Clustering on high-dimensional and low sample size (HDLSS) data remains a critical, persistent challenge where extreme sparsity and noise confound cluster analysis. This creates a dilemma: spectral methods fail as distance metrics degrade, while deep clustering tends to over-fit scarce data. To break this dilemma, a Self-Enhanced Density Clustering (SEDC) framework that integrates the cluster structure discovery and embedding representation learning into an iterative enhancement process is proposed in this paper. Specifically, SEDC uses adaptive density-derived centroids to parameterize probabilistic soft labels, which in turn supervise a lightweight multilayer perceptron (MLP) to learn the low-dimensional embedding from data. The resulting embedding provides a refined metric space for further generating superior labels in the subsequent interaction process. This feedback forms a mutual reinforcement that progressively enhances the discrimination of embedding while rigorously mitigating over-fitting. Extensive experiments on 43 challenging HDLSS datasets demonstrate state-of-the-art performance, substantially outperforming popular clustering methods. This work delivers a principled and promising solution for robust data clustering in HDLSS situations.

Employing a minimal array of electroencephalography (EEG) channels for neonatal sleep stage classification is essential for data acquisition in the Internet of Medical Things (IoMT), as single-channel and edge-based features can reduce data transfer and processing requirements, enhancing cost-effectiveness and practicality. In this paper, we evaluate the efficacy of a single channel and the viability of a binary classification scheme for discerning awake and sleep states and transitions to quiet sleep. For this, two datasets of EEG signals for neonate sleep analysis were recorded from Children's Hospital of Fudan University, Shanghai, comprising recordings from 64 and 19 neonates, respectively. From each epoch, a diverse ensemble of 490 features was extracted through a blend of discrete and continuous wavelet transforms (DWT, CWT), spectral statistics, and temporal features. In addition, we introduced an innovative hybrid univariate and ensemble feature selection approach with multidomain feature fusion, a stacking-based ensemble classifier that outperforms existing work. We achieved 90.37%, 91.13%, and 94.88% accuracy for sleep/awake, quiet sleep/non-quiet sleep, and quiet sleep/awake, respectively. This was corroborated by significant Kappa values of 77.5%, 80.29%, and 89.76%. Using SelectPercentile, we devised three distinct feature selection mechanisms: one using DWT, one with CWT, and another incorporating both spectral and temporal features. Subsequently, SelectKBest was used to determine the most effective features. For our stacked model, we incorporated a trifecta of the ExtraTree model with variable estimators, a Random Forest, and an Artificial Neural Network (ANN) as base classifiers, and for the final prediction phase, ANN was implemented again. The model's performance was evaluated using K-fold and leave-one-subject cross-validation.

Obstructive sleep apnea (OSA) and sleep fragmentation are closely linked physiological phenomena that play crucial roles in the diagnosis and management of sleep disorders. While numerous deep learning models have been developed for either OSA detection or sleep stage classification, few attempts have been made to address both tasks simultaneously. To this end, we propose MT-TASPPNet (Multi-Task Triple Atrous Spatial Pyramid Pooling Network), a unified multi-modal multi-task network that jointly performs automatic OSA event detection and sleep staging. The model integrates modality-specific feature extractors for EEG, ECG, and airflow signals, and employs Atrous Spatial Pyramid Pooling modules in both the modality-specific and shared representation pathways to capture multi-scale temporal-frequency patterns. Additionally, an EOG-guided prior mechanism is incorporated to enhance the discrimination of subtle sleep stages. We use a 3-min input window (1-min target with $\pm$ 1-min context) and evaluate our method on three large-scale datasets: SHHS1, SHHS2, and Sydney Sleep Biobank. The model achieves OSA detection accuracy between 0.798 and 0.884 (MF1: 0.772 to 0.821), and sleep staging accuracy between 0.776 and 0.834 (MF1: 0.735 to 0.749, $\mathcal {K}$: 0.697 to 0.77). Notably, the model maintains consistent performance despite data heterogeneity and individual variability. These results validate the stability and adaptability of MT-TASPPNet in clinical settings, paving the way for efficient and scalable multi-task sleep analysis systems.

Negative emotions are linked to the onset of neurodegenerative diseases and dementia, yet they are often difficult to detect through observation. Physiological signals from wearable devices offer a promising noninvasive method for continuous emotion monitoring. In this study, we propose a lightweight, resource-efficient machine learning approach for binary emotion classification, distinguishing between negative (sadness, disgust, anger) and positive (amusement, tenderness, gratitude) affective states using only electrocardiography (ECG) signals. The method is designed for deployment in resource-constrained systems, such as Internet of Things (IoT) devices, by reducing battery consumption and cloud data transmission through the avoidance of computationally expensive multimodal inputs. We utilized ECG data from 218 CSV files extracted from four studies in the Psychophysiology of Positive and Negative Emotions (POPANE) dataset, which comprises recordings from 1,157 healthy participants across seven studies. Each file represents a unique subject emotion, and the ECG signals, recorded at 1000 Hz, were segmented into$\mathbf{1 0}$-second epochs to reflect real-world usage. Our approach integrates multidomain feature extraction, selective feature fusion, and a voting classifier. We evaluated it using a participant-exclusive generalized model and a participantinclusive personalized model. The personalized model achieved the best performance, with an average accuracy of 95.59 %, outperforming the generalized model, which reached 69.92 % accuracy. Comparisons with other studies on the POPANE and similar datasets show that our approach consistently outperforms existing methods. This work highlights the effectiveness of personalized models in emotion recognition and their suitability for wearable applications that require accurate, low-power, and realtime emotion tracking. Code availability at GitHub.

Multi-view clustering aims to integrate complementary information from multiple views to improve clustering performance. However, existing ensemble-based methods suffer from information loss due to their reliance on single-granularity labels, limiting the discriminative capability of learned representations. Meanwhile, representation and graph fusion-based approaches face challenges such as explicit view alignment and manual weight tuning, making them less effective for heterogeneous views with varying data distributions. To address these limitations, we propose a novel multi-view clustering framework via Multi-granularity Ensemble (MGE), fully using the multi-granularity information across diverse views for accurate and consistent clustering. Specifically, MGE first modifies the hierarchical clustering and then leverages it on each view (including the fused view) to achieve multi-granularity labels. Moreover, the cross-view and cross-granularity fusion strategy is designed to learn a robust co-association similarity matrix, which effectively preserves the fine-grained and coarse-grained structures of multi-view data and facilitates subsequent clustering. Therefore, MGE can provide a comprehensive representation of local and global patterns within data, eliminating the requirement for view alignment and weight tuning. Experiments demonstrate that MGE consistently outperforms state-of-the-art methods across multiple datasets, validating its effectiveness and superiority in handling heterogeneous views.

Early detection and accurate diagnosis are essential to improving patient outcomes. The use of convolutional neural networks (CNNs) for tumor detection has shown promise, but existing models often suffer from overparameterization, which limits their performance gains. In this study, fuzzy sigmoid convolution (FSC) is introduced along with two additional modules: top-of-the-funnel and middle-of-the-funnel. The proposed methodology significantly reduces the number of trainable parameters without compromising classification accuracy. A novel convolutional operator is central to this approach, effectively dilating the receptive field while preserving input data integrity. This enables efficient feature map reduction and enhances the model’s tumor detection capability. In the FSC-based model, fuzzy sigmoid activation functions are incorporated within convolutional layers to improve feature extraction and classification. The inclusion of fuzzy logic into the architecture improves its adaptability and robustness. Extensive experiments on three benchmark datasets demonstrate the superior performance and efficiency of the proposed model. The FSC-based architecture achieved classification accuracies of 99.17 %, 99.75 %, and 99.89 % on three different datasets. The model employs 100 times fewer parameters than large-scale transfer learning architectures, highlighting its computational efficiency and suitability for detecting brain tumors early. This research offers lightweight, high-performance deep-learning models for medical imaging applications. Code: https://github.com/irfan334590/Fuzzy-Sigmoid-Conv.git

A timely diagnosis and treatment of sleep disorders in neonates during their first week of life is crucial. Current methods for staging neonatal sleep rely heavily on multiple electroencephalography (EEG) channels. These channels increase computational complexity, require a large amount of data to be transferred to the cloud, and may cause skin irritation. We propose an innovative automated classification approach that integrates multi-view feature fusion, AdaptiSelect-based feature optimization, the smart cloud data transfer and reconstruction (STREAM) module, and a rotational ensemble stacking model. The data reduction module significantly enhances edge-cloud systems’ performance in IoT-based healthcare environments by reducing data transmission by a factor of 153.6 through efficient feature selection and compact data packet formation. This module ensures minimal bandwidth usage, reduces the computational load on resource-constrained edge devices, and lowers cloud storage requirements while maintaining full data reconstruction. The dataset used in this research combines two large datasets collected over four years from the Children’s Hospital Fudan University, Shanghai. A unique set of 315 features are extracted from each epoch of a single channel using flexible analytical wavelet transform (FAWT), dual-tree complex wavelet transform (DTCWT), enhanced covariance (ECOV), and spectral features based on α, β, θ, and δ brain waves. These features are refined using AdaptiSelect, achieving an accuracy of 81.16% and a Kappa of 72.17% with one channel. Accuracy improves to 82.79% with a Kappa of 74.70% when using two channels, validated through 10-fold cross-validation. Additionally, Leave-One-Subject-Out crossvalidation (LOSO-CV) further demonstrates the effectiveness of the proposed approach as a generalized solution. Using both single and multichannel setups, the proposed approach outperforms the most significant state-of-the-art methods in neonatal sleep analysis.

High-density surface EMG (HD-sEMG) is gaining attention because of its non-invasive nature and high spatial resolution. However, wearable HD-sEMG measurements with over 128 channels face challenges in system integration and reliable network-free inter-device synchronization. This article presents a wireless distributed wearable HD-sEMG acquisition system named Oct-HD, which supports up to eight acquisition modules (512 channels) with microsecond-level synchronization without requiring a network. The full-channel impedance detection ensures reliable electrode-skin contact and signal acquisition. The system also includes a self-locking base station that stores, charges, and configures the modules. Both simulated and real-world validation demonstrate that the system maintains a long-term inter-module offline error within 3ms, even under vibrations and extreme temperatures, demonstrating reliability for network-free outdoor and open-space monitoring. To support high-level signal interpretation, we further developed an integrated analysis software suite alongside the hardware. This toolkit enables motor unit decomposition, feature extraction, root mean square (RMS) map and power spectral density (PSD) analysis. Comparative experiments with a commercial system (Sessantaquattro) involving ten hand postures and 17 subjects were conducted, as hand gesture recognition is one of the most common applications in the field of electromyography. Results showed a significant performance improvement (p<10-5) of Oct-HD over the state-of-the-art system in signal quality and anti-interference capacity. Gesture classification results across four mainstream models demonstrated general accuracy improvements with Oct-HD over the commercial system in both dynamic and maintenance tasks. This highlights the effectiveness of Oct-HD in enhancing applications in prosthetic control and human-computer interaction. The Oct-HD system offers a notable advancement in wireless HD-sEMG acquisition, offering superior channel capacity, synchronization precision, signal quality, and anti-interference capacity compared to existing systems. The network-free microsecond-level synchronization and enhanced signal performance provide greater monitoring flexibility across various muscle groups, paving the way for broader applications in human-machine interaction.

Rapid eye movement (REM) sleep without atonia (RSWA) is a critical diagnostic criterion for REM sleep behavior disorder (RBD). Current clinical practices rely on time-consuming manual annotation, increasing workload, and introducing variability. Existing automated methods, including CNN, LSTM, Transformer, and their combinations, fail to fully exploit the inherent physiological relationship between sleep staging and RSWA detection, while also facing challenges such as severe data imbalance and the complex fusion of multichannel signals. To address these limitations, we propose a multi-task learning framework that jointly optimizes both tasks. Our Multi-scale Information Attention Bottleneck Network (MIABNet) backbone improves multichannel fusion. Building upon MIABNet, the Multi-task RBD Network (MtRBD) implements dynamic feature enhancement, facilitating cross-task information flow while preserving physiological relationships. On the clinical CZ-RBD dataset collected from 30 patients over 59 nights at Shanghai Changzheng Hospital, our framework achieved the accuracy of 83.0% for sleep staging and 93.6% for RSWA detection, with an accuracy of 77.6% for critical RSWA event identification, outperforming single-task methods in cross-subject validation. Through modality selection and Grad-CAM visualization, we enhance clinical interpretability, providing reliable support for early detection of RBD and related neurodegenerative diseases.

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.

Stroke is the second leading cause of disability and mortality worldwide. Extensive researches on rehabilitation assessment for stroke survivors using wearable plantar pressure sensors often suffer from troublesome processes and unsatisfactory results due to excessive sensors and sparse pressure sensing structures. To address this, we developed an automatic assessment system for the recovery stage of stroke patients based solely on smart high-density flexible wearable plantar pressure insoles and an ensemble learning classification algorithm (ELCA). This system quantitatively evaluates the stroke patient's recovery progress. The data from 37 stroke patients were collected using self-developed smart insoles, from which multidimensional high-order features were extracted. ELCA employing seven basic classifiers was then developed to quantitatively assess recovery stages. Finally, the leave-one-out method was used to evaluate the performance of classifiers. The results show the ELCA has the best performance, achieving an accuracy, specificity, and sensitivity of up to 91.890/0, 97.30%, and 91.89% respectively, preliminarily demonstrating the system possesses excellent capabilities in quantitatively assessing rehabilitation progress. This solution is expected to provide an objective and practical method for long-term home rehabilitation monitoring of stroke patients.

Sleep is essential for health, with poor-quality sleep may link to cognitive impairment, increased disease risk, etc. Traditional sleep monitoring systems, such as polysomnography(PSG), are comprehensive but costly, uncomfortable, and confined to clinical settings. Recent wearable sleep monitoring devices typically employ single-channel EEG signal from the forehead, which can only acquire single-modal signals and may limit the accuracy of sleep analysis to some extent. To address these issues, this paper proposes a low-cost, multi-modal, wearable and comfortable headband system for sleep monitoring. The headband integrates six EEG sensors, a six-axis inertial measurement unit (IMU) and a temperature sensor to collect EEG signals, motion data, and environmental temperature, and can also derive information from other modalities such as heart beat, respiration rate, body movement, etc. The headband system integrates multiple sensors, with the EEG sensors primarily using flexible claw-shaped dry electrodes that penetrate the hair to make sufficient contact with the scalp for precise detection of minute signals. This system provides a wealth of multi-modal information, which offers a solution for precise sleep analysis and the identification of sleep disorders such as insomnia and sleep apnea. To verify the performance of the headband prototype, comprehensive experiments were performaed as compare to PSG. Experimental results show that the Pearson correlation coefficient of EEG signals can reach 0.9435, and the RR interval derived from IMU is only 0.001 seconds different from that obtained from PSG ECG signals, proving a high consistent with the standard results measured by PSG.

Surface electromyogram (sEMG)-based multidegree of freedom (DoF) finger force estimation for the prosthesis and armband applications has obtained increasing attention in the human–machine interface (HMI) field. However, few studies have explored the relation between force estimation performance and coverage area of sEMG electrodes. To address the needs of transradial amputees with varying stump lengths, we investigated the force estimation performance using 16 different electrode layouts covering different forearm areas. Additionally, since the position of the armband affects force estimation performance, we evaluated how model performance varies with the armband worn from the wrist to the elbow. This allows users to select their armband position based on a tradeoff between model performance and practical convenience. We acquired 256-channel forearm sEMG and multi-DoF finger force data from 20 intact subjects. Each subject participated in the experiment on two different days (3 to 25 days apart). Benchmark features were extracted and least squares-based linear finite impulse response models were constructed to estimate the multi-DoF finger force. Both intra-day and interday results were reported for comparison. As a result, the interday regression root mean square error ranged from 8.71±0.80% to 10.98±0.98% of maximum force for prosthesis application and from 9.45±0.79% to 10.82±0.90% of maximum force for armband application. In summary, this work enables users to customize their systems based on their physical conditions and requirements.

Image clustering attracts much attention in computer vision and multimedia. Due to the absence of labels, even deep clustering still often achieves unreliable results. Although semi-supervised deep clustering can alleviate this problem, it introduces a new problem in the selection of supervised information during semi-supervised learning. To address this issue, in this paper, we propose a novel active deep clustering method that can actively select informative data for querying human annotations and apply these annotations to guide deep clustering. We seamlessly integrate active learning and self-paced learning into a unified deep clustering framework, which can automatically evaluate the difficulty and representativeness of each data and further find the important data. To demonstrate its effectiveness, we conduct extensive experiments on benchmark image data sets. The results show that our proposed method outperforms the state-of-the-art semi-supervised deep clustering and deep active learning methods. The code is available at https://github.com/wodedazhuozi/DSAC.

Surface electromyography (sEMG)-based gesture recognition can achieve high intra-session performance. However, the inter-session performance of gesture recognition decreases sharply due to the shift in data distribution. Therefore, developing a robust model to minimize the data distribution difference is crucial to improving the user experience. In this work, based on the inter-session gesture recognition task, we propose a novel algorithm called locality preserving and maximum margin criterion (LPMM). The LPMM algorithm integrates three main modules, including domain alignment, pseudo-label selection, and iteration result selection. Domain alignment is designed to preserve the neighborhood structure of the feature and minimize the overlap of different classes. The pseudo-label selection and iteration result selection can avoid the decrease in accuracy caused by mislabeled samples. The proposed algorithm was evaluated on two of the most widely used EMG databases. It achieves a mean accuracy of 98.46% and 71.64%, respectively, which is superior to state-of-the-art domain adaptation methods.

Automatic sleep staging offers a quick and objective assessment for quantitatively interpreting sleep stages in neonates. However, most of the existing studies either do not encompass any temporal information, or simply apply neural networks to exploit temporal information at the expense of high computational overhead and modeling ambiguity. This limits the application of these methods to multiple scenarios. In this paper, a sequential end-to-end sleep staging model, SeqEESleepNet, which is competent for parallelly processing sequential epochs and has a fast training rate to adapt to different scenarios, is proposed. SeqEESleepNet consists of a sequence epoch generation (SEG) module, a sequential multi-scale convolution neural network (SMSCNN) and squeeze and excitation (SE) blocks. The SEG module expands independent epochs into sequential signals, enabling the model to learn the temporal information between sleep stages. SMSCNN is a multi-scale convolution neural network that can extract both multi-scale features and temporal information from the signal. Subsequently, the followed SE block can reassign the weights of features through mapping and pooling. Experimental results exhibit that in a clinical dataset, the proposed method outperforms the state-of-the-art approaches, achieving an overall accuracy, F1-score, and Kappa coefficient of 71.8%, 71.8%, and 0.684 on a three-class classification task with a single channel EEG signal. Based on our overall results, we believe the proposed method could pave the way for convenient multi-scenario neonatal sleep staging methods.

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.

Sleep staging plays a critical role in evaluating the quality of sleep. Currently, most studies are either suffering from dramatic performance drops when coping with varying input modalities or unable to handle heterogeneous signals. To handle heterogeneous signals and guarantee favorable sleep staging performance when a single modality is available, a pseudo-siamese neural network (PSN) to incorporate electroencephalography (EEG), electrooculography (EOG) characteristics is proposed (PSEENet). PSEENet consists of two parts, spatial mapping modules (SMMs) and a weight-shared classifier. SMMs are used to extract high-dimensional features. Meanwhile, joint linkages among multi-modalities are provided by quantifying the similarity of features. Finally, with the cooperation of heterogeneous characteristics, associations within various sleep stages can be established by the classifier. The evaluation of the model is validated on two public datasets, namely, Montreal Archive of Sleep Studies (MASS) and SleepEDFX, and one clinical dataset from Huashan Hospital of Fudan University (HSFU). Experimental results show that the model can handle heterogeneous signals, provide superior results under multimodal signals and show good performance with single modality. PSEENet obtains accuracy of 79.1%, 82.1% with EEG, EEG and EOG on Sleep-EDFX, and significantly improves the accuracy with EOG from 73.7% to 76% by introducing similarity information.

Despite the recent advances in automatic sleep staging, few studies have focused on real-time sleep staging to promote the regulation of sleep or the intervention of sleep disorders. In this paper, a novel network named SwSleepNet, that can handle both precisely offline sleep staging, and online sleep stages prediction and calibration is proposed. For offline analysis, the proposed network coordinates sequence broadening module (SBM), sequential CNN (SCNN), squeeze and excitation (SE) block, and sequence consolidation module (SCM) to balance the operational efficiency of the network and the comprehensive feature extraction. For online analysis, only SCNN and SE are involved in predicting the sleep stage within a short-time segment of the recordings. Once more than two successive segments have disparate predictions, the calibration mechanism will be triggered, and contextual information will be involved. In addition, to investigate the appropriate time of the segment that is suitable to predict a sleep stage, segments with five-second, three-second, and two-second data are analyzed. The performance of SwSleepNet is validated on two publicly available datasets Sleep-EDF Expanded and Montreal Archive of Sleep Studies (MASS), and one clinical dataset Huashan Hospital Fudan University (HSFU), with the offline accuracy of 84.5%, 86.7%, and 81.8%, respectively, which outperforms the state-of-the-art methods. Additionally, for the online sleep staging, the dedicated calibration mechanism allows SwSleepNet to achieve high accuracy over 80% on three datasets with the short-time segments, demonstrating the robustness and stability of SwSleepNet. This study presents a real-time sleep staging architecture, which is expected to pave the way for accurate sleep regulation and intervention.

Due to the limitations of large size, non-random movement, high cost and complex equipment, the video recognition and pressure testing platform used for gait monitoring can only be operated in laboratory environment. Some insole devices invented in recent years are basically equipped with other modules, making them inconvenient to wear. To solve the above problems, this paper proposes intelligent flexible pressure insoles with low cost and high resolution, as well as convenience and comfortness. The insole collects the plantar pressure distribution and motion data of daily walking through 12 x 4 flexible pressure array and accelerometer sensor, and then wirelessly transmits the data to the upper computer through Bluetooth. Material property tests were conducted and the results showed robustness and stability of the pressure sensor. The feasibility of the insole for gait monitoring is verified through preliminary walking experiments. The results show that of the proposed insole is characterized by low cost, high resolution, portability and comfortableness. Additionally, it can be used directly into the shoe without any external module, regardless of site and environment restrictions. The insole can meet the needs of daily gait monitoring and provide more quantitative reference data for gait rehabilitation.

In smart healthcare facilities designed especially for the elderly, noncontact electrocardiogram (ECG) measurements could provide essential information about an elderly person’s health by enabling long-term health analytics. In this research work, we propose an Internet of Things (IoT)-based noncontact ECG measurement system. The noncontact measurement is done using flexible electrodes that are made of fabric. These fabric-based flexible electrodes are designed to measure ECG signals from the sole of the feet (SOF) or the palms of the hands (POHs) without touching human skin. To mitigate the impact of nearby electromagnetic radiation on the electrodes, a double layer of isopotential shielding is placed underneath the two active electrodes. The gathered biosignals are stored in the IoT device and transmitted to the cloud. To reduce the amount of stored and transmitted data, we improved our adaptive coding algorithm. The adaptive coding results in an average data reduction of 72%. The data can be fully recovered in the cloud for further analyses using advanced cloud-based tools in ThingSpeak. The study tested the proposed system on 35 participants, including elderly persons, adults, and children. Based on the experiments, the proposed system accurately measures the ECG signal. We validated the results with the ground truth data [polysomnography (PSG)] showing an average heart rate (HR) error of$\mp 1$beat per minute (BPM). Moreover, we compared QRS complexes detected on wrists with those detected from SOF (with or without socks), POH (with or without gloves), and one hand and one foot (with or without a sock and glove), and found no significant differences.

With massive data collected in Internet of Things (IoT)-based smart environment, improving privacy preservation via client verification and identification is crucial. Surface electromyogram (sEMG) has emerged as a cancelable neuromuscular biometric trait, which makes up the noncancelability flaw of the traditional face and fingerprint biometrics. Current studies are in the proof-of-concept stage. In-depth studies to find the optimal solution to decode sEMG biometrics with excellent cross-day performance are very scarce. For neurophysiological biometrics, the permanence across time is a crucial factor. Our work aims to optimize the cross-day performance of the sEMG biometric decoder. We systematically evaluated the performance of 28 hand gestures to generate sEMG, 55 temporal–spectral–spatial features to represent sEMG, 9 distance measures and 9 classifiers to make decisions. Both biometric verification and identification were investigated in rigorous cross-day validations. Results show that the optimal combination of ≥ 10 temporal–spectral–spatial features achieved the best cross-day performance with city-block distance and support vector machine (SVM) applied. EMG generated by middle finger extension and hand close is preferred as biometric tokens. Using the optimized decoder, a cross-day identification accuracy of 88.75% and verification error rate of 9.85% were achieved. The verification error rate could be further reduced to 2.45% if impostors input sEMG under random gestures. Moreover, our work proved the reliability of sEMG biometrics even under muscle fatigue for the first time. This is also the first study to systematically evaluate the cross-day performance of different components in sEMG biometric decoding systems, serving as a technique-screening tool for future studies.

Tedious parameter settings and poor performances seriously affect the entropy estimation's effectiveness in time series analysis. To solve these limits, we propose a conceptually novel definition, cumulative diversity pattern entropy (CDEn), focusing on eliminating parameter selections and improving quantization accuracy, stability, and robustness. The CDEn algorithm consists of three steps: 1) improved phase-space reconstruction (IPSR) with constant embedding dimension$m= 2$and time delay$\tau =1$; 2) diversity pattern partition generated by the cosine similarity between adjacent vectors; and 3) entropy calculation based on the normalized cumulative probability distribution. Numerical experiments are performed using 7 synthetic datasets and 15 baseline entropy methods for comparative validation. The results confirm CDEn's best description of chaotic/stochastic dynamics with the highest quantization accuracy and the lowest error rate of 2.04%. The coefficient of variation (CV) results also verify CDEn's excellent quantization stability with CV lower than 10−2. The relative change rate results demonstrate that CDEn achieves the best robustness to data length and noise. Finally, the entropy algorithms are applied to a real-world dataset, i.e., neonatal sleep EEG analysis. The results further confirm that suggested CDEn outperforms the state-of-the-art entropy methods, with the minimum outliers and best statistical significance (highest mean of effect size, 1.22) in characterizing the neurodynamics of different sleep stages.

Deep learning methods have become an important tool for automatic sleep staging in recent years. However, most of the existing deep learning-based approaches are sharply constrained by the input modalities, where any insertion, substitution, and deletion of input modalities would directly lead to the unusable of the model or a deterioration in the performance. To solve the modality heterogeneity problems, a novel network architecture named MaskSleepNet is proposed. It consists of a masking module, a multi-scale convolutional neural network (MSCNN), a squeezing and excitation (SE) block, and a multi-headed attention (MHA) module. The masking module consists of a modality adaptation paradigm that can cooperate with modality discrepancy. The MSCNN extracts features from multiple scales and specially designs the size of the feature concatenation layer to prevent invalid or redundant features from zero-setting channels. The SE block further optimizes the weights of the features to optimize the network learning efficiency. The MHA module outputs the prediction results by learning the temporal information between the sleeping features. The performance of the proposed model was validated on two publicly available datasets, Sleep-EDF Expanded (Sleep-EDFX) and Montreal Archive of Sleep Studies (MASS), and a clinical dataset, Huashan Hospital Fudan University (HSFU). The proposed MaskSleepNet can achieve favorable performance with input modality discrepancy, e.g. for single-channel EEG signal, it can reach 83.8%, 83.4%, 80.5%, for two-channel EEG+EOG signals it can reach 85.0%, 84.9%, 81.9% and for three-channel EEG+EOG+EMG signals, it can reach 85.7%, 87.5%, 81.1% on Sleep-EDFX, MASS, and HSFU, respectively. In contrast the accuracy of the state-of-the-art approach which fluctuated widely between 69.0% and 89.4%. The experimental results exhibit that the proposed model can maintain superior performance and robustness in handling input modality discrepancy issues.

The clinical manifestations of OSA (obstructive sleep apnea) are night sleep snoring accompanied by apnea. fNIRS (functional near-infrared spectroscopy) can measure the relative concentration changes of oxyhemoglobin and deoxyhemoglobin, thereby measuring hemodynamics and oxygenation. Combined with the clinical manifestations of obstructive sleep apnea, fNIRS technology can be used in the monitoring of OSA. According to the principle of fNIRS, a miniaturized, wireless, and flexible device is designed in the article. The device can measure the change of blood oxygen concentration in the forehead of the brain, so that achieve the purpose of detecting OSA. To verify the effectiveness of the equipment, a breathing experiment was designed in the article to compare the equipment with the existing NIRX system. To our best knowledge, this is the first work that proposed a miniaturized flexible sleep apnea system based on monitoring fluctuations of cerebral hemodynamics. Meanwhile, the feasibility of the proposed system was verified. However, the stability of the equipment and related data processing algorithms need to be enhanced. The proposed system is expected to pave the way for the investigation of the involvement of the cerebral hemodynamics in the pathogenesis of OSA patients.

Sleep posture, which affects the quality of sleep and could lead to medical conditions, such as pressure ulcers, is a key metric for sleep analysis in Internet of Medical Things (IoMT). In this article, a real-time and low-cost smart mat system for sleep posture recognition based on frequency channel selection is proposed. The system can recognize postures unobtrusively with a dense flexible sensor array. In addition, to enable real-time recognition with a relatively low-cost STM32 processor system, a lightweight algorithm that includes frequency channel selection, model pretraining, and real-time classification is proposed. Through a series of short-term and overnight experiments with 21 subjects, the feasibility and reliability of the proposed system were evaluated. Experimental results show that the accuracy of the short-term experiment is up to 95.43% and of the overnight experiment is up to 86.80% for four posture categories (supine, prone, right, and left) classification. The model size is just 56 kB which is much smaller than other methods. The runtime of the complete algorithm is about 6 ms with a low-power STM32 embedded system, which shows the system’s ability to provide real-time posture recognition. As an edge device, the proposed system could lead to the development of fast, convenient, and low-cost sleep posture recognition products for IoMT.

Data center virtualization is a flexible and efficient way to enable multiple users to share the common resources of a physical data center (DC). For efficient sharing, virtual data center (VDC) embedding is a vital problem that should be carefully addressed. However, existing studies on VDC embedding mostly assume that the capacity of each VDC is fixed, but do not consider the time-varying feature of resource demands. Considering the fact that the resource demands of most enterprise IT services exhibit the time-varying feature, resource allocation based on the fixed capacity assumption would cause a great inefficiency. To overcome this inefficiency, we propose a new VDC consolidation scheme that takes into account the time-varying feature of resource demands when embedding VDCs. We first develop a resource demand prediction model for each VDC using the Long Short-Term Memory (LSTM) neural network, which is used to predict the real-time resource demands of VDCs at different future moments. Based on the predicted resource demands, we then embed VDCs whose peaks and valleys of resource demands stagger each other onto common physical servers and links, such that the required physical resources can be minimized under the condition that all the resource demands of different VDCs are satisfied at all the different moments. An integer linear programming (ILP) model and a resource demand correlation-based heuristic algorithm are also developed for the proposed scheme. Simulation results show that the proposed consolidation scheme can significantly improve resource utilization in a DC. It can save up to 25 percent of physical servers and 29 percent of physical links used for accommodating the same requests as compared to a scheme assigning resources based on the fixed capacity assumption.

Human–machine interaction requires accurate recognition of human intentions (e.g., via hand gestures). Here, we assessed the cross-day robustness of widely used hand gesture classification techniques applied to high-density surface electromyogram (HD-sEMG) signals (256 channels). Our evaluation covered techniques in each stage of the classification framework: first, 50 temporal-spectral-spatial domain features, second, 15 feature optimization techniques, and third, seven classifiers. Moreover, although HD-sEMG provides sufficient neuromuscular information, some of the channels may present low signal-to-noise ratio and should therefore be treated as outliers. Accordingly, we performed our evaluation with, first, all outlier channels retained, and second, removal of the features corresponding to poor-quality channels and substitution with interpolated values from neighbor channels. The impact of sliding window and data augmentation was also investigated. We examined the results on a 35-gesture classification task using HD-sEMG acquired from 20 subjects on two sessions in separate days. The results showed that interpolation of features from outlier channels significantly improved the performance in most cases. Use of a sliding window and of data augmentation contributed to a higher classification accuracy. For the classification of 11 selected gestures of common daily use, the support vector machine classifier achieved the highest classification accuracy of 91.9% in a cross-day validation protocol using an optimal combination of 13 features (each extracted from sliding windows), feature optimization by linear discriminant analysis, and data augmentation. Our work can serve as a technique-screening tool on cross-day applications of human–machine interactions.

Conventional biometric modalities, such as the face, fingerprint, and iris, are vulnerable against imitation and circumvention. Accordingly, secure biometric modalities with cancelable properties are needed for personal identification, especially in smart healthcare applications. Here we developed a person identification model using high-density surface electromyography (HD-sEMG) as biometric traits. In this model, the HD-sEMG biometric templates are cancelable and could be customized by the users through finger isometric contractions. A deep feature learning approach, implemented by convolutional neural networks (CNNs) is used to capture user-specific patterns from HD-sEMG signals and make identification decisions. This model has been validated on twenty-two subjects, with training and testing data acquired from two different days. The rank-1 identification accuracy and equal error rate for 44 identities (22 subjects × 2 accounts) can reach 87.23% and 4.66%, respectively. The cross-day identification accuracy of the proposed model is higher than the results of previous methods reported in the literature. The usability and efficiency of the proposed model are also investigated, indicating its potentials for practical applications.

Sleep posture, as a crucial index for sleep quality assessment and pressure ulcer prevention, has been widely studied for medical diagnoses and sleep disease treatment. In this paper, an unobtrusive smart mat system for sleep posture recognition is proposed, which is based on a dense flexible sensor array and printed electrodes and along with an algorithmic framework. With the dense flexible sensor array, the system offers a comfortable and high-resolution solution for long-term pressure sensing. Meanwhile, compared with other large-area and low-density mat systems, it reduces the area to minimize manufacturing cost and computational complexity, while also increases the density of the sensor to improve accuracy. To distinguish the sleep postures, the algorithmic framework that includes pre-processing, feature extraction, and posture classification is developed. Pilot studies in two scenarios including subject-dependent and subject- independent classification are performed with 7 persons for 4 different postures recognition. The experimental results show that the accuracy of the smart mat system can achieve over 78% using Support Vector Machines (SVMs) and k-Nearest Neighbor (kNN) for the subject-independent scenario. For the subject-dependent scenario, the accuracy can reach over 95%. It proves that the proposed method can recognize different sleep postures effectively.

Enhancing information security via reliable user authentication in wireless body area network (WBAN)-based Internet-of-Things (IoT) applications has attracted increasing attention. The noncancelability of traditional biometrics (e.g., fingerprint) for user authentication increases the privacy disclosure risks once the biometric template is exposed, because users cannot volitionally create a new template. In this work, we propose a cancelable biometric modality based on high-density surface electromyogram (HD-sEMG) encoded by hand gesture password, for user authentication. HD-sEMG signals (256 channels) were acquired from the forearm muscles when users performed a prescribed gesture password, forming their biometric token. Thirty four alternative hand gestures in common daily use were studied. Moreover, to reduce the data acquisition and transmission burden in IoT devices, an automatically generated password-specific channel mask was employed to reduce the number of active channels. HD-sEMG biometrics were also robust with reduced sampling rate, further reducing power consumption. HD-sEMG biometrics achieved a low equal error rate (EER) of 0.0013 when impostors entered a wrong gesture password, as validated on 20 subjects. Even if impostors entered the correct gesture password, the HD-sEMG biometrics still achieved an EER of 0.0273. If the HD-sEMG biometric template was exposed, users could cancel it by simply changing it to a new gesture password, with an EER of 0.0013. To the best of our knowledge, this is the first study to employ HD-sEMG signals under common daily hand gestures as biometric tokens, with training and testing data acquired on different days.

In this article, we propose a novel neuromuscular password-based user authentication method. The method consists of two parts: surface electromyogram (sEMG) based finger muscle isometric contraction password (FMICP) and neuromuscular biometrics. FMICP can be entered through isometric contraction of different finger muscles in a prescribed order without actual finger movement, which makes it difficult for observers to obtain the password. In our study, the isometric contraction patterns of different finger muscles were recognized through high-density sEMG signals acquired from the right dorsal hand. Moreover, both time-frequency-space domain features at macroscopic level (interference-pattern EMG) and motor neuron firing rate features at microscopic level (via decomposition) were extracted to represent neuromuscular biometrics, serving as a second defense. The FMICP and macro-micro neuromuscular biometrics together form a neuromuscular password. The proposed neuromuscular password achieved an equal error rate (EER) of 0.0128 when impostors entered a wrong FMICP. Even when impostors entered the correct FMICP, the neuromuscular biometrics, as the second defense, inhibited impostors with an EER of 0.1496. To the best of our knowledge, this is the first study to use individually unique neuromuscular information during unobservable muscle isometric contractions for user authentication, with training and testing data acquired on different days.

Sleep is a natural phenomenon controlled by the central nervous system. The sleep-wake pattern, which functions as an essential indicator of neurophysiological organization in the neonatal period, has profound meaning in the prediction of cognitive diseases and brain maturity. In recent years, unobtrusive sleep monitoring and automatic sleep staging have been intensively studied for adults, but much less for neonates. This work aims to investigate a novel video-based unobtrusive method for neonatal sleep-wake classification by analyzing the behavioral changes in the neonatal facial region. A hybrid model is proposed to monitor the sleep-wake patterns of human neonates. The model combines two algorithms: deep convolutional neural network (DCNN) and support vector machine (SVM), where DCNN works as a trainable feature extractor and SVM as a classifier. Data was collected from nineteen Chinese neonates at the Children's Hospital of Fudan University, Shanghai, China. The classification results are compared with the gold standard of video-electroencephalography scored by pediatric neurologists. Validations indicate that the proposed hybrid DCNN-SVM model achieved reliable performances in classifying neonatal sleep and wake states in RGB video frames (with the face region detected), with an accuracy of 93.8 ± 2.2% and an F1-score 0.93 ± 0.3.

Identifying bio-signals based-sleep stages requires time-consuming and tedious labor of skilled clinicians. Deep learning approaches have been introduced in order to challenge the automatic sleep stage classification conundrum. However, the difficulties can be posed in replacing the clinicians with the automatic system due to the differences in many aspects found in individual bio-signals, causing the inconsistency in the performance of the model on every incoming individual. Thus, we aim to explore the feasibility of using a novel approach, capable of assisting the clinicians and lessening the workload. We propose the transfer learning framework, entitled MetaSleepLearner, based on Model Agnostic Meta-Learning (MAML), in order to transfer the acquired sleep staging knowledge from a large dataset to new individual subjects (source code is available at https://github.com/IoBT-VISTEC/MetaSleepLearner). The framework was demonstrated to require the labelling of only a few sleep epochs by the clinicians and allow the remainder to be handled by the system. Layer-wise Relevance Propagation (LRP) was also applied to understand the learning course of our approach. In all acquired datasets, in comparison to the conventional approach, MetaSleepLearner achieved a range of 5.4% to 17.7% improvement with statistical difference in the mean of both approaches. The illustration of the model interpretation after the adaptation to each subject also confirmed that the performance was directed towards reasonable learning. MetaSleepLearner outperformed the conventional approaches as a result from the fine-tuning using the recordings of both healthy subjects and patients. This is the first work that investigated a non-conventional pre-training method, MAML, resulting in a possibility for human-machine collaboration in sleep stage classification and easing the burden of the clinicians in labelling the sleep stages through only several epochs rather than an entire recording.

The ability to expertly control different fingers contributes to hand dexterity during object manipulation in daily life activities. The macroscopic spatial patterns of muscle activations during finger movements using global surface electromyography (sEMG) have been widely researched. However, the spatial activation patterns of microscopic motor units (MUs) under different finger movements have not been well investigated. The present work aims to quantify MU spatial activation patterns during movement of distinct fingers (index, middle, ring and little finger). Specifically, we focused on extensor muscles during extension contractions. Motor unit action potentials (MUAPs) during movement of each finger were obtained through decomposition of high-density sEMG (HD-sEMG). First, we quantified the spatial activation patterns of MUs for each finger based on 2-dimension (2-D) root-mean-square (RMS) maps of MUAP grids after spike-triggered averaging. We found that these activation patterns under different finger movements are distinct along the distal-proximal direction, but with partial overlap. Second, to further evaluate MU separability, we classified the spatial activation pattern of each individual MU under distinct finger movement and associated each MU with its corresponding finger with Regularized Uncorrelated Multilinear Discriminant Analysis (RUMLDA). A high accuracy of MU-finger classification tested on 12 subjects with a mean of 88.98% was achieved. The quantification of MU spatial activation patterns could be beneficial to studies of neural mechanisms of the hand. To the best of our knowledge, this is the first work which manages to quantify MU behaviors under different finger movements.

With the soaring development of body sensor network (BSN)-based health informatics, information security in such medical devices has attracted increasing attention in recent years. Employing the biosignals acquired directly by the BSN as biometrics for personal identification is an effective approach. Noncancelability and cross-application invariance are two natural flaws of most traditional biometric modalities. Once the biometric template is exposed, it is compromised forever. Even worse, because the same biometrics may be employed as tokens for different accounts in multiple applications, the exposed template can be used to compromise other accounts. In this work, we propose a cancelable and cross-application discrepant biometric approach based on high-density surface electromyogram (HD-sEMG) for personal identification. We enrolled two accounts for each user. HD-sEMG signals from the right dorsal hand under isometric contractions of different finger muscles were employed as biometric tokens. Since isometric contraction, in contrast to dynamic contraction, requires no actual movement, the users' choice to login to different accounts is greatly protected against impostors. We realized a promising identification accuracy of 85.8% for 44 identities (22 subjects × 2 accounts) with training and testing data acquired 9 days apart. The high identification accuracy of different accounts for the same user demonstrates the promising cancelability and cross-application discrepancy of the proposed HD-sEMG-based biometrics. To the best of our knowledge, this is the first study to employ HD-sEMG in personal identification applications, with signal variation across days considered.

Photoplethysmography (PPG) has shown its great potential for noninvasive health monitoring, but its application in wearable devices is largely impeded due to its extreme vulnerability to motion artifacts. In this article, we proposed a new stochastic modeling based nonlinear Bayesian filtering framework for the recovery of corrupted PPG waveform under strenuous physical exercise in wearable health-monitoring devices. A deep recurrent neural network was first recruited for accurate cardiac-period segmentation of corrupted PPG signals. Then, a stochastic model was applied to extract waveform details from clean PPG pulses, and was further derived into a system-state space. Following this was an extended Kalman filter using the state-space structured by modeling. The covariance of measurement noise was estimated by motion-related information to adjust it into the real physical environment adaptively. Comparison results with state-of-the-art methods on a wearable-device-based 48-subject data set showed the outstanding performance of the proposed denoising framework, with period-segmentation sensitivity and precision higher than 99.1%, instantaneous heart rate (HR) error lower than 2 beats/min, average HR error down to 1.14 beats/min, and recovery accuracy of waveform details significantly improved (p <; 0.05). This framework is the first PPG denoising strategy that introduces waveform-modeling methods to ensure detail recovery, and a great example of algorithm fusion between stochastic signal processing and emerging deep learning methods for time-sequential biomedical signal processing.

The papers in this special section were presented at the 2019 IEEE-EMBS International Conferences on Biomedical and Health Informatics (BHI’19) and Wearable and Implantable Body Sensor Networks (BSN’19). Topics of integrative sensor networks, informatics and modeling bring together the tightly coupled and rapidly developing fields of biomedical and health informatics and body sensor networks. Biomedical and health informatics encompasses methods to extract and communicate information from data in order to impact health, healthcare, life sciences and biomedicine. Body sensor networks provide one means to measure the needed data, through continuous monitoring in both clinical and free-living environments.

The papers in this special section focuses on artificial intelligent-driven informatics, sensing, imaging and big data analytics in dealing with the COVID-19 pandemic.

Food intake monitoring can play an important role in the prevention of malnutrition in the aging population, but traditional tools may not be adequate for use in this target group. These tools typically involve the use of questionnaires or food diaries that require manual data entry. Due to their time-consuming nature, they are often incomplete, contain mistakes, or not used at all. An alternative to self-reporting tools, in the form of a plate system that automatically measures the consumed food during the meal, is presented in this paper. Furthermore, the system can estimate the location where each bite was taken on the plate. The system is compatible with an off-the-shelf plate that is mounted on top of a base station. Weight sensors are integrated in the base, allowing for easy removal and cleaning of the plate. Localization of bites is done by looking at the movement of the center of mass during eating. When used with a compartmentalized plate, the amount of consumed food per compartment can be measured. With prior knowledge of the type of food in each compartment, this can give an indication of calories and nutritional intake. We present a bite detection algorithm using a random forest decision tree classifier. Data from 24 aging adults (ages 52-95) eating a single meal with chopsticks was used to train and evaluate the model. Out of a total of 836 true annotated bites, the algorithm detected 602 with a precision and recall of 0.78 and 0.76, respectively. By summing the weights of detected bites from each compartment, the algorithm was able to estimate the amount of food taken per compartment with an average error of (8 ±8)% of the portion size.

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.

The four papers in this special section focus on the use of blockchain in the healthcare field. With the development of society, health has received increasing attentions. The development of science and technology has also promoted the protection of health. In recent years, the rapid development of computing and networking technologies has improved the ability to collect, measure, and analyze health-related data, and thus tremendous opportunities have opened up for healthcare computing. Meanwhile, these technologies have also brought new challenges and issues.

Epilepsy seizure prediction paves the way of timely warning for patients to take more active and effective intervention measures. Compared to seizure detection that only identifies the inter-ictal state and the ictal state, far fewer researches have been conducted on seizure prediction because the high similarity makes it challenging to distinguish between the pre-ictal state and the inter-ictal state. In this paper, a novel solution on seizure prediction is proposed using common spatial pattern (CSP) and convolutional neural network (CNN). Firstly, artificial pre-ictal EEG signals based on the original ones are generated by combining the segmented pre-ictal signals to solve the trial imbalance problem between the two states. Secondly, a feature extractor employing wavelet packet decomposition and CSP is designed to extract the distinguishing features in both the time domain and the frequency domain. It can improve overall accuracy while reducing the training time. Finally, a shallow CNN is applied to discriminate between the pre-ictal state and the inter-ictal state. Our proposed solution is evaluated on 23 patients' data from Boston Children's Hospital-MIT scalp EEG dataset by employing a leave-one-out cross-validation, and it achieves a sensitivity of 92.2% and false prediction rate of 0.12/h. Experimental result demonstrates that the proposed approach outperforms most state-of-the-art methods.

A novel dry disposable electrode using carbonized foam as conductive material is presented. The conductive material is flexible and the manufacturing of it is inexpensive. In this paper, the preparation of the conductive material and the electrical properties of the electrode are investigated. A test protocol is designed to compare the in-vitro impedance, skin-electrode interface and the signal quality of the proposed electrode with that of the wet Ag/AgCl electrode. Experimental results reveal that the carbonized foam has good flexibility and conductivity. The proposed electrode can acquire ECG signal of promising signal quality when compared with Ag/AgCl electrode in the case of static and motion. Furthermore, raw data with less power line interference was observed by proposed electrodes without noise suppression circuits or algorithms. All these make the novel electrode a promising candidate for wearable bio-potential recording.

Gait analysis is an important tool for monitoring and preventing injuries as well as to quantify functional decline in neurological diseases and elderly people. In most cases, it is more meaningful to monitor patients in natural living environments with low-end equipment such as cameras and wearable sensors. However, inertial sensors cannot provide enough details on angular dynamics. This paper presents a method that uses a single RGB camera to track the 2D joint coordinates with state-of-the-art vision algorithms. Reconstruction of the 3D trajectories uses sparse representation of an active shape model. Subsequently, we extract gait features and validate our results in comparison with a state-of-the-art commercial multi-camera tracking system. Our results are comparable to those from the current literature based on depth cameras and optical markers to extract gait characteristics.

The growth of the Internet of Things (IoT) application within the health- and wellbeing domain enables individuals to monitor their health. Acquired data can be used privately, contribute to clinical databases, or for research. The amount of health and wellbeing tracking devices introduces complexity in data aggregation and scattered overviews. Few services exist to aggregate health data. Current services raise privacy concerns. Consume is a service for aggregating authentication and authorisation for Application Programming Interfaces (APIs). Consume aims at research and allows to add existing and custom APIs on-the-fly without restarting services.

Obstructive sleep apnea (OSA) is a popular sleep disorder. Traditional OSA diagnosis methods are cumbersome and expensive, which bring inconvenience for patient diagnosis and heavy workload for physician. Automatically identifying OSA patients from electrocardiogram (ECG) records is important for clinical diagnosis and treatment. In this paper, a new method based on the frequency and network domains is proposed to automatically recognize OSA patients with nocturnal ECG records. First, each RR-interval (beat to beat heart rate) series was divided into segments. By calculating the power spectral density (PSD) of heart rate variability segment with Lomb-Scargle method, the dynamic time warping (DTW) distance was used to evaluate the similarity (dissimilarity) of the lower frequency in the PSD series, then the DTW distance matrix was transformed to a binary matrix, and then network metrics were calculated to discriminate OSA patients with healthy subjects. The new method was tested with data of 389 subjects collected from two public databases that consist of normal subjects without OSA (apnea-hypopnea index, AHI 5) and OSA patients (AHI 5). Results show that a single network metric (local clustering coefficient) can recognize OSA patients with 90.1% accuracy, 88.29% sensitivity, and 90.5% specificity, and confirm the potential of using the ECG records for OSA patients recognition.

A novel wearable sensor system for seizure monitoring of neonates comprised of smart clothing, video recording and cloud platform is presented. Textile electrodes and Inertial Measurement Unit (IMU) are embedded in the smart clothing to obtain ECG signal and motion signal whereby epileptic seizure detection algorithm is performed. Moreover, a video monitoring module provides real-time information about patients. The cloud platform receives the pre-processed data and enables remote monitoring, centralized signal processing and data management. Comparison with commercial instruments shows that the smart clothing is capable of acquiring high-quality signals. Pilot tests under disinfection operations at Children's Hospital of Fudan University confirm clinical feasibility of the proposed system. The scalability and modularity of the unobtrusive wearable front end and the design of system architecture based on cloud enable the whole system with great potential in clinical practice and home monitoring scenarios.

This paper presents the work-in-progress prototype of i-Ribbon---a wearable device designed to elicit values in the context of weight loss. Starting with an Obesity Awareness Ribbon, we introduced the i-Ribbon concept. For prototyping, we built a system that could extract user's personal health-related data through a mobile application and sent it to a wearable device. The functional prototype enabled us to implement different interaction strategies to elicit corresponding values. Base on the reflection on design and prototyping process, possibilities of future research were identified.

The papers in this special section focus on the topic of sensor informatics for mental health applications. The papers provide novel insights on advances in detection, sensing, analysis, and modeling of central and/or autonomic correlates useful in psychophysiological states assessment.

In the past decade, research on human–computer interaction has embraced psychophysiological user interfaces that enhance awareness of computers about conscious cognitive and affective states of users and increase their adaptive capabilities. Still, human experience is not limited to the levels of cognition and affect but extends further into the realm of universal instincts and innate behaviours that form the collective unconscious. Patterns of instinctual traits shape archetypes that represent images of the unconscious. This study investigated whether seven various archetypal experiences of users lead to recognisable patterns of physiological responses. More specifically, the potential of predicting the archetypal experiences by a computer from physiological data collected with wearable sensors was evaluated. The subjects were stimulated to feel the archetypal experiences and conscious emotions by means of film clips. The physiological data included measurements of cardiovascular and electrodermal activities. Statistical analysis indicated a significant relationship between the archetypes portrayed in the videos and the physiological responses. Data mining methods enabled us to create between-subject prediction models that were capable of classifying four archetypes with an accuracy of up to 57.1%. Further analysis suggested that classification performance could be improved up to 70.3% in the case of seven archetypes by using within-subject models.

Premature infants are subject to numerous interventions ranging from a simple diaper change to surgery while residing in neonatal intensive care units. These neonates often suffer from pain, distress, and discomfort during the first weeks of their lives. Although pharmacological pain treatment often is available, it cannot always be applied to relieve a neonate from pain or discomfort. This paper describes a nonpharmacological solution, called Mimo, which provides comfort through mediation of a parent's physiological features to the distressed neonate via an intelligent pillow system embedded with sensing and actuating functions. We present the design, the implementation, and the evaluation of the prototype. Clinical tests at Máxima Medical Center in the Netherlands show that among the nine of ten infants who showed discomfort following diaper change, a shorter recovery time to baseline skin conductance analgesimeter values could be measured when the maternal heartbeat vibration in the Mimo was switched ON and in seven of these ten a shorter crying time was measured.

Abstract: Instruction in physics aims at achieving two goals: the acquisition of body of knowledge and problem solving skills in physics. This requires students to connect physical phenomena, physics principles, and physics sym-bols. Computer simulation provides students with graphical model that unites phenomenon and principles in physics. However, such minimally guided approach may harm learning since it overburdens the working mem-ory. Also, simulation is inadequate in promoting problem solving skills since students need to exercise with a variety of physics problems. Intelligent tutoring systems (ITS), in contrast, train students in solving physics problems. In this paper, we designed an online puzzle game in physics that combines simulation and pseudo-tutor (namely QTut). We addressed three challenges: extensibility, scalability, and reusability in designing our game. We conducted usability tests with 10 participants on the game prototype to study the user performances and perceptions for improvement. The results indicate the game as educative and moderately entertaining. The use of scaffolding in the game positively contributed to the game learning experience. Moreover, the game GUI expressed information well that made the game understandable, even with little instructions. 1

Lifelogging tools aim to precisely capture daily experiences of people from the first-person perspective. Although there have been numerous lifelogging tools developed for users to record the external environment around them, the internal part of experience characterized by emotions seems to be neglected in the lifelogging field. However, the internal experiences of people are important and, therefore, lifelogging tools should be able to capture not only the environmental data, but also emotional experiences, thereby providing a more complete archive of past events. Moreover, there are implicit emotions that cannot be consciously experienced, but still influence human behaviors and memories. It has been proven that conscious emotions can be recognized from physiological signals of the human body. This fact may be used to enhance life-logs with information about unconscious emotions, which otherwise would remain hidden. On the other hand, it is not clear if unconscious emotions can be recognized from physiological signals and differentiated from conscious emotions. Therefore, an experiment was designed to elicit emotions (both conscious and unconscious) with visual and auditory stimuli and to record cardiovascular responses of 34 participants. The experimental results showed that heart rate responses to the presentation of the stimuli are unique for every category of the emotional stimuli and allow differentiation between various emotional experiences of the participants.

Critically ill prematurely born babies admitted at the neonatal intensive care unit (NICU) have to be monitored constantly. The saturation of the peripheral oxygen (SPO2) is one of the crucial monitoring parameters on these babies. It is necessary that these fragile neonates feel most comfortable as possible during the monitoring. The current solutions for these SPO2 oximeters can be uncomfortable for use and hampers parent-child interaction. In this paper we propose an innovative solution for reflectance pulse oximeter based on Near Infrared Spectroscopy (NIRS) techniques that will lead into more comfortable use in a long term monitoring. Prototypes with the reflectance sensors embedded in soft foam and fabric materials are built to enhance a comfortable non-invasive yet reliable monitoring. These monitoring units give the opportunity of integration into a snuggle and mattress where the baby lays on most of the time. In this paper we report the integration of the prototype monitoring units into a snuggle. To evaluate the comfort as well as performance of the final prototype, we first conduct tests on adults. The prototype monitoring units are tested on various body locations of adult participants. Signal quality on different body locations is reported and questionnaires for comfort assessment are analyzed. Experiments on the premature babies will be carried out at NICU of Máxima Medical Centre (MMC) in Veldhoven, the Netherlands.

Blood oxygen saturation is one of the key parameters for health monitoring of premature infants at the neonatal intensive care unit (NICU). In this paper, we propose and demonstrate a design of a wearable wireless blood saturation monitoring system. Reflectance pulse oxymeter based on Near Infrared Spectroscopy (NIRS) techniques are applied for enhancing the flexibility of measurements at different locations on the body of the neonates and the compatibility to be integrated into a non-invasive monitoring platform, such as a neonatal smart jacket. Prototypes with the reflectance sensors embedded in soft fabrics are built. The thickness of device is minimized to optimize comfort. To evaluate the performance of the prototype, experiments on the premature babies were carried out at NICU of Ma¿xima Medical Centre (MMC) in Veldhoven, the Netherlands. The results show that the heart rate and SpO2measured by the proposed design are corresponding to the readings of the standard monitor.

During the stress of cardiopulmonary resuscitation (CPR), it is difficult to maintain the right rhythm and correct ratio of insufflations to chest compressions and to exert the compressions at a constant pressure. In this paper, we propose and demonstrate an integrated sensor system-the "Rhythm of Life Aid" (ROLA) to support medical staff during CPR of newborn infants. The design concept is based on interactive audio and visual feedback with consideration of functionalities and user friendliness. A prototype ROLA device is built, consisting of a transparent foil integrated with pressure sensor and electroluminescent foil actuators for indication of the exerted chest compression pressure, as well as an audio box to generate distinctive sounds as audio guidance for insufflations and compressions. To evaluate the performance of the ROLA device, a sensory mannequin and a dedicated software interface are implemented to give immediate feedback and record data for further processing. Tests of the ROLA prototype on the sensory mannequin by ten pairs of a doctor and a nurse at Máxima Medical Centre in Veldhoven, The Netherlands show that the use of ROLA device achieves a more constant rhythm and pressure of chest compressions during CPR of newborn infants.