The electroencephalogram (EEG), for measuring the electrophysiological activity of the brain, has been widely applied in automatic detection of epilepsy seizures. Various EEG-based seizure detection ...algorithms have already yielded high sensitivity, but training those algorithms requires a large amount of labelled data. Data labelling is often done with a lot of human efforts, which is very time-consuming. In this study, we propose a hybrid system integrating an unsupervised learning (UL) module and a supervised learning (SL) module, where the UL module can significantly reduce the workload of data labelling. For preliminary seizure screening, UL synthesizes amplitude-integrated EEG (aEEG) extraction, isolation forest-based anomaly detection, adaptive segmentation, and silhouette coefficient-based anomaly detection evaluation. The UL module serves to quickly locate the determinate subjects (seizure segments and seizure-free segments) and the indeterminate subjects (potential seizure candidates). Afterwards, more robust seizure detection for the indeterminate subjects is performed by the SL using an EasyEnsemble algorithm. EasyEnsemble, as a class-imbalance learning method, can potentially decrease the generalization error of the seizure-free segments. The proposed method can significantly reduce the workload of data labelling while guaranteeing satisfactory performance. The proposed seizure detection system is evaluated using the Children's Hospital Boston - Massachusetts Institute of Technology (CHB-MIT) scalp EEG dataset, and it achieves a mean accuracy of 92.62%, a mean sensitivity of 95.55%, and a mean specificity of 92.57%. To the best of our knowledge, this is the first epilepsy seizure detection study employing the integration of both the UL and the SL modules, achieving a competitive performance superior or similar to that of the state-of-the-art methods.
The increased prevalence of chronic disease in aging population entails health risks and imposes significant economic and social burden. It is essential to provide comfortable, cost-effective, and ...easy-to-use unobtrusive and wearable systems for personal well-being and healthcare. Novel flexible material-based non-invasive and wearable sensors offer an efficient and cost-effective solution, which enables the continuous and real-time monitoring of important physiological signs of the human beings, the assessment of personal health conditions and that provides feedback from remote and home monitoring. In this paper, novel flexible material-based wearable sensors, devised into body sensor networks to capture and monitor vital bio-signals, including electroencephalography (EEG), electrocardiography (ECG) and respiratory, are proposed. Silver nanowires (Ag NWs) and polydimethylsiloxane composite material, carbon foam, and graphene-based fiber are used to sense the EEG, ECG, and respiratory, respectively. With different flexible materials, the smart hat and smart jacket are designed to affix the sensors, which enable long-term health monitoring of vital signals seamlessly. Meanwhile, the corresponding acquisition circuits are developed and mounted with the proposed electrodes on the garments. More importantly, a comprehensive protocol is designed to validate the performance of the proposed system, while some standard sensors and commercial devices are used for comparison. The evaluation results demonstrate the proposed system represents a comparable performance with the existing system. In summary, the proposed sensing system offers an unobtrusive, detachable, expandable, user-friendly, and comfortable solution for physiological signal monitoring. It can be expected to use for the remote healthcare monitoring and provide personalized information of health, fitness, and diseases.
Elimination of intra-artifacts in EEG has been overlooked in most of the existing sleep staging systems, especially in deep learning-based approaches. Whether intra-artifacts, originated from the eye ...movement, chin muscle firing, or heart beating, etc., in EEG signals would lead to a positive or a negative masking effect on deep learning-based sleep staging systems was investigated in this paper. We systematically analyzed several traditional pre-processing methods involving fast Independent Component Analysis (FastICA), Information Maximization (Infomax), and Second-order Blind Source Separation (SOBI). On top of these methods, a SOBI-WT method based on the joint use of the SOBI and Wavelet Transform (WT) is proposed. It offered an effective solution for suppressing artifact components while retaining residual informative data. To provide a comprehensive comparative analysis, these pre-processing methods were applied to eliminate the intra-artifacts and the processed signals were fed to two ready-to-use deep learning models, namely two-step hierarchical neural network (THNN) and SimpleSleepNet for automatic sleep staging. The evaluation was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDF Expanded, and a clinical dataset that was collected in Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed SOBI-WT method increased the accuracy from 79.0% to 81.3% on MASS, 83.3% to 85.7% on Sleep-EDF Expanded, and 75.5% to 77.1% on HSFU compared with the raw EEG signal, respectively. Experimental results demonstrate that the intra-artifacts bring out a masking negative impact on the deep learning-based sleep staging systems and the proposed SOBI-WT method has the best performance in diminishing this negative impact compared with other artifact elimination methods.
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.
Gaze estimation, as a technique that reflects individual attention, can be used for disability assistance and assisting physicians in diagnosing diseases such as autism spectrum disorder (ASD), ...Parkinson's disease, and attention deficit hyperactivity disorder (ADHD). Various techniques have been proposed for gaze estimation and achieved high resolution. Among these approaches, electrooculography (EOG)-based gaze estimation, as an economical and effective method, offers a promising solution for practical applications. Objective: In this paper, we systematically investigated the possible EOG electrode locations which are spatially distributed around the orbital cavity. Afterward, quantities of informative features to characterize physiological information of eye movement from the temporal-spectral domain are extracted from the seven differential channels. Methods and procedures: To select the optimum channels and relevant features, and eliminate irrelevant information, a heuristical search algorithm (i.e., forward stepwise strategy) is applied. Subsequently, a comparative analysis of the impacts of electrode placement and feature contributions on gaze estimation is evaluated via 6 classic models with 18 subjects. Results: Experimental results showed that the promising performance was achieved both in the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) within a wide gaze that ranges from −50° to +50°. The MAE and RMSE can be improved to 2.80° and 3.74° ultimately, while only using 10 features extracted from 2 channels. Compared with the prevailing EOG-based techniques, the performance improvement of MAE and RMSE range from 0.70° to 5.48° and 0.66° to 5.42°, respectively. Conclusion: We proposed a robust EOG-based gaze estimation approach by systematically investigating the optimal channel/feature combination. The experimental results indicated not only the superiority of the proposed approach but also its potential for clinical application. Clinical and translational impact statement: Accurate gaze estimation is a key step for assisting disabilities and accurate diagnosis of various diseases including ASD, Parkinson's disease, and ADHD. The proposed approach can accurately estimate the points of gaze via EOG signals, and thus has the potential for various related medical applications.
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 (-45°, 45°), 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 (0°) 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.
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.
Recently, Electrooculography-based Human-Computer Interaction (EOG-HCI) technology has gained widespread attention in industrial areas, including assistive robots, augmented reality in gaming, etc. ...However, as the fundamental step of EOG-HCI, accurate eye movement classification (EMC) still faces a significant challenge, where their constraints in extracting discriminative features limit the performance of most existing works. To address this issue, a Residual Self-Calibrated Network with Multi-Scale Channel Attention (RSCA), focusing on efficient feature extraction and enhancement is proposed. The RSCA network first employs three self-calibrated convolution blocks within a hierarchical residual framework to fully extract the discriminative multi-scale features. Then, a multi-scale channel attention module adaptively weights the learned features to screen out the discriminative representation by aggregating the multi-scale context information along the channel dimension, thus further boosting the performance. Comprehensive experiments were performed using 5 public datasets and 7 prevailing methods for comparative validation. The results confirm that the RSCA network outperforms all other methods significantly, establishing a state-of-the-art benchmark for EOG-based EMC. Furthermore, thorough ablation analyses confirm the effectiveness of the employed modules within the RSCA network, providing valuable insights for the design of EOG-based deep models.Recently, Electrooculography-based Human-Computer Interaction (EOG-HCI) technology has gained widespread attention in industrial areas, including assistive robots, augmented reality in gaming, etc. However, as the fundamental step of EOG-HCI, accurate eye movement classification (EMC) still faces a significant challenge, where their constraints in extracting discriminative features limit the performance of most existing works. To address this issue, a Residual Self-Calibrated Network with Multi-Scale Channel Attention (RSCA), focusing on efficient feature extraction and enhancement is proposed. The RSCA network first employs three self-calibrated convolution blocks within a hierarchical residual framework to fully extract the discriminative multi-scale features. Then, a multi-scale channel attention module adaptively weights the learned features to screen out the discriminative representation by aggregating the multi-scale context information along the channel dimension, thus further boosting the performance. Comprehensive experiments were performed using 5 public datasets and 7 prevailing methods for comparative validation. The results confirm that the RSCA network outperforms all other methods significantly, establishing a state-of-the-art benchmark for EOG-based EMC. Furthermore, thorough ablation analyses confirm the effectiveness of the employed modules within the RSCA network, providing valuable insights for the design of EOG-based deep models.
Gaze estimation based on electrooculograms (EOGs) has been widely explored. However, the inter-subject variability of EOGs still leaves a significant challenge for practical applications. It ...contributes to performance degradation when handling inter-subject issues. In this paper, an unsupervised transfer learning approach with an adaptive reweighting and resampling (ARR) strategy to fully consider individual variability is proposed for EOG-based gaze angle estimation. It allows quantifying domain shifts by leveraging the source-target similarities, reweighting and resampling the source data to retain relevant instances and disregard irrelevant instances during adaptation. Specifically, our proposed methodology first assesses the domain shifts via decomposing transformation matrices, which are estimated between the training subjects (denoted as multi-source domains) and the test subject (denoted as target domain). Then, the multi-domain shifts are assigned as weighted indicators to resample the multi-source domains for model training. Comparative experiments with several prevailing transfer learning methods including CORrelation ALignment (CORAL), Geodesic Flow Kernel (GFK), Joint Distribution Adaptation (JDA), Transfer component analysis (TCA), and Balanced distribution adaption (BDA) using two different normalization processes were conducted on a realistic scenario across 18 subjects. Experimental results demonstrate that the ARR strategy can significantly improve performance (mean absolute error (MAE) reduction: 7.0%, root mean square error (RMSE) reduction: 6.3%), outperforming the prevailing methods. Besides, the impacts of data diversity and data size on ARR strategy are further investigated. It exhibits that data size is more important than data diversity for EOG-based gaze angle estimation, and also presents the benefits of the ARR strategy for dealing with practical scenarios.