Characteristics of physical movements are indicative of infants’ neuro-motor development and brain dysfunction. For instance, infant seizure, a clinical signal of brain dysfunction, could be identified and predicted by monitoring its physical movements. With the advance of wearable sensor technology, including the miniaturization of sensors, and the increasing broad application of micro- and nanotechnology, and smart fabrics in wearable sensor systems, it is now possible to collect, store, and process multimodal signal data of infant movements in a more efficient, more comfortable, and non-intrusive way. This review aims to depict the state-of-the-art of wearable sensor systems for infant movement monitoring. We also discuss its clinical significance and the aspect of system design.

For infants admitted at neonatal intensive care unit, the continuous monitoring of health parameters is critical for their optimal treatment and outcomes. So it’s crucial to provide proper treatment, accurate and comfortable monitoring conditions for newborn infants. In this paper, we propose wearable sensor systems integrated with flexible material based non-invasive sensors for neonatal monitoring. The system aims at providing reliable vital signs monitoring as well as comfortable clinical en vironments for neonatal care. The system consists of a smart vest and a cloud platform. In the smart vest, a novel stretching sensor based on Polydimethylsiloxane-Graphene (PDMS-Graphene) compound is created to detect newborns’ respiration signal; textile-based dry electrodes are developed to measure Electrocardiograph (ECG) signals; inertial measurement units (IMUs) are embedded to obtain movement information including accelerated speed and angular velocity of newborn wrists. Experiments were conducted to systematically test the sensing related characteristics of the aforementioned flexible materials and the performance of the proposed multi-sensor platform. The results show that the proposed system can achieve high quality signals. The wearable sensor platform is promising for continuous long term monitoring of neonates. The multimodal physiological and behavioral signals measured by the platform can be further processed for clinical decision support on the neonatal health status.

Sleep staging is the essential step in sleep quality assessment and sleep disorders diagnosis. However, most current automatic sleep staging approaches use recurrent neural networks (RNN), resulting in a relatively large training burden. Moreover, these methods only extract information of the whole epoch or adjacent epochs, ignoring the local signal variations within epoch. To address these issues, a novel deep learning architecture named segmented attention network (SAN) is proposed in this paper. The architecture can be divided into feature extraction (FE) and time sequence encoder (TSE). The FE module consists of multiple multiscale CNN (MMCNN) and residual squeeze and excitation block (SE block). The former extracts features from multiple equal-length EEG segments and the latter reinforced the features. The TSE module based on a multi-head attention mechanism could capture the temporal information in the features extracted by FE module. Noteworthy, in SAN, we replaced the RNN module with a TSE module for temporal learning and made the network faster. The evaluation of the model was performed on two widely used public datasets, Montreal Archive of Sleep Studies (MASS) and Sleep-EDFX, and one clinical dataset from Huashan Hospital of Fudan University, Shanghai, China (HSFU). The proposed model achieved the accuracy of 85.5%, 86.4%, 82.5% on Sleep-EDFX, MASS and HSFU, respectively. The experimental results exhibited favorable performance and consistent improvements of SAN on different datasets in comparison with the state-of-the-art studies. It also proved the necessity of sleep staging by integrating the local characteristics within epochs and adjacent informative features among epochs.

EEG, which can provide brain alteration information via recording the electrical activity of neurons in the cerebral cortex, has been widely used in neurophysiology. However, conventional wet electrodes in EEG monitoring typically suffer from inherent limitations, including the requirement of skin pretreatment, the risk of superficial skin infections, and signal performance deterioration that may occur over time due to the air drying of the conductive gel. Although the emergence of dry electrodes has overcome these shortcomings, their electrode–skin contact impedance is significantly high and unstable, especially in hair-covered areas. To address the above problems, an active claw-shaped dry electrode is designed, moving from electrode morphological design, slurry preparation, and coating to active electrode circuit design. The active claw-shaped dry electrode, which consists of a claw-shaped electrode and active electrode circuit, is dedicated to offering a flexible solution for elevating electrode fittings on the scalp in hair-covered areas, reducing electrode–skin contact impedance and thus improving the quality of the acquired EEG signal. The performance of the proposed electrodes was verified by impedance, active electrode circuit, eyes open-closed, steady-state visually evoked potential (SSVEP), and anti-interference tests, based on EEG signal acquisition. Experimental results show that the proposed claw-shaped electrodes (without active circuit) can offer a better fit between the scalp and electrodes, with a low electrode–skin contact impedance (18.62 KΩ@1 Hz in the hairless region and 122.15 KΩ@1 Hz in the hair-covered region). In addition, with the active circuit, the signal-to-noise ratio (SNR) of the acquiring EEG signal was improved and power frequency interference was restrained, therefore, the proposed electrodes can yield an EEG signal quality comparable to wet electrodes.

Accurate sleep staging for patients with sleep disorders requires the integration of multiple channels and various signal modalities. While Graph Convolutional Networks (GCNs) have significantly improved sleep staging accuracy by effectively processing complex data, current GCN-based methods often require a large number of signal channels and struggle to capture temporal correlations effectively. They are leading to a large limitation in the scope of graph network models in sleep staging. To address these challenges, we propose an attention based Spatial-Temporal Graph Network for sleep staging, named ASTGSleep. ASTGSleep effectively addresses the temporal continuity of sleep data and overcomes limitations related to the number of channels by integrating the Temporal Graph Construction and Feature Extraction Module (TGFEM). TGFEM captures dynamic temporal features through temporal graph construction, complementing spatial features and enhancing sensitivity to sleep stage transitions. Moreover, the Multi-Dimensional Fusion Module (MDFM) optimizes and fuses these spatio-temporal features using a graph attention network, further improving accuracy and robustness in sleep staging. Experimental results demonstrate that ASTGSleep achieves competitive accuracy on datasets with different numbers of channels, such as MASSSS3 with 26 channels (87.0%) and SleepEDF-20 with 3 channels (86.5%). Furthermore, its performance on sleep disorder datasets, including CAP (81.4%) and clinical CZ-RBD (82.7%), shows robust generalization and enhanced accuracy, making it a promising tool for automatic sleep staging in clinical diagnostics.