic binary search tree algorithm, 43% lower than reverse binary search tree algorithm, and its reading efficiency reaches 0.93.
- 1 January 2020
- Published by Tech Science Press in Computers, Materials & Continua
- Vol. 66 (1) , 931-945
Open AccessA Physical Layer Network Coding Based Tag Anti-collision Algorithm for RFID System
In RFID (Radio Frequency IDentification) system, when multiple tags are in the operating range of one reader and send their information to the reader simultaneously, the signals of these tags are superimposed in the air, which results in a collision and leads to the degrading of tags identifying efficiency. To improve the multiple tags’ identifying efficiency due to collision, a physical layer network coding based binary search tree algorithm (PNBA) is proposed in this paper. PNBA pushes the conflicting signal information of multiple tags into a stack, which is discarded by the traditional anti-collision algorithm. In addition, physical layer network coding is exploited by PNBA to obtain unread tag information through the decoding operation of physical layer network coding using the con- flicting information in the stack. Therefore, PNBA reduces the number of interactions between reader and tags, and improves the tags identification efficiency. Theoretical analysis and simulation results using MATLAB demonstrate that PNBA reduces the number of readings, and improve RFID identification effi- ciency. Especially, when the number of tags to be identified is 100, the average needed reading number of PNBA is 83% lower than the basic binary search tree algorithm, 43% lower than reverse binary search tree algorithm, and its reading efficiency reaches 0.93.
- Open Access
- 5 June 2019
- Published by SAGE Publications in International Journal of Distributed Sensor Networks
- Vol. 15 (6)
Common network coding condition and traffic matching supported network coding aware routing for wireless multihop network
Network coding–based routing has been widely considered as a promising technology to improve the network throughput of wireless multihop network. However, existing network coding aware routings have the problem of failure decoding and usually neglect the transmission scheduling, which degrades the gain of network coding. In this article, a common network coding condition and traffic matching supported network coding aware routing is proposed for wireless multihop network. In this, common network coding condition is proposed to avoid the problem of failed decoding. In addition, traffic matching mechanism is presented to promote the occurrence of network coding. Besides, a coding and load aware routing metric, which jointly considers the network coding opportunity and node load, is designed to evaluate the discovered paths. Extensive simulations on NS2 demonstrate that CTNR increases the number of coding opportunities and network coding occurrence, and improves network throughput.
- 5 June 2019
- Published by SAGE Publications in International Journal of Distributed Sensor Networks
- Vol. 15 (6)
Open AccessCommon network coding condition and traffic matching supported network coding aware routing for wireless multihop network
Network coding–based routing has been widely considered as a promising technology to improve the network throughput of wireless multihop network. However, existing network coding aware routings have the problem of failure decoding and usually neglect the transmission scheduling, which degrades the gain of network coding. In this article, a common network coding condition and traffic matching supported network coding aware routing is proposed for wireless multihop network. In this, common network coding condition is proposed to avoid the problem of failed decoding. In addition, traffic matching mechanism is presented to promote the occurrence of network coding. Besides, a coding and load aware routing metric, which jointly considers the network coding opportunity and node load, is designed to evaluate the discovered paths. Extensive simulations on NS2 demonstrate that CTNR increases the number of coding opportunities and network coding occurrence, and improves network throughput.
- Open Access
- 20 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 71767-71782
Traffic Shaped Network Coding Aware Routing for Wireless Sensor Networks
Energy efficiency is a critical problem for wireless sensor networks. In past decades, network coding has been proved as a promising technology to reduce the number of transmissions, save energy and improve network throughput, especially suitable for the wireless network, which motivates the emergence of network coding aware routings. However, existing network coding aware routings have the failure decoding problem because of defective network coding conditions. On the other hand, existing network coding aware routings usually consider the ideal traffic scheduling and neglect nodes’ energy and load which are important to wireless sensor networks. Therefore, it is not appropriate to directly apply existing network coding aware routings in wireless sensor networks. Regarding the problems above, this paper proposes the traffic shaped network coding aware routing (TSCAR) for wireless sensor networks. In TSCAR, a universal network coding condition is presented to solve the false decoding problem. And traffic shaping mechanism is proposed to shape the traffic of different flows to create more coding actions when coding opportunities exist. In addition, network calculus is used to analyze the delay of TSCAR. Besides, a coding, load, and energy aware routing metric (CLERM) is proposed to evaluate the discovered paths. Extensive simulation results demonstrate that TSCAR increases the number of coding opportunities and the proportion of coded packets, improves network throughput, and extends the network lifetime of wireless sensor networks.
- 20 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 71767-71782
Open AccessTraffic Shaped Network Coding Aware Routing for Wireless Sensor Networks
Energy efficiency is a critical problem for wireless sensor networks. In past decades, network coding has been proved as a promising technology to reduce the number of transmissions, save energy and improve network throughput, especially suitable for the wireless network, which motivates the emergence of network coding aware routings. However, existing network coding aware routings have the failure decoding problem because of defective network coding conditions. On the other hand, existing network coding aware routings usually consider the ideal traffic scheduling and neglect nodes’ energy and load which are important to wireless sensor networks. Therefore, it is not appropriate to directly apply existing network coding aware routings in wireless sensor networks. Regarding the problems above, this paper proposes the traffic shaped network coding aware routing (TSCAR) for wireless sensor networks. In TSCAR, a universal network coding condition is presented to solve the false decoding problem. And traffic shaping mechanism is proposed to shape the traffic of different flows to create more coding actions when coding opportunities exist. In addition, network calculus is used to analyze the delay of TSCAR. Besides, a coding, load, and energy aware routing metric (CLERM) is proposed to evaluate the discovered paths. Extensive simulation results demonstrate that TSCAR increases the number of coding opportunities and the proportion of coded packets, improves network throughput, and extends the network lifetime of wireless sensor networks.
- Open Access
- 1 October 2018
- Published by Springer Nature in EURASIP Journal on Wireless Communications and Networking
- Vol. 2018 (1) , 231
Research on network coding aware energy efficient routing for wireless sensor networks
- 1 October 2018
- Published by Springer Nature in EURASIP Journal on Wireless Communications and Networking
- Vol. 2018 (1) , 231
Open AccessResearch on network coding aware energy efficient routing for wireless sensor networks