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 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.

Heart sounds deliver vital physiological and pathological evidence about health. Wireless cardiac auscultation offers continuous cardiac monitoring of an individual without 24*7 manual healthcare care services. In this paper, a novel wireless sensing system to monitor and analyze cardiac condition is proposed, which sends the information to the caregiver as well as a medical practitioner with an application of the Internet of Things (IoT). An integrated system for heart sound acquisition, storage, asynchronous analysis has been developed, from scratch to information uploading through IoT and signal analysis. Cardiac auscultation sensing unit has been designed to monitor cardiovascular health of an individual. Bluetooth protocol is used to offer power efficiency and moderate data transmission rate. The Hilbert-Huang transform is used to eliminate interference signals and to help to extract the heart sound signal features. Subsequence segmentation algorithm based on double-threshold has been developed to extract physiological parameters. Preprocessing, segmentation and clustering technique were performed for significant health information interpretation. The cardiac auscultation monitoring system may provide a way for heart disease self-management.

In recent years, automatic sleep staging methods have achieved competitive performance using electroencephalography (EEG) signals. However, the acquisition of EEG signals is cumbersome and inconvenient. Therefore, we propose a novel sleep staging approach using electrooculogram (EOG) signals, which are more convenient to acquire than the EEG. A two-scale convolutional neural network first extracts epoch-wise temporary-equivalent features from raw EOG signals. A recurrent neural network then captures the long-term sequential information. The proposed method was validated on 101 full-night sleep data from two open-access databases, the montreal archive of sleep studies and Sleep-EDF, achieving an overall accuracy of 81.2 and 76.3%, respectively. The results are comparable to those models trained with EEG signals. In addition, comparisons with six state-of-the-art methods further demonstrate the effectiveness of the proposed approach. Overall, this study provides a new avenue for sleep monitoring.

Background: Ambiguities and anomalies in the Activity of Daily Living (ADL) patterns indicate deviations from Wellness. The monitoring of lifestyles could facilitate remote physicians or caregivers to give insight into symptoms of the disease and provide health improvement advice to residents; Objective: This research work aims to apply lifestyle monitoring in an ambient assisted living (AAL) system by diagnosing conduct and distinguishing variation from the norm with the slightest conceivable fake alert. In pursuing this aim, the main objective is to fill the knowledge gap of two contextual observations (i.e., day and time) in the frequent behavior modeling for an individual in AAL. Each sensing category has its advantages and restrictions. Only a single type of sensing unit may not manage composite states in practice and lose the activity of daily living. To boost the efficiency of the system, we offer an exceptional sensor data fusion technique through different sensing modalities; Methods: As behaviors may also change according to other contextual observations, including seasonal, weather (or temperature), and social interaction, we propose the design of a novel activity learning model by adding behavioral observations, which we name as the Wellness indices analysis model; Results: The ground-truth data are collected from four elderly houses, including daily activities, with a sample size of three hundred days plus sensor activation. The investigation results validate the success of our method. The new feature set from sensor data fusion enhances the system accuracy to (98.17% ± 0.95) from (80.81% ± 0.68). The performance evaluation parameters of the proposed model for ADL recognition are recorded for the 14 selected activities. These parameters are Sensitivity (0.9852), Specificity (0.9988), Accuracy (0.9974), F1 score (0.9851), False Negative Rate (0.0130).

Objective: Classification of sleep-wake states using multichannel electroencephalography (EEG) data that reliably work for neonates. Methods: A deep multilayer perceptron (MLP) neural network is developed to classify sleep-wake states using multichannel bipolar EEG signals, which takes an input vector of size 108 containing the joint features of 9 channels. The network avoids any post-processing step in order to work as a full-fledged real-time application. For training and testing the model, EEG recordings of 3525 30-second segments from 19 neonates (postmenstrual age of 37 ± 05 weeks) are used. Results: For sleep-wake classification, mean Cohen’s kappa between the network estimate and the ground truth annotation by human experts is 0.62. The maximum mean accuracy can reach up to 83% which, to date, is the highest accuracy for sleep-wake classification.