Zitong Wan

Bio: Zitong Wan is an academic researcher from University of Liverpool. The author has contributed to research in topics: Transfer of learning & Artificial intelligence. The author has an hindex of 2, co-authored 4 publications receiving 32 citations. Previous affiliations of Zitong Wan include Xi'an Jiaotong-Liverpool University.

Deep Transfer Learning-Based Fault Diagnosis for Gearbox under Complex Working Conditions

Abstract: In the large amount of available data, information insensitive to faults in historical data interferes in gear fault feature extraction. Furthermore, as most of the fault diagnosis models are learned from offline data collected under single/fixed working condition only, this may cause unsatisfactory performance for complex working conditions (including multiple and unknown working conditions) if not properly dealt with. This paper proposes a transfer learning-based fault diagnosis method of gear faults to reduce the negative effects of the abovementioned problems. In the proposed method, a cohesion evaluation method is applied to select sensitive features to the task with a transfer learning-based sparse autoencoder to transfer the knowledge learnt under single working condition to complex working conditions. The experimental results on wind turbine drivetrain diagnostics simulator show that the proposed method is effective in complex working conditions and the achieved results are better than those of traditional algorithms.

A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface

Abstract: The classification of motor imagery (MI) signal is a representative problem in brain-computer interface (BCI) systems. Because one main application field of MI-based BCI is medical rehabilitation, it is often difficult to obtain a large amount of labeled data from the same subject. Moreover, there are huge individual differences among subjects, so the data from other subjects can not be directly used to train the classifier of the target subject. A transfer learning approach which based on data alignment and deep transfer learning is proposed to solve above problem, and the effectiveness of the proposed approach is verified by experiments based on open dataset.

Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review

Abstract: The brain–computer interface (BCI) is an emerging technology that has the potential to revolutionize the world, with numerous applications ranging from healthcare to human augmentation. Electroencephalogram (EEG) motor imagery (MI) is among the most common BCI paradigms that have been used extensively in smart healthcare applications such as post-stroke rehabilitation and mobile assistive robots. In recent years, the contribution of deep learning (DL) has had a phenomenal impact on MI-EEG-based BCI. In this work, we systematically review the DL-based research for MI-EEG classification from the past ten years. This article first explains the procedure for selecting the studies and then gives an overview of BCI, EEG, and MI systems. The DL-based techniques applied in MI classification are then analyzed and discussed from four main perspectives: preprocessing, input formulation, deep learning architecture, and performance evaluation. In the discussion section, three major questions about DL-based MI classification are addressed: (1) Is preprocessing required for DL-based techniques? (2) What input formulations are best for DL-based techniques? (3) What are the current trends in DL-based techniques? Moreover, this work summarizes MI-EEG-based applications, extensively explores public MI-EEG datasets, and gives an overall visualization of the performance attained for each dataset based on the reviewed articles. Finally, current challenges and future directions are discussed.

Deep Learning-Based Fault Diagnosis of Photovoltaic Systems: A Comprehensive Review and Enhancement Prospects

Abstract: Photovoltaic (PV) systems are subject to failures during their operation due to the aging effects and external/environmental conditions. These faults may affect the different system components such as PV modules, connection lines, converters/inverters, which can lead to a decrease in the efficiency, performance, and further system collapse. Thus, a key factor to be taken into consideration in high-efficiency grid-connected PV systems is the fault detection and diagnosis (FDD). The performance of the FDD method depends mainly on the quality of the extracted features including real-time changes, phase changes, trend changes, and faulty modes. Thus, the data representation learning is the core stage of intelligent FDD techniques. Recently, due to the enhancement of computing capabilities, the increase of the big data use, and the development of effective algorithms, the deep learning (DL) tool has witnessed a great success in data science. Therefore, this paper proposes an extensive review on deep learning based FDD methods for PV systems. After a brief description of the DL-based strategies, techniques for diagnosing PV systems proposed in recent literature are overviewed and analyzed to point out their differences, advantages and limits. Future research directions towards the improvement of the performance of the DL-based FDD techniques are also discussed. This review paper aims to systematically present the development of DL-based FDD for PV systems and provide guidelines for future research in the field.

Investigating EEG-Based Functional Connectivity Patterns for Multimodal Emotion Recognition.

Abstract: Compared with the rich studies on the motor brain-computer interface (BCI), the recently emerging affective BCI presents distinct challenges since the brain functional connectivity networks involving emotion are not well investigated. Previous studies on emotion recognition based on electroencephalography (EEG) signals mainly rely on single-channel-based feature extraction methods. In this paper, we propose a novel emotion-relevant critical subnetwork selection algorithm and investigate three EEG functional connectivity network features: strength, clustering coefficient, and eigenvector centrality. The discrimination ability of the EEG connectivity features in emotion recognition is evaluated on three public emotion EEG datasets: SEED, SEED-V, and DEAP. The strength feature achieves the best classification performance and outperforms the state-of-the-art differential entropy feature based on single-channel analysis. The experimental results reveal that distinct functional connectivity patterns are exhibited for the five emotions of disgust, fear, sadness, happiness, and neutrality. Furthermore, we construct a multimodal emotion recognition model by combining the functional connectivity features from EEG and the features from eye movements or physiological signals using deep canonical correlation analysis. The classification accuracies of multimodal emotion recognition are 95.08/6.42% on the SEED dataset, 84.51/5.11% on the SEED-V dataset, and 85.34/2.90% and 86.61/3.76% for arousal and valence on the DEAP dataset, respectively. The results demonstrate the complementary representation properties of the EEG connectivity features with eye movement data. In addition, we find that the brain networks constructed with 18 channels achieve comparable performance with that of the 62-channel network in multimodal emotion recognition and enable easier setups for BCI systems in real scenarios.