Rong Yao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Rong Yao has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Cheng Wu
Department of Automation, Tsinghua University, Beijing, China
1 shared publication - Chongdang Liu
Department of Automation, State CIMS Engineering Research Center, Tsinghua University, Beijing, China
1 shared publication - Haifang Li
Department of Artificial Intelligence and Informatics, Mayo Clinic, Jacksonville, FL 32224, USA
1 shared publication - Linxuan Zhang
Department of Automation, Tsinghua University, Beijing 100084, China
1 shared publication - Pengfei Yang
Key Laboratory of Data Engineering and Visual Computing, College of Computer Science and Technology, Chongqing University of Posts and Telecommunication, Chongqing, China
1 shared publication - Xiong Yang
Tianjin University
1 shared publication
Latest Publications
- 2 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-10
Dual Attention-Based Temporal Convolutional Network for Fault Prognosis Under Time-Varying Operating Conditions
Fault prognosis under time-varying operating conditions is critical to predictive maintenance of complex industrial machines. However, prognostic methods proposed in the literature toward varying operating conditions typically focus on limited discrete states with clear boundaries, which are not always encountered in practical scenarios. This article aims to propose a more general method that can handle complex operating conditions with more nonlinearity and dynamics. In this work, a novel deep model named dual attention-based temporal convolutional network (DATCN), is developed to integrate multisensor data with time-varying operating settings for health assessment of industrial machines. An efficient deep temporal convolutional network is introduced to extract degradation features for sequence modeling. A novel dual attention model is developed to adaptively capture the temporal dynamics of sensor data and operating data, further enhancing the feature representations and highlighting the degradation information under time-varying operating settings. Besides, domain adaptation layer with multikernel maximum mean discrepancies (MK-MMD) is embedded to mitigate the domain-shift issue caused by varying operating conditions. The experimental results on the popular turbofan engine data set and a real-world Ion mill etching process validate the effectiveness of the proposed method and show its superiority in yielding significant improvements of prognostic accuracy relative to existing state-of-the-art methods.
- 2 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 70 (00189456) , 1-10
Dual Attention-Based Temporal Convolutional Network for Fault Prognosis Under Time-Varying Operating Conditions
Fault prognosis under time-varying operating conditions is critical to predictive maintenance of complex industrial machines. However, prognostic methods proposed in the literature toward varying operating conditions typically focus on limited discrete states with clear boundaries, which are not always encountered in practical scenarios. This article aims to propose a more general method that can handle complex operating conditions with more nonlinearity and dynamics. In this work, a novel deep model named dual attention-based temporal convolutional network (DATCN), is developed to integrate multisensor data with time-varying operating settings for health assessment of industrial machines. An efficient deep temporal convolutional network is introduced to extract degradation features for sequence modeling. A novel dual attention model is developed to adaptively capture the temporal dynamics of sensor data and operating data, further enhancing the feature representations and highlighting the degradation information under time-varying operating settings. Besides, domain adaptation layer with multikernel maximum mean discrepancies (MK-MMD) is embedded to mitigate the domain-shift issue caused by varying operating conditions. The experimental results on the popular turbofan engine data set and a real-world Ion mill etching process validate the effectiveness of the proposed method and show its superiority in yielding significant improvements of prognostic accuracy relative to existing state-of-the-art methods.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 122-130
Difference Analysis of Brain Network Working Memory Data with EEG Sub-Sequence Feature Vector as Node
Many studies have shown that microstates are related to psychological processes. This study investigated the microphysical activities of brain microstates and working memory, and found that there are significant differences in microstates at different stages of working memory and there are also significant differences in microstates between normal people and patients. However, the microstate can only analyze the EEG signal from a global perspective, and cannot understand the EEG signal characteristics of each channel in detail. This study proposes a new analysis method based on microstates to analyze EEG signals, including segmentation, feature extraction, EEG signal feature selection, channel network construction, and channel network characteristic analysis. In the segmentation, the microstates used to segment the multi-channel signal, and divide each channel signal into sub-sequences of different lengths. The feature extraction mainly uses the features frequently used in EEG signals, including statistical features, nonlinearities, and entropy characteristics. In this experiment, a sequence forward selection algorithm is used to select a set of effective features that best represent the EEG signal. In the channel construction network, the Pearson correlation coefficient is used to calculate the correlation between each sub-segment of each channel of the working memory. Finally, the network attributes of the networks and the similarity between each channel are analyzed. It is found that there are significant differences between normal people and patients in the network properties constructed and the channel network, which provides a basis for the diagnosis and treatment of patients with schizophrenia.
- 1 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 122-130
Difference Analysis of Brain Network Working Memory Data with EEG Sub-Sequence Feature Vector as Node
Many studies have shown that microstates are related to psychological processes. This study investigated the microphysical activities of brain microstates and working memory, and found that there are significant differences in microstates at different stages of working memory and there are also significant differences in microstates between normal people and patients. However, the microstate can only analyze the EEG signal from a global perspective, and cannot understand the EEG signal characteristics of each channel in detail. This study proposes a new analysis method based on microstates to analyze EEG signals, including segmentation, feature extraction, EEG signal feature selection, channel network construction, and channel network characteristic analysis. In the segmentation, the microstates used to segment the multi-channel signal, and divide each channel signal into sub-sequences of different lengths. The feature extraction mainly uses the features frequently used in EEG signals, including statistical features, nonlinearities, and entropy characteristics. In this experiment, a sequence forward selection algorithm is used to select a set of effective features that best represent the EEG signal. In the channel construction network, the Pearson correlation coefficient is used to calculate the correlation between each sub-segment of each channel of the working memory. Finally, the network attributes of the networks and the similarity between each channel are analyzed. It is found that there are significant differences between normal people and patients in the network properties constructed and the channel network, which provides a basis for the diagnosis and treatment of patients with schizophrenia.