Heart rate is a crucial indicator of human health with significant physiological importance. Traditional contact methods for measuring heart rate, such as electrocardiograph or wristbands, may not always meet the need for convenient health monitoring. Remote photoplethysmography (rPPG) provides a non-contact method for measuring heart rate and other physiological indicators by analyzing blood volume pulse signals. This approach is non-invasive, does not require direct contact, and allows for long-term healthcare monitoring. Deep learning has emerged as a powerful tool for processing complex image and video data, and has been increasingly employed to extract heart rate signals remotely. This article reviewed the latest research advancements in rPPG-based heart rate measurement using deep learning, summarized available public datasets, and explored future research directions and potential advancements in non-contact heart rate measurement.
Humans ; Deep Learning ; Heart Rate/physiology* ; Photoplethysmography/methods* ; Video Recording ; Face ; Monitoring, Physiologic/methods* ; Signal Processing, Computer-Assisted

Motor imagery (MI) is a mental process that can be recognized by electroencephalography (EEG) without actual movement. It has significant research value and application potential in the field of brain-computer interface (BCI) technology. To address the challenges posed by the non-stationary nature and low signal-to-noise ratio of MI-EEG signals, this study proposed a Riemannian spatial filtering and domain adaptation (RSFDA) method for improving the accuracy and efficiency of cross-session MI-BCI classification tasks. The approach addressed the issue of inconsistent data distribution between source and target domains through a multi-module collaborative framework, which enhanced the generalization capability of cross-session MI-EEG classification models. Comparative experiments were conducted on three public datasets to evaluate RSFDA against eight existing methods in terms of classification accuracy and computational efficiency. The experimental results demonstrated that RSFDA achieved an average classification accuracy of 79.37%, outperforming the state-of-the-art deep learning method Tensor-CSPNet (76.46%) by 2.91% ( P < 0.01). Furthermore, the proposed method showed significantly lower computational costs, requiring only approximately 3 minutes of average training time compared to Tensor-CSPNet's 25 minutes, representing a reduction of 22 minutes. These findings indicate that the RSFDA method demonstrates superior performance in cross-session MI-EEG classification tasks by effectively balancing accuracy and efficiency. However, its applicability in complex transfer learning scenarios remains to be further investigated.
Electroencephalography/methods* ; Brain-Computer Interfaces ; Humans ; Imagination/physiology* ; Signal Processing, Computer-Assisted ; Movement/physiology* ; Signal-To-Noise Ratio ; Deep Learning ; Algorithms

This paper realized a portable brain-computer interface (BCI) system tailored for smart healthcare. Through the decoding of steady-state visual evoked potential (SSVEP), this system can rapidly and accurately identify the intentions of subjects, thereby meeting the practical demands of daily medical scenarios. Firstly, an SSVEP stimulation interface and an electroencephalogram (EEG) signal acquisition software were designed, which enable the system to execute multi-target and multi-task operations while also incorporating data visualization functionality. Secondly, the EEG signals recorded from the occipital region were decomposed into eight sub-frequency bands using filter bank canonical correlation analysis (FBCCA). Subsequently, the similarity between each sub-band signal and the reference signals was computed to achieve efficient SSVEP decoding. Finally, 15 subjects were recruited to participate in the online evaluation of the system. The experimental results indicated that in real-world scenarios, the system achieved an average accuracy of 85.19% in identifying the intentions of the subjects, and an information transfer rate (ITR) of 37.52 bit/min. This system was awarded third prize in the Visual BCI Innovation Application Development competition at the 2024 World Robot Contest, validating its effectiveness. In conclusion, this study has developed a portable, multifunctional SSVEP online decoding system, providing an effective approach for human-computer interaction in smart healthcare.
Brain-Computer Interfaces ; Humans ; Evoked Potentials, Visual/physiology* ; Electroencephalography ; Signal Processing, Computer-Assisted ; Software ; Adult ; Male

Brain-computer interface (BCI) has high application value in the field of healthcare. However, in practical clinical applications, convenience and system performance should be considered in the use of BCI. Wearable BCIs are generally with high convenience, but their performance in real-life scenario needs to be evaluated. This study proposed a wearable steady-state visual evoked potential (SSVEP)-based BCI system equipped with a small-sized electroencephalogram (EEG) collector and a high-performance training-free decoding algorithm. Ten healthy subjects participated in the test of BCI system under simplified experimental preparation. The results showed that the average classification accuracy of this BCI was 94.10% for 40 targets, and there was no significant difference compared to the dataset collected under the laboratory condition. The system achieved a maximum information transfer rate (ITR) of 115.25 bit/min with 8-channel signal and 98.49 bit/min with 4-channel signal, indicating that the 4-channel solution can be used as an option for the few-channel BCI. Overall, this wearable SSVEP-BCI can achieve good performance in real-life scenario, which helps to promote BCI technology in clinical practice.
Brain-Computer Interfaces ; Humans ; Evoked Potentials, Visual/physiology* ; Electroencephalography ; Wearable Electronic Devices ; Algorithms ; Signal Processing, Computer-Assisted ; Adult ; Male

Fatigue driving is one of the leading causes of traffic accidents, posing a significant threat to drivers and road safety. Most existing methods focus on studying whole-brain multi-channel electroencephalogram (EEG) signals, which involve a large number of channels, complex data processing, and cumbersome wearable devices. To address this issue, this paper proposes a fatigue detection method based on frontal EEG signals and constructs a fatigue driving detection model using an asymptotic hierarchical fusion network. The model employed a hierarchical fusion strategy, integrating an attention mechanism module into the multi-level convolutional module. By utilizing both cross-attention and self-attention mechanisms, it effectively fused the hierarchical semantic features of power spectral density (PSD) and differential entropy (DE), enhancing the learning of feature dependencies and interactions. Experimental validation was conducted on the public SEED-VIG dataset. The proposed model achieved an accuracy of 89.80% using only four frontal EEG channels. Comparative experiments with existing methods demonstrate that the proposed model achieves high accuracy and superior practicality, providing valuable technical support for fatigue driving monitoring and prevention.
Humans ; Electroencephalography/methods* ; Automobile Driving ; Fatigue/diagnosis* ; Accidents, Traffic/prevention & control* ; Signal Processing, Computer-Assisted ; Neural Networks, Computer ; Algorithms ; Prefrontal Cortex/physiology*

Multi-task learning (MTL) has demonstrated significant advantages in the field of physiological signal measurement. This approach enhances the model's generalization ability by sharing parameters and features between similar tasks, even in data-scarce environments. However, traditional multi-task physiological signal measurement methods face challenges such as feature conflicts between tasks, task imbalance, and excessive model complexity, which limit their application in complex environments. To address these issues, this paper proposes an enhanced multi-scale spatiotemporal network (EMSTN) based on Eulerian video magnification (EVM), super-resolution reconstruction and convolutional multilayer perceptron. First, EVM is introduced in the input stage of the network to amplify subtle color and motion changes in the video, significantly improving the model's ability to capture pulse and respiratory signals. Additionally, a super-resolution reconstruction module is integrated into the network to enhance the image resolution, thereby improving detail capture and increasing the accuracy of facial action unit (AU) tasks. Then, convolutional multilayer perceptron is employed to replace traditional 2D convolutions, improving feature extraction efficiency and flexibility, which significantly boosts the performance of heart rate and respiratory rate measurements. Finally, comprehensive experiments on the Binghamton-Pittsburgh 4D Spontaneous Facial Expression Database (BP4D+) fully validate the effectiveness and superiority of the proposed method in multi-task physiological signal measurement.
Humans ; Neural Networks, Computer ; Signal Processing, Computer-Assisted ; Face/physiology* ; Video Recording ; Facial Expression ; Heart Rate ; Algorithms

Meditation aims to guide individuals into a state of deep calm and focused attention, and in recent years, it has shown promising potential in the field of medical treatment. Numerous studies have demonstrated that electroencephalogram (EEG) patterns change during meditation, suggesting the feasibility of using deep learning techniques to monitor meditation states. However, significant inter-subject differences in EEG signals poses challenges to the performance of such monitoring systems. To address this issue, this study proposed a novel model-calibrated multi-source adversarial adaptation network (CMAAN). The model first trained multiple domain-adversarial neural networks in a pairwise manner between various source-domain individuals and the target-domain individual. These networks were then integrated through a calibration process using a small amount of labeled data from the target domain to enhance performance. We evaluated the proposed model on an EEG dataset collected from 18 subjects undergoing methamphetamine rehabilitation. The model achieved a classification accuracy of 73.09%. Additionally, based on the learned model, we analyzed the key EEG frequency bands and brain regions involved in the meditation process. The proposed multi-source domain adaptation framework improves both the performance and robustness of EEG-based meditation monitoring and holds great promise for applications in biomedical informatics and clinical practice.
Humans ; Electroencephalography/methods* ; Meditation ; Calibration ; Neural Networks, Computer ; Brain/physiology* ; Rest/physiology* ; Deep Learning ; Signal Processing, Computer-Assisted

Convolutional neural networks (CNNs) are renowned for their excellent representation learning capabilities and have become a mainstream model for motor imagery based electroencephalogram (MI-EEG) signal classification. However, MI-EEG exhibits strong inter-individual variability, which may lead to a decline in classification performance. To address this issue, this paper proposes a classification model based on dynamic multi-scale CNN and multi-head temporal attention (DMSCMHTA). The model first applies multi-band filtering to the raw MI-EEG signals and inputs the results into the feature extraction module. Then, it uses a dynamic multi-scale CNN to capture temporal features while adjusting attention weights, followed by spatial convolution to extract spatiotemporal feature sequences. Next, the model further optimizes temporal correlations through time dimensionality reduction and a multi-head attention mechanism to generate more discriminative features. Finally, MI classification is completed under the supervision of cross-entropy loss and center loss. Experiments show that the proposed model achieves average accuracies of 80.32% and 90.81% on BCI Competition IV datasets 2a and 2b, respectively. The results indicate that DMSCMHTA can adaptively extract personalized spatiotemporal features and outperforms current mainstream methods.
Electroencephalography/methods* ; Humans ; Neural Networks, Computer ; Brain-Computer Interfaces ; Attention ; Signal Processing, Computer-Assisted ; Imagination/physiology* ; Algorithms

Electroencephalogram (EEG) serves as an effective indicator of detecting fatigue driving. Utilizing the open accessible Shanghai Jiao Tong University Emotion Electroencephalography Dataset (SEED-VIG), driving states are divided into three categories including awake, tired and drowsy for investigation. Given the characteristics of mutual influence and interdependence among EEG channels, as well as the consistency of the graph convolutional neural network (GCNN) structure, we designed an adjacency matrix based on the Pearson correlation coefficients of EEG signals among channels and their positional relationships. Subsequently, we developed a GCNN for recognition. The experimental results show that the average classification accuracy of driving state categories for 20 subjects, from the SEED-VIG dataset under the smooth feature of differential entropy (DE) linear dynamic system is 91.66%. Moreover, the highest classification accuracy can reach 98.87%, and the average Kappa coefficient is 0.83. This work demonstrates the reliability of this method and provides a guideline for the research field of safe driving brain computer interface.
Humans ; Electroencephalography/methods* ; Neural Networks, Computer ; Fatigue/physiopathology* ; Automobile Driving ; Brain-Computer Interfaces ; Signal Processing, Computer-Assisted ; Convolutional Neural Networks

The existing epilepsy seizure detection algorithms have problems such as overfitting and poor generalization ability due to high reliance on manual labeling of electroencephalogram's data and data imbalance between seizure and interictal periods. An unsupervised learning detection method for epileptic seizure that jointed graph attention network (GAT) and Transformer framework (GAT-T) was proposed. In this method, channel correlations were adaptively learned by GAT encoder. Temporal information was captured by one-dimensional convolution decoder. Combining outputs of the two mentioned above, predicted values for electroencephalogram were generated. The collective anomaly score was calculated and the detection threshold was determined. The results demonstrated that GAT-T achieved the average performance exceeding 90% (or 99%) with a 0.25 s (or 2 s) time segment length, which could effectively detect epileptic seizures. Moreover, the channel association probability matrix was expected to assist clinicians in the initial screening of the epileptogenic zone, and ablation experiments also reflected the significance of each module in GAT-T. This study may assist clinicians in making more accurate diagnostic and therapeutic decisions for epilepsy patients.
Humans ; Electroencephalography/methods* ; Epilepsy/physiopathology* ; Algorithms ; Seizures/physiopathology* ; Neural Networks, Computer ; Signal Processing, Computer-Assisted