This page has only limited features, please log in for full access.
When processing sparse-spectrum biomedical signals, traditional time-frequency (TF) analysis methods are faced with the defects of blurry energy concentration and low TF resolution caused by the Heisenberg uncertainty principle. The synchrosqueezing-based methods have demonstrated advanced TF performances in recent studies. However, these methods contain at least three drawbacks: (1) existence of non-reassigned points (NRPs), (2) low noise robustness, and (3) low amplitude accuracy. In this study, the novel TF method, termed multi-synchrosqueezing extracting transform (MSSET), is proposed to address these limitations. The proposed MSSET is divided into three steps. First, multisynchrosqueezing transform (MSST) is performed with specific iterations. Second, a synch-extracting is applied to retain the TF distribution of MSST results that relate most to time-varying information of the raw signal; meanwhile, the other smeared TF energy is discarded. Finally, the MSSET result is obtained by rounding the adjacent results at the frequency plane. Numerical verification results show that the proposed MSSET method can effectively solve the NRPs problem and enhance noise robustness. Furthermore, while retaining superior energy concentration and signal reconstruction capability, the MSSET's amplitude accuracy reaches about 90%, significantly higher than other methods. In the same conditions, the MSSET even consumes less time than MSST and IMSST. It also achieves the best composite performance with the least amplitude accuracy-time cost ratio (ATCR) index. Actual application examples in the Bat signal and the electrocardiograph (ECG) signal also validate the excellent performances of our method. To conclude, our proposed MSSET is superior to state-of-the-art methods and is expected to be widely used in the sparse-spectrum biomedical signal.
Yalin Wang; Wei Zhou; Xian Zhao; Chen Chen; Wei Chen. MSSET: A high-performance time-frequency analysis method for sparse-spectrum biomedical signal. Computers in Biology and Medicine 2021, 135, 104637 .
AMA StyleYalin Wang, Wei Zhou, Xian Zhao, Chen Chen, Wei Chen. MSSET: A high-performance time-frequency analysis method for sparse-spectrum biomedical signal. Computers in Biology and Medicine. 2021; 135 ():104637.
Chicago/Turabian StyleYalin Wang; Wei Zhou; Xian Zhao; Chen Chen; Wei Chen. 2021. "MSSET: A high-performance time-frequency analysis method for sparse-spectrum biomedical signal." Computers in Biology and Medicine 135, no. : 104637.
With the increasing application of functional near-infrared spectroscopy (fNIRS) technology, topological brain network analysis has recently been developed and successfully applied in fNIRS-based brain research. However, the current network information is analyzed through the binary network, and it lacks a dynamic estimation. In this study, we proposed a novel dynamic weighted “small-world” topology network and applied it to fNIRS analysis. Firstly, we introduced a novel flat-top (FT) window to estimate sliding-window correlation (SWC), improving the spectrum performances. And then, we applied the least absolute shrinkage and selection operator (LASSO) algorithm to the time-varying correlation matrix and obtained corresponding sparse matrix results. Finally, we established a dynamic weighted topological graph and calculated “small-world” network parameters to analyze the brain network dynamics. Simulation results showed that our proposed FT-based SWC method realized wider bandwidth, better spectrum performance, and more accurate dynamic tracking capability with the minimum mean square errors(MSEs) results in each iterative simulation. The fNIRS results showed that the average node degree (DE) and global efficiency (GE) reached a peak in the middle and late periods of the task. The network parameters showed similar changes in 2-back and 3-back tasks, which differ from the 0-back task. Statistical analysis revealed the DE and GE of the subnetwork decreased as the task became more difficult. These results revealed the typical time-varying characteristics of the brain network dynamics during the working memory process, which were expected to unveil the brain mechanisms underlying the cognitive neural activity in greater depth.
Yalin Wang; Xian Zhao; Wei Zhou; Chen Chen; Wei Chen. Dynamic weighted “small-world” graphical network establishment for fNIRS time-varying brain function analysis. Biomedical Signal Processing and Control 2021, 69, 102902 .
AMA StyleYalin Wang, Xian Zhao, Wei Zhou, Chen Chen, Wei Chen. Dynamic weighted “small-world” graphical network establishment for fNIRS time-varying brain function analysis. Biomedical Signal Processing and Control. 2021; 69 ():102902.
Chicago/Turabian StyleYalin Wang; Xian Zhao; Wei Zhou; Chen Chen; Wei Chen. 2021. "Dynamic weighted “small-world” graphical network establishment for fNIRS time-varying brain function analysis." Biomedical Signal Processing and Control 69, no. : 102902.
The transformation procedure of deriving amplitude-integrated (a)EEG from raw EEG has been well described in a purely analog prototype, however the inherent specifications within the prototype are not established or disclosed. In this paper, we aim at providing an accessible and digitalized aEEG algorithm that is evaluated quantitatively and validated in clinical practice. The algorithms, especially the filter design and envelope detection methods, applied in the transformation procedure, are investigated. The effectiveness and feasibility of the filters namely, symmetric and asymmetric filters followed with four different envelope detection methods (low-pass filtering, squaring and low-pass filtering, Hilbert transform, and moving average) are evaluated on a clinical dataset collected at Children's Hospital of Fudan University which involves 30 infants. Compared to the outputs of the commercial available (a)EEG device NicoletOne, the Spearman rank correlations (SRs) of the upper/lower tracings of aEEG using the asymmetric filter and squaring and low-pass filtering-based envelope detection method can reach over 0.97. Meanwhile, the SRs of the upper and the lower margin amplitude of aEEG can achieve 0.98 and 0.97, respectively. Furthermore, the accuracy of the obtained aEEG tracings in identifying the aEEG background activities can achieve 100%. To our knowledge, this is the first work to present a digital procedure to transform the EEG into aEEG by assessing the impact of different filters and envelope detection methods. With the high performance of the proposed approach, this work can promote the standardization of aEEG transformation procedure and the exploration of the sophisticated automatic aEEG interpretation algorithms.
Chen Chen; Yan Xu; Zeyu Wang; Chenglu Sun; Xian Zhao; Jiahao Fan; Hendrik Niemarkt; Peter Andriessen; Laishuan Wang; Wei Chen. A digitized approach for amplitude-integrated electroencephalogram transformation towards a standardized procedure. Biomedical Signal Processing and Control 2021, 66, 102433 .
AMA StyleChen Chen, Yan Xu, Zeyu Wang, Chenglu Sun, Xian Zhao, Jiahao Fan, Hendrik Niemarkt, Peter Andriessen, Laishuan Wang, Wei Chen. A digitized approach for amplitude-integrated electroencephalogram transformation towards a standardized procedure. Biomedical Signal Processing and Control. 2021; 66 ():102433.
Chicago/Turabian StyleChen Chen; Yan Xu; Zeyu Wang; Chenglu Sun; Xian Zhao; Jiahao Fan; Hendrik Niemarkt; Peter Andriessen; Laishuan Wang; Wei Chen. 2021. "A digitized approach for amplitude-integrated electroencephalogram transformation towards a standardized procedure." Biomedical Signal Processing and Control 66, no. : 102433.
: K-complexes, as a significant indicator in sleep staging and sleep protection, are an important micro-event in sleep analysis. Clinically, K-complexes are recognized through the expert visual inspection of electroencephalogram (EEG) during sleep. Since this process is laborious and has high inter-observer variability, developing automated K-complex detection methods can alleviate the burden on clinicians while providing reliable recognition results. However, existing methods face the following issues. First, most work only identifies the K-complexes in stage 2, which requires distinguishing the sleep stages as the prerequisite for further events’ identification. Second, most approaches can only detect the occurrence of events without the ability to predict their location and duration, which are also essential to sleep analysis. : In this work, a novel hybrid expert scheme for K-complex detection is proposed by integrating signal morphology with expert knowledge into the decision-making process. To eliminate artifacts, and to minimize the individual variability in raw sleep EEG signals, the potential K-complex candidates are first screened by combining Teager energy operator (TEO) and personalized thresholds. Then, to distinguish signal shapes from background activity, a novel frame of filtering based on morphological filtering (MF) is devised to differentiate morphological components of K-complex waveforms from EEG series. Finally, K-complex waveforms are identified from the extracted morphological information by judgment rules, which are inspired by expert knowledge of micro-sleep events. : Detection performance is evaluated by its application on the public database MASS-C1 (Montreal archives of sleep studies cohort one) which includes the recordings of 19 healthy adults. The detection performance demonstrates an F-measure of 0.63 with a recall of 0.81 and a precision of 0.53 on average. The duration error between events and detections is 0.10 s. : The presented scheme has detected the occurrence of events. Meanwhile, it has recognized their locations and durations. The favorable results exhibit that the proposed scheme outperforms the state-of-the-art studies and has great potential to help release the burden of experts in sleep EEG analysis.
Xian Zhao; Chen Chen; Wei Zhou; Yalin Wang; Jiahao Fan; Zeyu Wang; Saeed Akbarzadeh; Wei Chen. An energy screening and morphology characterization-based hybrid expert scheme for automatic identification of micro-sleep event K-complex. Computer Methods and Programs in Biomedicine 2021, 201, 105955 .
AMA StyleXian Zhao, Chen Chen, Wei Zhou, Yalin Wang, Jiahao Fan, Zeyu Wang, Saeed Akbarzadeh, Wei Chen. An energy screening and morphology characterization-based hybrid expert scheme for automatic identification of micro-sleep event K-complex. Computer Methods and Programs in Biomedicine. 2021; 201 ():105955.
Chicago/Turabian StyleXian Zhao; Chen Chen; Wei Zhou; Yalin Wang; Jiahao Fan; Zeyu Wang; Saeed Akbarzadeh; Wei Chen. 2021. "An energy screening and morphology characterization-based hybrid expert scheme for automatic identification of micro-sleep event K-complex." Computer Methods and Programs in Biomedicine 201, no. : 105955.
Commonly used sensors like accelerometers, gyroscopes, surface electromyography sensors, etc., which provide a convenient and practical solution for human activity recognition (HAR), have gained extensive attention. However, which kind of sensor can provide adequate information in achieving a satisfactory performance, or whether the position of a single sensor would play a significant effect on the performance in HAR are sparsely studied. In this paper, a comparative study to fully investigate the performance of the aforementioned sensors for classifying four activities (walking, tooth brushing, face washing, drinking) is explored. Sensors are spatially distributed over the human body, and subjects are categorized into three groups (able-bodied people, stroke survivors, and the union of both). Performances of using accelerometer, gyroscope, sEMG, and their combination in each group are evaluated by adopting the Support Vector Machine classifier with the Leave-One-Subject-Out Cross-Validation technique, and the optimal sensor position for each kind of sensor is presented based on the accuracy. Experimental results show that using the accelerometer could obtain the best performance in each group. The highest accuracy of HAR involving stroke survivors was 95.84 ± 1.75% (mean ± standard error), achieved by the accelerometer attached to the extensor carpi ulnaris. Furthermore, taking the practical application of HAR into consideration, a novel approach to distinguish various activities of stroke survivors based on a pre-trained HAR model built on healthy subjects is proposed, the highest accuracy of which is 77.89 ± 4.81% (mean ± standard error) with the accelerometer attached to the extensor carpi ulnaris.
Long Meng; Anjing Zhang; Chen Chen; Xingwei Wang; Xinyu Jiang; Linkai Tao; Jiahao Fan; Xuejiao Wu; Chenyun Dai; Yiyuan Zhang; Bart Vanrumste; Toshiyo Tamura; Wei Chen. Exploration of Human Activity Recognition Using a Single Sensor for Stroke Survivors and Able-Bodied People. Sensors 2021, 21, 799 .
AMA StyleLong Meng, Anjing Zhang, Chen Chen, Xingwei Wang, Xinyu Jiang, Linkai Tao, Jiahao Fan, Xuejiao Wu, Chenyun Dai, Yiyuan Zhang, Bart Vanrumste, Toshiyo Tamura, Wei Chen. Exploration of Human Activity Recognition Using a Single Sensor for Stroke Survivors and Able-Bodied People. Sensors. 2021; 21 (3):799.
Chicago/Turabian StyleLong Meng; Anjing Zhang; Chen Chen; Xingwei Wang; Xinyu Jiang; Linkai Tao; Jiahao Fan; Xuejiao Wu; Chenyun Dai; Yiyuan Zhang; Bart Vanrumste; Toshiyo Tamura; Wei Chen. 2021. "Exploration of Human Activity Recognition Using a Single Sensor for Stroke Survivors and Able-Bodied People." Sensors 21, no. 3: 799.
Sleep posture, as a crucial index for sleep quality assessment, has been widely studied in sleep analysis. In this paper, an unobtrusive smart mat system based on a dense flexible sensor array and printed electrodes along with an algorithmic framework for sleep posture recognition is proposed. With the dense flexible sensor array, the system offers a comfortable and high-resolution solution for long-term pressure sensing. Meanwhile, compared to other methods, it reduces production costs and computational complexity with a smaller area of the mat and improves portability with fewer sensors. To distinguish the sleep posture, the algorithmic framework that includes pre-processing and Deep Residual Networks (ResNet) is developed. With the ResNet, the proposed system can omit the complex hand-crafted feature extraction process and provide compelling performance. The feasibility and reliability of the proposed system were evaluated on seventeen subjects. Experimental results exhibit that the accuracy of the short-term test is up to 95.08% and the overnight sleep study is up to 92.99% for four categories (supine, prone, right, and left) classification, which outperform the most of state-of-the-art studies. With the promising results, the proposed system showed great potential in applications like sleep studies, the prevention of pressure ulcers, etc.
Haikang Diao; Chen Chen; Wei Yuan; Amara Amara; Toshiyo Tamura; Jiahao Fan; Long Meng; Xiangyu Liu; Wei Chen. Deep Residual Networks for Sleep Posture Recognition With Unobtrusive Miniature Scale Smart Mat System. IEEE Transactions on Biomedical Circuits and Systems 2021, 15, 111 -121.
AMA StyleHaikang Diao, Chen Chen, Wei Yuan, Amara Amara, Toshiyo Tamura, Jiahao Fan, Long Meng, Xiangyu Liu, Wei Chen. Deep Residual Networks for Sleep Posture Recognition With Unobtrusive Miniature Scale Smart Mat System. IEEE Transactions on Biomedical Circuits and Systems. 2021; 15 (1):111-121.
Chicago/Turabian StyleHaikang Diao; Chen Chen; Wei Yuan; Amara Amara; Toshiyo Tamura; Jiahao Fan; Long Meng; Xiangyu Liu; Wei Chen. 2021. "Deep Residual Networks for Sleep Posture Recognition With Unobtrusive Miniature Scale Smart Mat System." IEEE Transactions on Biomedical Circuits and Systems 15, no. 1: 111-121.
Objective: Classification of sleep-wake states using multichannel electroencephalography (EEG) data that reliably work for neonates. Methods: A deep multilayer perceptron (MLP) neural network is developed to classify sleep-wake states using multichannel bipolar EEG signals, which takes an input vector of size 108 containing the joint features of 9 channels. The network avoids any post-processing step in order to work as a full-fledged real-time application. For training and testing the model, EEG recordings of 3525 30-second segments from 19 neonates (postmenstrual age of 37 ± 05 weeks) are used. Results: For sleep-wake classification, mean Cohen’s kappa between the network estimate and the ground truth annotation by human experts is 0.62. The maximum mean accuracy can reach up to 83% which, to date, is the highest accuracy for sleep-wake classification.
Saadullah Farooq Abbasi; Jawad Ahmad; Ahsen Tahir; Muhammad Awais; Chen Chen; Muhammad Irfan; Hafiza Ayesha Siddiqa; Abu Bakar Waqas; Xi Long; Bin Yin; Saeed Akbarzadeh; Chunmei Lu; Laishuan Wang; Wei Chen. EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network. IEEE Access 2020, 8, 183025 -183034.
AMA StyleSaadullah Farooq Abbasi, Jawad Ahmad, Ahsen Tahir, Muhammad Awais, Chen Chen, Muhammad Irfan, Hafiza Ayesha Siddiqa, Abu Bakar Waqas, Xi Long, Bin Yin, Saeed Akbarzadeh, Chunmei Lu, Laishuan Wang, Wei Chen. EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network. IEEE Access. 2020; 8 ():183025-183034.
Chicago/Turabian StyleSaadullah Farooq Abbasi; Jawad Ahmad; Ahsen Tahir; Muhammad Awais; Chen Chen; Muhammad Irfan; Hafiza Ayesha Siddiqa; Abu Bakar Waqas; Xi Long; Bin Yin; Saeed Akbarzadeh; Chunmei Lu; Laishuan Wang; Wei Chen. 2020. "EEG-Based Neonatal Sleep-Wake Classification Using Multilayer Perceptron Neural Network." IEEE Access 8, no. : 183025-183034.
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. 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. 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. 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.
Jiahao Fan; Chenglu Sun; Chen Chen; Xinyu Jiang; Xiangyu Liu; Xian Zhao; Long Meng; Chenyun Dai; Wei Chen. EEG data augmentation: Towards class imbalance problem in sleep staging tasks. Journal of Neural Engineering 2020, 17, 056017 .
AMA StyleJiahao Fan, Chenglu Sun, Chen Chen, Xinyu Jiang, Xiangyu Liu, Xian Zhao, Long Meng, Chenyun Dai, Wei Chen. EEG data augmentation: Towards class imbalance problem in sleep staging tasks. Journal of Neural Engineering. 2020; 17 (5):056017.
Chicago/Turabian StyleJiahao Fan; Chenglu Sun; Chen Chen; Xinyu Jiang; Xiangyu Liu; Xian Zhao; Long Meng; Chenyun Dai; Wei Chen. 2020. "EEG data augmentation: Towards class imbalance problem in sleep staging tasks." Journal of Neural Engineering 17, no. 5: 056017.
Objective. Electrical status epilepticus during sleep (ESES), as electroencephalographic disturbances, is characterized by strong activation of epileptiform activity in the electroencephalogram (EEG) during sleep. Quantitative descriptors of such epileptiform activity can support the diagnose and the prognosis of children with ESES. To quantify the epileptiform activity of ESES, a knowledge-based approach to mimic the clinical decision-making process is proposed. Approach. Firstly, a morphological operations-based scheme is designed to quickly locate the positive peaks/negative pits and roughly estimate the onset/offset of spike and slow-wave abnormalities. Then, to provide the accurate duration of ESES patterns, a set of rules for further adjusting these onsets/offsets are proposed by merging medical knowledge with a generalized threshold obtained from statistics. As such, the quantification is accomplished by evaluating the obtained spike and slow-wave abnormalities and their various durations. Main results. The effectiveness and feasibility of the proposed method were evaluated on a clinical dataset that collected at Children's Hospital of Fudan University, Shanghai, China. We demonstrate that the proposed method can recognize different types of spike and slow-wave abnormalities. The sensitivity, precision, and false positive rate achieved 91.96%, 97.09%, and 1.88/min, respectively. The estimation error for the spike-wave index was 2.32%. Comparison results showed that our method outperforms the state-of-the-art. Significance. The quantification of spike and slow-waves provides information about ESES activity. The detection of variations types of spike and slow-waves improves the performance in the quantification of ESES. Experimental results suggest that the proposed method has great potential in automatic ESES quantification and can help improve the diagnosis and researches of epileptic encephalopathy with ESES.
Xian Zhao; Xinhua Wang; Chen Chen; Jiahao Fan; Xilin Yu; Zeyu Wang; Saeed Akbarzadeh; Qiang Li; Shuizhen Zhou; Wei Chen. A knowledge-based approach for automatic quantification of epileptiform activity in children with electrical status epilepticus during sleep. Journal of Neural Engineering 2020, 17, 046032 .
AMA StyleXian Zhao, Xinhua Wang, Chen Chen, Jiahao Fan, Xilin Yu, Zeyu Wang, Saeed Akbarzadeh, Qiang Li, Shuizhen Zhou, Wei Chen. A knowledge-based approach for automatic quantification of epileptiform activity in children with electrical status epilepticus during sleep. Journal of Neural Engineering. 2020; 17 (4):046032.
Chicago/Turabian StyleXian Zhao; Xinhua Wang; Chen Chen; Jiahao Fan; Xilin Yu; Zeyu Wang; Saeed Akbarzadeh; Qiang Li; Shuizhen Zhou; Wei Chen. 2020. "A knowledge-based approach for automatic quantification of epileptiform activity in children with electrical status epilepticus during sleep." Journal of Neural Engineering 17, no. 4: 046032.
In recent times, with the advancement of digital imaging, automatic facial recognition has been intensively studied for adults, while less for neonates. Due to the miniature facial structure and facial attributes, newborn facial recognition remains a challenging area. In this paper, an automatic video-based Neonatal Face Attributes Recognition (NFAR) approach in a hierarchical framework is proposed by coalescing the intensity-based method, pose estimation, and novel dedicated neonatal Face Feature Selection (FFS) algorithm. The intensity-based method is used for face detection, followed by the facial pose estimation algorithm and FFS are dedicated to neonatal pose and face feature recognition, respectively. In this study, video-data of 19 neonates’ were collected from the Children’s Hospital affiliated to Fudan University, Shanghai, to evaluate the proposed NFAR approach. The results show promising performance to detect the neonatal face, pose estimation (-450, 450), and facial features (nose, mouth, and eyes) recognition. The NFAR approach exhibits a sensitivity, accuracy, and specificity of 98.7%, 98.5%, and, 95.7% respectively, for the newborn babies at the frontal (00) facial region. The neonatal face and its attributes recognition can be expected to detect neonate’s medical abnormalities unobtrusively by examining the variation in newborn facial texture pattern.
Muhammad Awais; Chen Chen; Xi Long; Bin Yin; Anum Nawaz; Saadullah Farooq Abbasi; Saeed Akbarzadeh; Linkai Tao; Chunmei Lu; Laishuan Wang; Ronald M. Aarts; Wei Chen. Novel Framework: Face Feature Selection Algorithm for Neonatal Facial and Related Attributes Recognition. IEEE Access 2020, 8, 59100 -59113.
AMA StyleMuhammad Awais, Chen Chen, Xi Long, Bin Yin, Anum Nawaz, Saadullah Farooq Abbasi, Saeed Akbarzadeh, Linkai Tao, Chunmei Lu, Laishuan Wang, Ronald M. Aarts, Wei Chen. Novel Framework: Face Feature Selection Algorithm for Neonatal Facial and Related Attributes Recognition. IEEE Access. 2020; 8 (99):59100-59113.
Chicago/Turabian StyleMuhammad Awais; Chen Chen; Xi Long; Bin Yin; Anum Nawaz; Saadullah Farooq Abbasi; Saeed Akbarzadeh; Linkai Tao; Chunmei Lu; Laishuan Wang; Ronald M. Aarts; Wei Chen. 2020. "Novel Framework: Face Feature Selection Algorithm for Neonatal Facial and Related Attributes Recognition." IEEE Access 8, no. 99: 59100-59113.
To characterize the irregularity of the spectrum of a signal, spectral entropy and its variants are widely adopted measures. However, spectral entropy is invariant under the permutation of the power spectrum estimations on a predefined grid. This erases the inherent order structure in the spectrum. To disentangle the order structure and extract meaningful information from raw digital signal, a novel analysis method is necessary. In this paper, we tried to unfold this order structure by defining descriptors mapping real- and vector-valued power spectrum estimation of a signal into a scalar value. The proposed descriptors showed its potential in diverse problems. Significant differences were observed from brain signals and surface electromyography of different pathological/physiological states. Drastic change accompanied by the alteration of the underlying process of signals enables it as a candidate feature for seizure detection and endpoint detection in speech signal. Since the order structure in the spectrum of physiological signal carries previously ignored information, which cannot be properly extracted by existing techniques, this paper takes one step forward along this direction by proposing computationally efficient descriptors with guaranteed information gain. To the best of our knowledge, this is the first work revealing the effectiveness of the order structure in the spectrum in physiological signal processing.
Xilin Yu; Zhenning Mei; Chen Chen; Wei Chen. Ranking Power Spectra: A Proof of Concept. Entropy 2019, 21, 1057 .
AMA StyleXilin Yu, Zhenning Mei, Chen Chen, Wei Chen. Ranking Power Spectra: A Proof of Concept. Entropy. 2019; 21 (11):1057.
Chicago/Turabian StyleXilin Yu; Zhenning Mei; Chen Chen; Wei Chen. 2019. "Ranking Power Spectra: A Proof of Concept." Entropy 21, no. 11: 1057.
Currently, the automatic sleep staging methods mainly face two problems: the first problem is that although the algorithms which use electroencephalogram (EEG) signals have nice performance, acquiring EEG signals is complicated and uncomfortable; the second one 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. 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. 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. 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.
Chenglu Sun; Chen Chen; Jiahao Fan; Wei Li; Yuanting Zhang; Wei Chen. A hierarchical sequential neural network with feature fusion for sleep staging based on EOG and RR signals. Journal of Neural Engineering 2019, 16, 066020 .
AMA StyleChenglu Sun, Chen Chen, Jiahao Fan, Wei Li, Yuanting Zhang, Wei Chen. A hierarchical sequential neural network with feature fusion for sleep staging based on EOG and RR signals. Journal of Neural Engineering. 2019; 16 (6):066020.
Chicago/Turabian StyleChenglu Sun; Chen Chen; Jiahao Fan; Wei Li; Yuanting Zhang; Wei Chen. 2019. "A hierarchical sequential neural network with feature fusion for sleep staging based on EOG and RR signals." Journal of Neural Engineering 16, no. 6: 066020.
Shubao Yin; Chen Chen; Hangyu Zhu; Xinping Wang; Wei Chen. Neural Networks for Pathological Gait Classification Using Wearable Motion Sensors. 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS) 2019, 1 .
AMA StyleShubao Yin, Chen Chen, Hangyu Zhu, Xinping Wang, Wei Chen. Neural Networks for Pathological Gait Classification Using Wearable Motion Sensors. 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS). 2019; ():1.
Chicago/Turabian StyleShubao Yin; Chen Chen; Hangyu Zhu; Xinping Wang; Wei Chen. 2019. "Neural Networks for Pathological Gait Classification Using Wearable Motion Sensors." 2019 IEEE Biomedical Circuits and Systems Conference (BioCAS) , no. : 1.
Amplitude-integrated electroencephalography (aEEG) is a simplified method for long-term, continuous, and bedside monitoring of brain activity. While conventional Electroencephalography (EEG) is the gold standard of assessing brain function, aEEG is easy to operate and allows bedside interpretation of brain activity by health care providers without extensive knowledge of neurophysiology. aEEG is increasingly applied in neurological monitoring in neonates, especially in the neonatal intensive care unit (NICU). To a growing extent, researchers and clinicians are convinced that aEEG provides valuable clinical information and can be used to assess the severity of neonatal encephalopathy. Meanwhile, to digitalize the aEEG transformation process and automate the interpretation process, different algorithms have been proposed in the last decades. This paper provides a comprehensive review of aEEG for neonatal monitoring from both clinical and technological perspectives. The paper first reviews the clinical applications of aEEG and discusses the merits and demerits of neonatal aEEG monitoring in terms of the assistance of the treatment and prognosis of cerebral diseases like hypoxic-ischemic encephalopathy (HIE), seizure and so on. And then furthermore, the algorithms to transform EEG into aEEG and the algorithms for aEEG interpretation like the automatic classification of aEEG tracing, automatic seizure detection of aEEG, etc. are reviewed.
Chen Chen; Chenglu Sun; Steffen Leonhardt; Peter Andriessen; Hendrik Niemarkt; Wei Chen. Amplitude-Integrated Electroencephalography Applications and Algorithms in Neonates: A Systematic Review. IEEE Access 2019, 7, 141766 -141781.
AMA StyleChen Chen, Chenglu Sun, Steffen Leonhardt, Peter Andriessen, Hendrik Niemarkt, Wei Chen. Amplitude-Integrated Electroencephalography Applications and Algorithms in Neonates: A Systematic Review. IEEE Access. 2019; 7 (99):141766-141781.
Chicago/Turabian StyleChen Chen; Chenglu Sun; Steffen Leonhardt; Peter Andriessen; Hendrik Niemarkt; Wei Chen. 2019. "Amplitude-Integrated Electroencephalography Applications and Algorithms in Neonates: A Systematic Review." IEEE Access 7, no. 99: 141766-141781.
In this paper, an unconstrained cardiac monitoring system with a novel dual tripolar concentric ring (D-TCR) geometry-based flexible active ECG electrodes is presented. The D-TCR ECG electrode, which based on the conductive flexible and stretchable Ag NWs/PDMS composite material, is designed to acquire the high-fidelity electrocardiographic potentials. The proposed system overcomes the constraints of the conventional ECG monitoring device, and provide the superiorities in far-field rejection, power line interference attenuation, driven right leg-release, etc. The effectiveness and feasibility of the proposed system were evaluated on a dataset that involves 16 subjects with different clothing materials and sleep postures. The average Pearson correlation coefficient of the heart rate variability (HRV) that extracted from the ECG signals obtained by the proposed system and the commercial device can reach over 0.95 with different clothes and postures. Furthermore, to give the quantitative analysis of the ECG, the error rates of time-domain and frequency-domain features extracted from the ECG signal are measured, which are less than 3%. Experimental results exhibit that the proposed system can achieve favorable signal quality and satisfy the basic requirements of the cardiorespiratory monitoring during sleep. Furthermore, the proposed system is expected to provide valuable information for sleep health surveillance, e.g., detecting cardiac abnormalities.
Zeyu Wang; Chen Chen; Linkai Tao; Xian Zhao; Wei Yuan; Wei Chen. An Unconstrained Cardiac Monitoring System With Novel Dual Tripolar Concentric Ring Geometry-Based Flexible Active ECG Electrodes for Sleep Health Surveillance. IEEE Access 2019, 7, 142176 -142189.
AMA StyleZeyu Wang, Chen Chen, Linkai Tao, Xian Zhao, Wei Yuan, Wei Chen. An Unconstrained Cardiac Monitoring System With Novel Dual Tripolar Concentric Ring Geometry-Based Flexible Active ECG Electrodes for Sleep Health Surveillance. IEEE Access. 2019; 7 (99):142176-142189.
Chicago/Turabian StyleZeyu Wang; Chen Chen; Linkai Tao; Xian Zhao; Wei Yuan; Wei Chen. 2019. "An Unconstrained Cardiac Monitoring System With Novel Dual Tripolar Concentric Ring Geometry-Based Flexible Active ECG Electrodes for Sleep Health Surveillance." IEEE Access 7, no. 99: 142176-142189.
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.
Chenglu Sun; Chen Chen; Wei Li; Jiahao Fan; Wei Chen. A Hierarchical Neural Network for Sleep Stage Classification Based on Comprehensive Feature Learning and Multi-Flow Sequence Learning. IEEE Journal of Biomedical and Health Informatics 2019, 24, 1351 -1366.
AMA StyleChenglu Sun, Chen Chen, Wei Li, Jiahao Fan, Wei Chen. A Hierarchical Neural Network for Sleep Stage Classification Based on Comprehensive Feature Learning and Multi-Flow Sequence Learning. IEEE Journal of Biomedical and Health Informatics. 2019; 24 (5):1351-1366.
Chicago/Turabian StyleChenglu Sun; Chen Chen; Wei Li; Jiahao Fan; Wei Chen. 2019. "A Hierarchical Neural Network for Sleep Stage Classification Based on Comprehensive Feature Learning and Multi-Flow Sequence Learning." IEEE Journal of Biomedical and Health Informatics 24, no. 5: 1351-1366.
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.
Chenglu Sun; Jiahao Fan; Chen Chen; Wei Li; Wei Chen. A Two-Stage Neural Network for Sleep Stage Classification Based on Feature Learning, Sequence Learning, and Data Augmentation. IEEE Access 2019, 7, 109386 -109397.
AMA StyleChenglu Sun, Jiahao Fan, Chen Chen, Wei Li, Wei Chen. A Two-Stage Neural Network for Sleep Stage Classification Based on Feature Learning, Sequence Learning, and Data Augmentation. IEEE Access. 2019; 7 ():109386-109397.
Chicago/Turabian StyleChenglu Sun; Jiahao Fan; Chen Chen; Wei Li; Wei Chen. 2019. "A Two-Stage Neural Network for Sleep Stage Classification Based on Feature Learning, Sequence Learning, and Data Augmentation." IEEE Access 7, no. : 109386-109397.
In this paper, an unconstrained cardiorespiratory system for monitoring of ECG and respiration during sleep is presented. A novel active dry ECG electrode, which based on the conductive flexible and stretchable Ag NWs/PDMS composite material is designed to acquire the electrocardiographic potentials through the cloth. Meanwhile, a membrane pressure sensor is applied to obtain the respiratory signal, which can avoid the intervention in the sleep process. Combining the novel active ECG electrode and the membrane pressure sensor, the followed signal acquisition circuit is designed to monitor the ECG and respiratory signals simultaneously without fixing any external sensor to the human body. To verify the performance of the proposed system, a comprehensive test protocol is presented. Firstly, we characterized the electrical properties and the signal sensing capability of the proposed sensor. Furthermore, the performance of the entire system is assessed to verify the effects caused by different clothing materials and sleep postures to the ECG signal and the respiratory signal acquisition. The average Pearson correlation coefficient of the RR interval that extracted from the ECG signal obtained by the proposed system and the commercial PSG device can reach over 0.9 of different clothes and postures. As for the respiration acquisition, the accuracy of the respiration rate in different postures can reach 95% during the 2 hours monitoring process. The experimental results are promising, which demonstrate that the proposed system can achieve favorable signal quality and satisfy the basic requirements of the cardiorespiratory monitoring during sleep. Moreover, the proposed system can be extended to the office environment to monitor the health status of the individual.
Zeyu Wang; Chen Chen; Linkai Tao; Wei Yuan; Wei Li; Chenglu Sun; Wei Chen. Novel Active ECG Electrode and Membrane Pressure Sensor-based Unconstrained Cardiorespiratory System for Sleep Monitoring. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2019, 2019, 6705 -6709.
AMA StyleZeyu Wang, Chen Chen, Linkai Tao, Wei Yuan, Wei Li, Chenglu Sun, Wei Chen. Novel Active ECG Electrode and Membrane Pressure Sensor-based Unconstrained Cardiorespiratory System for Sleep Monitoring. 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2019; 2019 ():6705-6709.
Chicago/Turabian StyleZeyu Wang; Chen Chen; Linkai Tao; Wei Yuan; Wei Li; Chenglu Sun; Wei Chen. 2019. "Novel Active ECG Electrode and Membrane Pressure Sensor-based Unconstrained Cardiorespiratory System for Sleep Monitoring." 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2019, no. : 6705-6709.
Stroke is a leading cause of mortality and disability, which can be affected by people's daily living habits. To investigate the effects of main daily living habits (smoking, drinking, diet, vegetable and fruits consumption, and exercise) on stroke risk in patients and provide the scientific basis for the assessment of the risk factors, a novel risk analysis model of the stroke is proposed. A data mining method using decision trees which adopted the optimized C4.5 algorithm is presented. It is able to deal with the unbalanced data problem of the classification. Meanwhile, the proposed method has been verified on a clinical dataset of 23,682 patients with 21 risk factors. The overall accuracy and kappa coefficient for stroke risk classification has reached 84.88% and 0.7763, respectively. Through the generated knowledge rules, it demonstrates that the behavioral habits in daily life have an indirect effect on the risk of stroke. While, it has an obvious effect on stroke when hypertension, diabetes mellitus, hypercholesterolemia, and BMI risk factors exist. In addition, it was observed that the aforementioned five daily living habits have a decreased impact on the stroke. It is anticipated that the proposed system could help in reducing the risk, mortality, and disability of stroke, and provide clinical decision support for the treatment of stroke.
Zeguo Shao; Chen Chen; Wei Li; Haoran Ren; Wei Chen. Assessment of the risk factors in the daily life of stroke patients based on an optimized decision tree. Technology and Health Care 2019, 27, 317 -329.
AMA StyleZeguo Shao, Chen Chen, Wei Li, Haoran Ren, Wei Chen. Assessment of the risk factors in the daily life of stroke patients based on an optimized decision tree. Technology and Health Care. 2019; 27 (Preprint):317-329.
Chicago/Turabian StyleZeguo Shao; Chen Chen; Wei Li; Haoran Ren; Wei Chen. 2019. "Assessment of the risk factors in the daily life of stroke patients based on an optimized decision tree." Technology and Health Care 27, no. Preprint: 317-329.
Automatic seizure detection has been often treated as a classification problem that aims at determining the label of electroencephalogram (EEG) signals by computer science, as EEG monitoring is a helpful adjunct to the diagnosis of epilepsy. In most existing work, the traditional signal energy of EEG has been applied for classification, since the energy pattern of epileptic seizures differs from that of nonseizures. Although they are effective, the accuracy either heavily depends on additional information besides energy or is limited by the shortcoming of energy-based features. To address this issue, the proposed approach achieves the classification based on the instantaneous energy of EEG signals instead. The proposed approach first measures the instantaneous energy related to changes in EEG signals. Then the energy behavior over time is characterized by instantaneous energy-based features from different aspects. Finally, the classification is carried out on the features to produce output labels. By processing instantaneous energy, the information of energy evolution is involved. As such, the accuracy is improved without bringing in extra information besides energy, or complicated transformation. In multi-class problems, the proposed approach has obtained promising results for identifying ictal EEG, which indicates the tremendous potential of the proposed approach for epileptic seizure detection.
Xian Zhao; Renjie Zhang; Zhenning Mei; Chen Chen; Wei Chen. Identification of Epileptic Seizures by Characterizing Instantaneous Energy Behavior of EEG. IEEE Access 2019, 7, 70059 -70076.
AMA StyleXian Zhao, Renjie Zhang, Zhenning Mei, Chen Chen, Wei Chen. Identification of Epileptic Seizures by Characterizing Instantaneous Energy Behavior of EEG. IEEE Access. 2019; 7 (99):70059-70076.
Chicago/Turabian StyleXian Zhao; Renjie Zhang; Zhenning Mei; Chen Chen; Wei Chen. 2019. "Identification of Epileptic Seizures by Characterizing Instantaneous Energy Behavior of EEG." IEEE Access 7, no. 99: 70059-70076.