Chenglu Sun

Chenglu Sun

Auto-generated profile, based on publicly available information

Chenglu Sun

Cooperation Product Department, Interactive Entertainment Group, Tencent, Shanghai, China

Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 August 2019 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
CSChenglu Sun
Chenglu Sun
Chen ChenChen Chen
Chen Chen
WLWei Li
Wei Li
JFJiahao Fan
Jiahao Fan
Wei ChenWei Chen
Wei Chen
Automatic sleep staging methods usually extract hand-crafted features or network trained features from signals recorded by polysomnography (PSG), and then estimate the stages by various classifiers. In this study, we propose a classification approach based on a hierarchical neural network to process multi-channel PSG signals for improving the performance of automatic five-class sleep staging. The proposed hierarchical network contains two stages: comprehensive feature learning stage and sequence learning stage. The first stage is used to obtain the feature matrix by fusing the hand-crafted features and network trained features. A multi-flow recurrent neural network (RNN) as the second stage is utilized to fully learn temporal information between sleep epochs and fine-tune the parameters in the first stage. The proposed model was evaluated by 147 full night recordings in a public sleep database, the Montreal Archive of Sleep Studies (MASS). The proposed approach can achieve the overall accuracy of 0.878, and the F1-score is 0.818. The results show that the approach can achieve better performance compared to the state-of-the-art methods. Ablation experiment and model analysis proved the effectiveness of different components of the proposed model. The proposed approach allows automatic sleep stage classification by multi-channel PSG signals with different criteria standards, signal characteristics, and epoch divisions, and it has the potential to exploit sleep information comprehensively.

1 October 2020 in Journal of Neural Engineering
Verified
Journal Article
Closed access
JFJiahao Fan
Jiahao Fan
CSChenglu Sun
Chenglu Sun
Chen ChenChen Chen
Chen Chen
XJXinyu Jiang
Xinyu Jiang
XLXiangyu Liu
Xiangyu Liu
WCWei Chen
Wei Chen
Objective. Automatic sleep staging models suffer from an inherent class imbalance problem (CIP), which hinders the classifiers from achieving a better performance. To address this issue, we systematically studied sleep electroencephalogram data augmentation (DA) approaches. Furthermore, we modified and transferred novel DA approaches from related research fields, yielding new efficient ways to enhance sleep datasets. Approach. This study covers five DA methods, including repeating minority classes, morphological change, signal segmentation and recombination, dataset-to-dataset transfer, as well as generative adversarial network (GAN). We evaluated these mentioned DA methods by a sleep staging model on two datasets, the Montreal archive of sleep studies (MASS) and Sleep-EDF. We used a classification model with a typical convolutional neural network architecture to evaluate the effectiveness of the mentioned DA approaches. We also conducted a comprehensive analysis of these methods. Main results. The classification results showed that DA methods, especially DA by GAN, significantly improved the total classification performance in comparison with the baseline. The improvement of accuracy, F1 score and Cohen Kappa coefficient range from 0.90% to 3.79%, 0.73% to 3.48%, 2.61% to 5.43% on MASS and 1.36% to 4.79%, 1.47% to 4.23%, 2.22% to 4.04% on Sleep-EDF, respectively. DA methods improved the classification performance in most cases, whereas the performance of class N1 showed a subtle degradation in the F1 scores. Significance. Overall, our study proved that DA approaches are efficient in alleviating CIP lying in sleep staging tasks. Meanwhile, this study provided avenues for further improving the sleep staging accuracy using DA methods.

8 August 2019 in IEEE Access
Verified
Journal Article
Open access
CSChenglu Sun
Chenglu Sun
JFJiahao Fan
Jiahao Fan
Chen ChenChen Chen
Chen Chen
WLWei Li
Wei Li
WCWei Chen
Wei Chen
Sleep stage classification is a fundamental but cumbersome task in sleep analysis. To score the sleep stage automatically, this study presents a stage classification method based on a two-stage neural network. The feature learning stage as the first stage can fuse network trained features with traditional hand-crafted features. A recurrent neural network (RNN) in the second stage is fully utilized for learning temporal information between sleep epochs and obtaining classification results. To solve serious sample imbalance problem, a novel pre-training process combined with data augmentation was introduced. The proposed method was evaluated by two public databases, the Sleep-EDF and Sleep Apnea (SA). The proposed method can achieve the F1-score and Kappa coefficient of 0.806 and 0.80 for healthy subjects, respectively, and achieve 0.790 and 0.74 for the subjects with suspect sleep disorders, respectively. The results show that the method can achieve better performance compared to the state-of-the-art methods for the same databases. Model analysis displayed that the combination of the hand-crafted features and network trained features can improve the classification performance via the comparison experiments. In addition, the RNN is a good choice for learning temporal information in sleep epochs. Besides, the pre-training process with data augmentation is verified that can reduce the impact of sample imbalance. The proposed model has potential to exploit sleep information comprehensively.

29 October 2019 in Journal of Neural Engineering
Verified
Journal Article
Closed access
CSChenglu Sun
Chenglu Sun
Chen ChenChen Chen
Chen Chen
JFJiahao Fan
Jiahao Fan
WLWei Li
Wei Li
YZYuan-Ting Zhang
Yuan-Ting Zhang
WCWei Chen
Wei Chen
Objective . Currently, the automatic sleep staging methods mainly face two problems: the first problem is that although the algorithms which use electroencephalogram (EEG) signals perform well, acquiring EEG signals is complicated and uncomfortable; the second problem is that if the methods utilize physiological signals collected by user-friendly devices, such as cardiorespiratory signals, whose accuracies are hard to be accepted by clinicians, although the employed signals are easy and comfortable to acquire. Approach . To overcome the two issues, an automatic sleep staging method is proposed by developing a hierarchical sequential neural network to process only the electrooculogram (EOG) and R–R interval (RR) signals. The two signals are convenient and comfortable to acquire. The proposed network mainly contains two parts: comprehensive feature learning and sequence learning. The first part extracts hand-crafted features, and network trained features are simultaneously learned by a two-scale network. Then the two kinds of features are fused. The second part utilized a two-flow recurrent neural network (RNN) to learn temporal information between sleep epochs. Main results . The proposed method was evaluated on 86 subjects from two public databases, the Montreal archive of sleep studies (MASS) and sleep apnea (SA). The proposed method can discriminate five sleep stages with the F1-score of 0.781 and 0.740 for MASS and SA, respectively. And discriminate four stages with the F1-score of 0.858 and 0.802 for MASS and SA, respectively. Significance . The proposed method can achieve comparable performance as using EEG signals for sleep staging and have better performance compared to five related state-of-the-art methods. Model analysis displayed that the network can learn effective features and sequence information from EOG and RR signals. In summary, the proposed method is promising to enable new sleep monitoring in a more convenient way while having a good performance on sleep staging.

10 August 2017 in Sensors
Verified
Journal Article
Open access
PDF file
CSChenglu Sun
Chenglu Sun
WLWei Li
Wei Li
Wei ChenWei Chen
Wei Chen
For extracting the pressure distribution image and respiratory waveform unobtrusively and comfortably, we proposed a smart mat which utilized a flexible pressure sensor array, printed electrodes and novel soft seven-layer structure to monitor those physiological information. However, in order to obtain high-resolution pressure distribution and more accurate respiratory waveform, it needs more time to acquire the pressure signal of all the pressure sensors embedded in the smart mat. In order to reduce the sampling time while keeping the same resolution and accuracy, a novel method based on compressed sensing (CS) theory was proposed. By utilizing the CS based method, 40% of the sampling time can be decreased by means of acquiring nearly one-third of original sampling points. Then several experiments were carried out to validate the performance of the CS based method. While less than one-third of original sampling points were measured, the correlation degree coefficient between reconstructed respiratory waveform and original waveform can achieve 0.9078, and the accuracy of the respiratory rate (RR) extracted from the reconstructed respiratory waveform can reach 95.54%. The experimental results demonstrated that the novel method can fit the high resolution smart mat system and be a viable option for reducing the sampling time of the pressure sensor array.

17 December 2018 in IEEE Access
Verified
Journal Article
Open access
Chen ChenChen Chen
Chen Chen
AUAdrien Ugon
Adrien Ugon
CSChenglu Sun
Chenglu Sun
WCWei Chen
Wei Chen
CPCarole Philippe
Carole Philippe
APAndrea Pinna
Andrea Pinna
Identification of sleep stages is a fundamental step in clinical sleep analysis. Existing automatic sleep staging systems ignore two major issues: 1) Most of existing automatic sleep staging systems are using numerical classification methods without involving medical knowledge. While these kinds of systems are not yet understood and accepted by physicians. 2) Individual variability sources are ignored. However, individual variability is observed in many aspects of sleep research (such as polysomnography recordings, sleep patterns, sleep architecture, etc.). In this paper, a hybrid expert system is proposed to mimic the decision-making process of clinical sleep staging in accordance with medical knowledge by using symbolic fusion. To formalize the medical guideline and knowledge, thresholds are used for translating the sleep events into symbols and the sleep event’s threshold dependencies are analyzed for fully understand the thresholds dependencies among different sleep stages and subjects. Meanwhile, the differential evolution algorithm is adopted to automate the setting-up of thresholds that used in the symbolic fusion model and to provide personalized thresholds, which allows taking the individual variability into consideration. The robustness and clinical applicability of the proposed system are evaluated and demonstrated on a clinical dataset. The dataset is composed of 16 patients (9 males and 7 females) and scored by physicians. Only 5% of the dataset is used for the training process to obtain the personalized thresholds. Then these personalized thresholds are passed to the classification process, and the overall accuracy on the identification of five sleep stages reaches 80.09%. Using a small dataset for the training process, the proposed system not only drastically reduces the training set but also achieves favorable results compared to most of the existing works.