Search

For the increasing number of patients with depression, this paper proposes an artificial intelligence method to effectively identify depression through voice signals, with the aim of improving the efficiency of diagnosis and treatment. Firstly, a pre-training model called wav2vec 2.0 is fine-tuned to encode and contextualize the speech, thereby obtaining high-quality voice features. This model is applied to the publicly available dataset - the distress analysis interview corpus-wizard of OZ (DAIC-WOZ). The results demonstrate a precision rate of 93.96%, a recall rate of 94.87%, and an F1 score of 94.41% for the binary classification task of depression recognition, resulting in an overall classification accuracy of 96.48%. For the four-class classification task evaluating the severity of depression, the precision rates are all above 92.59%, the recall rates are all above 92.89%, the F1 scores are all above 93.12%, and the overall classification accuracy is 94.80%. The research findings indicate that the proposed method effectively enhances classification accuracy in scenarios with limited data, exhibiting strong performance in depression identification and severity evaluation. In the future, this method has the potential to serve as a valuable supportive tool for depression diagnosis.

Parkinson's disease patients have early vocal cord damage, and their voiceprint characteristics differ significantly from those of healthy individuals, which can be used to identify Parkinson's disease. However, the samples of the voiceprint dataset of Parkinson's disease patients are insufficient, so this paper proposes a double self-attention deep convolutional generative adversarial network model for sample enhancement to generate high-resolution spectrograms, based on which deep learning is used to recognize Parkinson's disease. This model improves the texture clarity of samples by increasing network depth and combining gradient penalty and spectral normalization techniques, and a family of pure convolutional neural networks (ConvNeXt) classification network based on Transfer learning is constructed to extract voiceprint features and classify them, which improves the accuracy of Parkinson's disease recognition. The validation experiments of the effectiveness of this paper's algorithm are carried out on the Parkinson's disease speech dataset. Compared with the pre-sample enhancement, the clarity of the samples generated by the proposed model in this paper as well as the Fréchet inception distance (FID) are improved, and the network model in this paper is able to achieve an accuracy of 98.8%. The results of this paper show that the Parkinson's disease recognition algorithm based on double self-attention deep convolutional generative adversarial network sample enhancement can accurately distinguish between healthy individuals and Parkinson's disease patients, which helps to solve the problem of insufficient samples for early recognition of voiceprint data in Parkinson's disease. In summary, the method effectively improves the classification accuracy of small-sample Parkinson's disease speech dataset and provides an effective solution idea for early Parkinson's disease speech diagnosis.

Sleep stage classification is essential for clinical disease diagnosis and sleep quality assessment. Most of the existing methods for sleep stage classification are based on single-channel or single-modal signal, and extract features using a single-branch, deep convolutional network, which not only hinders the capture of the diversity features related to sleep and increase the computational cost, but also has a certain impact on the accuracy of sleep stage classification. To solve this problem, this paper proposes an end-to-end multi-modal physiological time-frequency feature extraction network (MTFF-Net) for accurate sleep stage classification. First, multi-modal physiological signal containing electroencephalogram (EEG), electrocardiogram (ECG), electrooculogram (EOG) and electromyogram (EMG) are converted into two-dimensional time-frequency images containing time-frequency features by using short time Fourier transform (STFT). Then, the time-frequency feature extraction network combining multi-scale EEG compact convolution network (Ms-EEGNet) and bidirectional gated recurrent units (Bi-GRU) network is used to obtain multi-scale spectral features related to sleep feature waveforms and time series features related to sleep stage transition. According to the American Academy of Sleep Medicine (AASM) EEG sleep stage classification criterion, the model achieved 84.3% accuracy in the five-classification task on the third subgroup of the Institute of Systems and Robotics of the University of Coimbra Sleep Dataset (ISRUC-S3), with 83.1% macro F1 score value and 79.8% Cohen's Kappa coefficient. The experimental results show that the proposed model achieves higher classification accuracy and promotes the application of deep learning algorithms in assisting clinical decision-making.

The pace of modern life is accelerating, the pressure of life is gradually increasing, and the long-term accumulation of mental fatigue poses a threat to health. By analyzing physiological signals and parameters, this paper proposes a method that can identify the state of mental fatigue, which helps to maintain a healthy life. The method proposed in this paper is a new recognition method of psychological fatigue state of electrocardiogram signals based on convolutional neural network and long short-term memory. Firstly, the convolution layer of one-dimensional convolutional neural network model is used to extract local features, the key information is extracted through pooling layer, and some redundant data is removed. Then, the extracted features are used as input to the long short-term memory model to further fuse the ECG features. Finally, by integrating the key information through the full connection layer, the accurate recognition of mental fatigue state is successfully realized. The results show that compared with traditional machine learning algorithms, the proposed method significantly improves the accuracy of mental fatigue recognition to 96.3%, which provides a reliable basis for the early warning and evaluation of mental fatigue.

The multi-window time-frequency reassignment helps to improve the time-frequency resolution of bark-frequency spectral coefficient (BFSC) analysis of heart sounds. For this purpose, a new heart sound classification algorithm combining feature extraction based on multi-window time-frequency reassignment BFSC with deep learning was proposed in this paper. Firstly, the randomly intercepted heart sound segments are preprocessed with amplitude normalization, the heart sounds were framed and time-frequency rearrangement based on short-time Fourier transforms were computed using multiple orthogonal windows. A smooth spectrum estimate is calculated by arithmetic averaging each of the obtained independent spectra. Finally, the BFSC of reassignment spectrum is extracted as a feature by the Bark filter bank. In this paper, convolutional network and recurrent neural network are used as classifiers for model comparison and performance evaluation of the extracted features. Eventually, the multi-window time-frequency rearrangement improved BFSC method extracts more discriminative features, with a binary classification accuracy of 0.936, a sensitivity of 0.946, and a specificity of 0.922. These results present that the algorithm proposed in this paper does not need to segment the heart sounds and randomly intercepts the heart sound segments, which greatly simplifies the computational process and is expected to be used for screening of congenital heart disease.

The task of automatic generation of medical image reports faces various challenges, such as diverse types of diseases and a lack of professionalism and fluency in report descriptions. To address these issues, this paper proposes a multimodal medical imaging report based on memory drive method (mMIRmd). Firstly, a hierarchical vision transformer using shifted windows (Swin-Transformer) is utilized to extract multi-perspective visual features of patient medical images, and semantic features of textual medical history information are extracted using bidirectional encoder representations from transformers (BERT). Subsequently, the visual and semantic features are integrated to enhance the model's ability to recognize different disease types. Furthermore, a medical text pre-trained word vector dictionary is employed to encode labels of visual features, thereby enhancing the professionalism of the generated reports. Finally, a memory driven module is introduced in the decoder, addressing long-distance dependencies in medical image data. This study is validated on the chest X-ray dataset collected at Indiana University (IU X-Ray) and the medical information mart for intensive care chest x-ray (MIMIC-CXR) released by the Massachusetts Institute of Technology and Massachusetts General Hospital. Experimental results indicate that the proposed method can better focus on the affected areas, improve the accuracy and fluency of report generation, and assist radiologists in quickly completing medical image report writing.

Lung cancer is one of the malignant tumors with the greatest threat to human health, and studies have shown that some genes play an important regulatory role in the occurrence and development of lung cancer. In this paper, a LightGBM ensemble learning method is proposed to construct a prognostic model based on immune relate gene (IRG) profile data and clinical data to predict the prognostic survival rate of lung adenocarcinoma patients. First, this method used the Limma package for differential gene expression, used CoxPH regression analysis to screen the IRG to prognosis, and then used XGBoost algorithm to score the importance of the IRG features. Finally, the LASSO regression analysis was used to select IRG that could be used to construct a prognostic model, and a total of 17 IRG features were obtained that could be used to construct model. LightGBM was trained according to the IRG screened. The K-means algorithm was used to divide the patients into three groups, and the area under curve (AUC) of receiver operating characteristic (ROC) of the model output showed that the accuracy of the model in predicting the survival rates of the three groups of patients was 96%, 98% and 96%, respectively. The experimental results show that the model proposed in this paper can divide patients with lung adenocarcinoma into three groups [5-year survival rate higher than 65% (group 1), lower than 65% but higher than 30% (group 2) and lower than 30% (group 3)] and can accurately predict the 5-year survival rate of lung adenocarcinoma patients.

Physiological studies have revealed that rats perform spatial localization relying on grid cells and place cells in the entorhinal-hippocampal CA3 structure. The dynamic connection between the entorhinal-hippocampal structure and the prefrontal cortex is crucial for navigation. Based on these findings, this paper proposes a spatial navigation method based on the entorhinal-hippocampal-prefrontal information transmission circuit of the rat's brain, with the aim of endowing the mobile robot with strong spatial navigation capability. Using the hippocampal CA3-prefrontal spatial navigation model as a foundation, this paper constructed a dynamic self-organizing model with the hippocampal CA1 place cells as the basic unit to optimize the navigation path. The path information was then fed back to the impulse neural network via hippocampal CA3 place cells and prefrontal cortex action neurons, improving the convergence speed of the model and helping to establish long-term memory of navigation habits. To verify the validity of the method, two-dimensional simulation experiments and three-dimensional simulation robot experiments were designed in this paper. The experimental results showed that the method presented in this paper not only surpassed other algorithms in terms of navigation efficiency and convergence speed, but also exhibited good adaptability to dynamic navigation tasks. Furthermore, our method can be effectively applied to mobile robots.

Identification of molecular subtypes of malignant tumors plays a vital role in individualized diagnosis, personalized treatment, and prognosis prediction of cancer patients. The continuous improvement of comprehensive tumor genomics database and the ongoing breakthroughs in deep learning technology have driven further advancements in computer-aided tumor classification. Although the existing classification methods based on gene expression omnibus database take the complexity of cancer molecular classification into account, they ignore the internal correlation and synergism of genes. To solve this problem, we propose a multi-layer graph convolutional network model for breast cancer subtype classification combined with hierarchical attention network. This model constructs the graph embedding datasets of patients' genes, and develops a new end-to-end multi-classification model, which can effectively recognize molecular subtypes of breast cancer. A large number of test data prove the good performance of this new model in the classification of breast cancer subtypes. Compared to the original graph convolutional neural networks and two mainstream graph neural network classification algorithms, the new model has remarkable advantages. The accuracy, weight-F1-score, weight-recall, and weight-precision of our model in seven-category classification has reached 0.851 7, 0.823 5, 0.851 7 and 0.793 6 respectively. In the four-category classification, the results are 0.928 5, 0.894 9, 0.928 5 and 0.865 0 respectively. In addition, compared with the latest breast cancer subtype classification algorithms, the method proposed in this paper also achieved the highest classification accuracy. In summary, the model proposed in this paper may serve as an auxiliary diagnostic technology, providing a reliable option for precise classification of breast cancer subtypes in the future and laying the theoretical foundation for computer-aided tumor classification.

The conventional fault diagnosis of patient monitors heavily relies on manual experience, resulting in low diagnostic efficiency and ineffective utilization of fault maintenance text data. To address these issues, this paper proposes an intelligent fault diagnosis method for patient monitors based on multi-feature text representation, improved bidirectional gate recurrent unit (BiGRU) and attention mechanism. Firstly, the fault text data was preprocessed, and the word vectors containing multiple linguistic features was generated by linguistically-motivated bidirectional encoder representation from Transformer. Then, the bidirectional fault features were extracted and weighted by the improved BiGRU and attention mechanism respectively. Finally, the weighted loss function is used to reduce the impact of class imbalance on the model. To validate the effectiveness of the proposed method, this paper uses the patient monitor fault dataset for verification, and the macro F 1 value has achieved 91.11%. The results show that the model built in this study can realize the automatic classification of fault text, and may provide assistant decision support for the intelligent fault diagnosis of the patient monitor in the future.

Cardiac three-dimensional electrophysiological labeling technology is the prerequisite and foundation of atrial fibrillation (AF) ablation surgery, and invasive labeling is the current clinical method, but there are many shortcomings such as large trauma, long procedure duration, and low success rate. In recent years, because of its non-invasive and convenient characteristics, ex vivo labeling has become a new direction for the development of electrophysiological labeling technology. With the rapid development of computer hardware and software as well as the accumulation of clinical database, the application of deep learning technology in electrocardiogram (ECG) data is becoming more extensive and has made great progress, which provides new ideas for the research of ex vivo cardiac mapping and intelligent labeling of AF substrates. This paper reviewed the research progress in the fields of ECG forward problem, ECG inverse problem, and the application of deep learning in AF labeling, discussed the problems of ex vivo intelligent labeling of AF substrates and the possible approaches to solve them, prospected the challenges and future directions for ex vivo cardiac electrophysiology labeling.

Methylcellulose is a semi-flexible cellulose ether derivative, whose hydrogels are thermosensitive and reversible, with good biocompatibility and adjustable function, and its application has attracted much attention in the biomedical field. In this paper, the application of methylcellulose-based thermo-sensitive hydrogels in biomedical field was reviewed. Based on the mechanism of gelation and influencing factors of methylcellulose, this paper focused on the recent advances in biomedical applications of methylcellulose-based hydrogels, including drug delivery, regenerative medicine, and other related fields. The current achievements in these fields were summarized in the form of lists in this paper to provide ideas and tendencies for future research. Finally, the future development of multifunctional methylcellulose-based hydrogel materials with improved performance was also discussed.

Wearable monitoring, which has the advantages of continuous monitoring for a long time with low physiological and psychological load, represents a future development direction of monitoring technology. Based on wearable physiological monitoring technology, combined with Internet of Things (IoT) and artificial intelligence technology, this paper has developed an intelligent monitoring system, including wearable hardware, ward Internet of Things platform, continuous physiological data analysis algorithm and software. We explored the clinical value of continuous physiological data using this system through a lot of clinical practices. And four value points were given, namely, real-time monitoring, disease assessment, prediction and early warning, and rehabilitation training. Depending on the real clinical environment, we explored the mode of applying wearable technology in general ward monitoring, cardiopulmonary rehabilitation, and integrated monitoring inside and outside the hospital. The research results show that this monitoring system can be effectively used for monitoring of patients in hospital, evaluation and training of patients' cardiopulmonary function, and management of patients outside hospital.

Electronic skin has shown great application potential in many fields such as healthcare monitoring and human-machine interaction due to their excellent sensing performance, mechanical properties and biocompatibility. This paper starts from the materials selection and structures design of electronic skin, and summarizes their different applications in the field of healthcare equipment, especially current development status of wearable sensors with different functions, as well as the application of electronic skin in virtual reality. The challenges of electronic skin in the field of wearable devices and healthcare, as well as our corresponding strategies, are discussed to provide a reference for further advancing the research of electronic skin.

Electrocardiogram (ECG) monitoring owns important clinical value in diagnosis, prevention and rehabilitation of cardiovascular disease (CVD). With the rapid development of Internet of Things (IoT), big data, cloud computing, artificial intelligence (AI) and other advanced technologies, wearable ECG is playing an increasingly important role. With the aging process of the population, it is more and more urgent to upgrade the diagnostic mode of CVD. Using AI technology to assist the clinical analysis of long-term ECGs, and thus to improve the ability of early detection and prediction of CVD has become an important direction. Intelligent wearable ECG monitoring needs the collaboration between edge and cloud computing. Meanwhile, the clarity of medical scene is conducive for the precise implementation of wearable ECG monitoring. This paper first summarized the progress of AI-related ECG studies and the current technical orientation. Then three cases were depicted to illustrate how the AI in wearable ECG cooperate with the clinic. Finally, we demonstrated the two core issues-the reliability and worth of AI-related ECG technology and prospected the future opportunities and challenges.

Rapid and accurate identification and effective non-drug intervention are the worldwide challenges in the field of depression. Electroencephalogram (EEG) signals contain rich quantitative markers of depression, but whole-brain EEG signals acquisition process is too complicated to be applied on a large-scale population. Based on the wearable frontal lobe EEG monitoring device developed by the authors' laboratory, this study discussed the application of wearable EEG signal in depression recognition and intervention. The technical principle of wearable EEG signals monitoring device and the commonly used wearable EEG devices were introduced. Key technologies for wearable EEG signals-based depression recognition and the existing technical limitations were reviewed and discussed. Finally, a closed-loop brain-computer music interface system for personalized depression intervention was proposed, and the technical challenges were further discussed. This review paper may contribute to the transformation of relevant theories and technologies from basic research to application, and further advance the process of depression screening and personalized intervention.

With the widespread use of electrical equipment, cognitive functions such as working memory (WM) could be severely affected when people are exposed to 50 Hz electromagnetic fields (EMF) for long term. However, the effects of EMF exposure on WM and its neural mechanism remain unclear. In the present paper, 15 rats were randomly assigned to three groups, and exposed to an EMF environment at 50 Hz and 2 mT for a different duration: 0 days (control group), 24 days (experimental group I), and 48 days (experimental group II). Then, their WM function was assessed by the T-maze task. Besides, their local field potential (LFP) in the media prefrontal cortex (mPFC) was recorded by the in vivo multichannel electrophysiological recording system to study the power spectral density (PSD) of θ and γ oscillations and the phase-amplitude coupling (PAC) intensity of θ-γ oscillations during the T-maze task. The results showed that the PSD of θ and γ oscillations decreased in experimental groups I and II, and the PAC intensity between θ and high-frequency γ (hγ) decreased significantly compared to the control group. The number of days needed to meet the task criterion was more in experimental groups I and II than that of control group. The results indicate that long-term exposure to EMF could impair WM function. The possible reason may be the impaired communication between different rhythmic oscillations caused by a decrease in θ-hγ PAC intensity. This paper demonstrates the negative effects of EMF on WM and reveals the potential neural mechanisms from the changes of PAC intensity, which provides important support for further investigation of the biological effects of EMF and its mechanisms.

Alzheimer's disease (AD) is a neurodegenerative disease characterized by cognitive impairment, with the predominant clinical diagnosis of spatial working memory (SWM) deficiency, which seriously affects the physical and mental health of patients. However, the current pharmacological therapies have unsatisfactory cure rates and other problems, so non-pharmacological physical therapies have gradually received widespread attention. Recently, a novel treatment using 40 Hz light flicker stimulation (40 Hz-LFS) to rescue the cognitive function of model animals with AD has made initial progress, but the neurophysiological mechanism remains unclear. Therefore, this paper will explore the potential neural mechanisms underlying the modulation of SWM by 40 Hz-LFS based on cross-frequency coupling (CFC). Ten adult Wistar rats were first subjected to acute LFS at frequencies of 20, 40, and 60 Hz. The entrainment effect of LFS with different frequency on neural oscillations in the hippocampus (HPC) and medial prefrontal cortex (mPFC) was analyzed. The results showed that acute 40 Hz-LFS was able to develop strong entrainment and significantly modulate the oscillation power of the low-frequency gamma (lγ) rhythms. The rats were then randomly divided into experimental and control groups of 5 rats each for a long-term 40 Hz-LFS (7 d). Their SWM function was assessed by a T-maze task, and the CFC changes in the HPC-mPFC circuit were analyzed by phase-amplitude coupling (PAC). The results showed that the behavioral performance of the experimental group was improved and the PAC of θ-lγ rhythm was enhanced, and the difference was statistically significant. The results of this paper suggested that the long-term 40 Hz-LFS effectively improved SWM function in rats, which may be attributed to its enhanced communication of different rhythmic oscillations in the relevant neural circuits. It is expected that the study in this paper will build a foundation for further research on the mechanism of 40 Hz-LFS to improve cognitive function and promote its clinical application in the future.

Feature extraction methods and classifier selection are two critical steps in heart sound classification. To capture the pathological features of heart sound signals, this paper introduces a feature extraction method that combines mel-frequency cepstral coefficients (MFCC) and power spectral density (PSD). Unlike conventional classifiers, the adaptive neuro-fuzzy inference system (ANFIS) was chosen as the classifier for this study. In terms of experimental design, we compared different PSDs across various time intervals and frequency ranges, selecting the characteristics with the most effective classification outcomes. We compared four statistical properties, including mean PSD, standard deviation PSD, variance PSD, and median PSD. Through experimental comparisons, we found that combining the features of median PSD and MFCC with heart sound systolic period of 100-300 Hz yielded the best results. The accuracy, precision, sensitivity, specificity, and F1 score were determined to be 96.50%, 99.27%, 93.35%, 99.60%, and 96.35%, respectively. These results demonstrate the algorithm's significant potential for aiding in the diagnosis of congenital heart disease.

Heart valve disease (HVD) is one of the common cardiovascular diseases. Heart sound is an important physiological signal for diagnosing HVDs. This paper proposed a model based on combination of basic component features and envelope autocorrelation features to detect early HVDs. Initially, heart sound signals lasting 5 minutes were denoised by empirical mode decomposition (EMD) algorithm and segmented. Then the basic component features and envelope autocorrelation features of heart sound segments were extracted to construct heart sound feature set. Then the max-relevance and min-redundancy (MRMR) algorithm was utilized to select the optimal mixed feature subset. Finally, decision tree, support vector machine (SVM) and k-nearest neighbor (KNN) classifiers were trained to detect the early HVDs from the normal heart sounds and obtained the best accuracy of 99.9% in clinical database. Normal valve, abnormal semilunar valve and abnormal atrioventricular valve heart sounds were classified and the best accuracy was 99.8%. Moreover, normal valve, single-valve abnormal and multi-valve abnormal heart sounds were classified and the best accuracy was 98.2%. In public database, this method also obtained the good overall accuracy. The result demonstrated this proposed method had important value for the clinical diagnosis of early HVDs.

For the transportation process of rescuing wounded personnel on naval vessels, a new type of shoulder type exoskeleton stretcher for individual soldier was designed in this paper. The three-dimensional model of the shoulder type exoskeleton stretcher for individual soldier was constructed using three dimensional modeling software. Finite element analysis technique was employed to conduct statics simulation, modal analysis, and transient dynamics analysis on the designed exoskeleton stretcher. The results show that the maximum stress of the exoskeleton stretcher for walking on flat ground is 265.55 MPa, which is lower than the allowable strength of the fabrication material. Furthermore, the overall deformation of the structure is small. Modal analysis reveals that the natural frequency range of the exoskeleton stretcher under different gait conditions is 1.96 Hz to 28.70 Hz, which differs significantly from the swing frequency of 1 Hz during walking. This indicates that the designed structure can effectively avoid resonance. The transient dynamics analysis results show that the maximum deformation and stress of exoskeleton stretcher remain within the safety range, which meets the expected performance requirements. In summary, the shoulder type exoskeleton stretcher for individual soldier designed in this study can solve the problem of requiring more than 2 people to carry for the existing stretcher, especially suitable for narrow spaces of naval vessels. The research results of this paper can provide a new solution for the rescue of wounded personnel on naval vessels.

Reduced chemotactic migration of polymorphonuclear neutrophil (PMN) in sepsis patients leads to decreased bacterial clearance and accelerates the progression of sepsis disease. Quantification of PMN chemotaxis in sepsis patients can help characterize the immune health of sepsis patients. Microfluidic microarrays have been widely used for cell chemotaxis analysis because of the advantages of low reagent consumption, near-physiological environment, and visualization of the migration process. Currently, the study of PMN chemotaxis using microfluidic chips is mainly limited by the cumbersome cell separation operation and low throughput of microfluidic chips. In this paper, we first designed an inertial cell sorting chip to achieve label-free separation of the two major cell types by using the basic principle that leukocytes (mainly granulocytes, lymphocytes and monocytes) and erythrocytes move to different positions of the spiral microchannel when they move in the spiral microchannel under different strength of inertial force and Dean's resistance. Subsequently, in this paper, we designed a multi-channel cell migration chip and constructed a microfluidic PMN inertial label-free sorting and chemotaxis analysis platform. The inertial cell sorting chip separates leukocyte populations and then injects them into the multi-channel cell migration chip, which can complete the chemotaxis test of PMN to chemotactic peptide (fMLP) within 15 min. The remaining cells, such as monocytes with slow motility and lymphocytes that require pre-activation with proliferative culture, do not undergo significant chemotactic migration. The test results of sepsis patients ( n =6) and healthy volunteers ( n =3) recruited in this study showed that the chemotaxis index (CI) and migration velocity ( v ) of PMN from sepsis patients were significantly weaker than those from healthy volunteers. In conclusion, the microfluidic PMN inertial label-free sorting and chemotaxis analysis platform constructed in this paper can be used as a new tool for cell label-free sorting and migration studies.

Diabetes and its complications that seriously threaten the health and life of human, has become a public health problem of global concern. Glycemic control remains a major focus in the treatment and management of patients with diabetes. The traditional lifestyle interventions, drug therapies, and surgeries have benefited many patients with diabetes. However, due to problems such as poor patient compliance, drug side effects, and limited surgical indications, there are still patients who fail to effectively control their blood glucose levels. With the development of bioelectronic medicine, neuromodulation techniques have shown great potential in the field of glycemic control and diabetes intervention with its unique advantages. This paper mainly reviewed the research advances and latest achievements of neuromodulation technologies such as peripheral nerve electrical stimulation, ultrasound neuromodulation, and optogenetics in blood glucose regulation and diabetes intervention, analyzed the existing problems and presented prospects for the future development trend to promote clinical research and application of neuromodulation technologies in the treatment of diabetes.

Rapid serial visual presentation (RSVP) is a type of psychological visual stimulation experimental paradigm that requires participants to identify target stimuli presented continuously in a stream of stimuli composed of numbers, letters, words, images, and so on at the same spatial location, allowing them to discern a large amount of information in a short period of time. The RSVP-based brain-computer interface (BCI) can not only be widely used in scenarios such as assistive interaction and information reading, but also has the advantages of stability and high efficiency, which has become one of the common techniques for human-machine intelligence fusion. In recent years, brain-controlled spellers, image recognition and mind games are the most popular fields of RSVP-BCI research. Therefore, aiming to provide reference and new ideas for RSVP-BCI related research, this paper reviewed the paradigm design and system performance optimization of RSVP-BCI in these three fields. It also looks ahead to its potential applications in cutting-edge fields such as entertainment, clinical medicine, and special military operations.

The portable light-weight magnetic resonance imaging system can be deployed in special occasions such as Intensive Care Unit (ICU) and ambulances, making it possible to implement bedside monitoring imaging systems, mobile stroke units and magnetic resonance platforms in remote areas. Compared with medium and high field imaging systems, ultra-low-field magnetic resonance imaging equipment utilizes light-weight permanent magnets, which are compact and easy to move. However, the image quality is highly susceptible to external electromagnetic interference without a shielded room and there are still many key technical problems in hardware design to be solved. In this paper, the system hardware design and environmental electromagnetic interference elimination algorithm were studied. Consequently, some research results were obtained and a prototype of portable shielding-free 50 mT magnetic resonance imaging system was built. The light-weight magnet and its uniformity, coil system and noise elimination algorithm and human brain imaging were verified. Finally, high-quality images of the healthy human brain were obtained. The results of this study would provide reference for the development and application of ultra-low-field magnetic resonance imaging technology.

There are some limitations in the localization of epileptogenic zone commonly used by human eyes to identify abnormal discharges of intracranial electroencephalography in epilepsy. However, at present, the accuracy of the localization of epileptogenic zone by extracting intracranial electroencephalography features needs to be further improved. As a new method using dynamic network model, neural fragility has potential application value in the localization of epileptogenic zone. In this paper, the neural fragility analysis method was used to analyze the stereoelectroencephalography signals of 35 seizures in 20 patients, and then the epileptogenic zone electrodes were classified using the random forest model, and the classification results were compared with the time-frequency characteristics of six different frequency bands extracted by short-time Fourier transform. The results showed that the area under curve (AUC) of epileptic focus electrodes based on time-frequency analysis was 0.870 (delta) to 0.956 (high gamma), and its classification accuracy increased with the increase of frequency band, while the AUC by using neural fragility could reach 0.957. After fusing the neural fragility and the time-frequency characteristics of the γ and high γ band, the AUC could be further increased to 0.969, which was improved on the original basis. This paper verifies the effectiveness of neural fragility in identifying epileptogenic zone, and provides a theoretical reference for its further clinical application.

In order to fully explore the neural oscillatory coupling characteristics of patients with mild cognitive impairment (MCI), this paper analyzed and compared the strength of the coupling characteristics for 28 MCI patients and 21 normal subjects under six different-frequency combinations. The results showed that the difference in the global phase synchronization index of cross-frequency coupling under δ-θ rhythm combination was statistically significant in the MCI group compared with the normal control group ( P = 0.025, d = 0.398). To further validate this coupling feature, this paper proposed an optimized convolutional neural network model that incorporated a time-frequency data enhancement module and batch normalization layers to prevent overfitting while enhancing the robustness of the model. Based on this optimized model, with the phase locking value matrix of δ-θ rhythm combination as the single input feature, the diagnostic accuracy of MCI patients was (95.49 ± 4.15)%, sensitivity and specificity were (93.71 ± 7.21)% and (97.50 ± 5.34)%, respectively. The results showed that the characteristics of the phase locking value matrix under the combination of δ-θ rhythms can adequately reflect the cognitive status of MCI patients, which is helpful to assist the diagnosis of MCI.

Electromagnetic stimulation is an important neuromodulation technique that modulates the electrical activity of neurons and affects cortical excitability for the purpose of modulating the nervous system. The phenomenon of inverse stochastic resonance is a response mechanism of the biological nervous system to external signals and plays an important role in the signal processing of the nervous system. In this paper, a small-world neural network with electrical synaptic connections was constructed, and the inverse stochastic resonance of the small-world neural network under electromagnetic stimulation was investigated by analyzing the dynamics of the neural network. The results showed that: the Levy channel noise under electromagnetic stimulation could cause the occurrence of inverse stochastic resonance in small-world neural networks; the characteristic index and location parameter of the noise had significant effects on the intensity and duration of the inverse stochastic resonance in neural networks; the larger the probability of randomly adding edges and the number of nearest neighbor nodes in small-world networks, the more favorable the anti-stochastic resonance was; by adjusting the electromagnetic stimulation parameters, a dual regulation of the inverse stochastic resonance of the neural network can be achieved. The results of this study provide some theoretical support for exploring the regulation mechanism of electromagnetic nerve stimulation technology and the signal processing mechanism of nervous system.

Medical studies have found that tumor mutation burden (TMB) is positively correlated with the efficacy of immunotherapy for non-small cell lung cancer (NSCLC), and TMB value can be used to predict the efficacy of targeted therapy and chemotherapy. However, the calculation of TMB value mainly depends on the whole exon sequencing (WES) technology, which usually costs too much time and expenses. To deal with above problem, this paper studies the correlation between TMB and slice images by taking advantage of digital pathological slices commonly used in clinic and then predicts the patient TMB level accordingly. This paper proposes a deep learning model (RCA-MSAG) based on residual coordinate attention (RCA) structure and combined with multi-scale attention guidance (MSAG) module. The model takes ResNet-50 as the basic model and integrates coordinate attention (CA) into bottleneck module to capture the direction-aware and position-sensitive information, which makes the model able to locate and identify the interesting positions more accurately. And then, MSAG module is embedded into the network, which makes the model able to extract the deep features of lung cancer pathological sections and the interactive information between channels. The cancer genome map (TCGA) open dataset is adopted in the experiment, which consists of 200 pathological sections of lung adenocarcinoma, including 80 data samples with high TMB value, 77 data samples with medium TMB value and 43 data samples with low TMB value. Experimental results demonstrate that the accuracy, precision, recall and F1 score of the proposed model are 96.2%, 96.4%, 96.2% and 96.3%, respectively, which are superior to the existing mainstream deep learning models. The model proposed in this paper can promote clinical auxiliary diagnosis and has certain theoretical guiding significance for TMB prediction.

In this paper, the differences between air probe and filled probe for measuring high-frequency dielectric properties of biological tissues are investigated based on the equivalent circuit model to provide a reference for the methodology of high-frequency measurement of biological tissue dielectric properties. Two types of probes were used to measure different concentrations of NaCl solution in the frequency band of 100 MHz-2 GHz. The results showed that the accuracy and reliability of the calculated results of the air probe were lower than that of the filled probe, especially the dielectric coefficient of the measured material, and the higher the concentration of NaCl solution, the higher the error. By laminating the probe terminal, liquid intrusion could be prevented, to a certain extent, to improve the accuracy of measurement. However, as the frequency decreased, the influence of the film on the measurement increased and the measurement accuracy decreased. The results of the study show that the air probe, despite its simple dimensional design and easy calibration, differs from the conventional equivalent circuit model in actual measurements, and the model needs to be re-corrected for actual use. The filled probe matches the equivalent circuit model better, and therefore has better measurement accuracy and reliability.

For patients with partial jaw defects, cysts and dental implants, doctors need to take panoramic X-ray films or manually draw dental arch lines to generate Panorama images in order to observe their complete dentition information during oral diagnosis. In order to solve the problems of additional burden for patients to take panoramic X-ray films and time-consuming issue for doctors to manually segment dental arch lines, this paper proposes an automatic panorama reconstruction method based on cone beam computerized tomography (CBCT). The V-network (VNet) is used to pre-segment the teeth and the background to generate the corresponding binary image, and then the Bezier curve is used to define the best dental arch curve to generate the oral panorama. In addition, this research also addressed the issues of mistakenly recognizing the teeth and jaws as dental arches, incomplete coverage of the dental arch area by the generated dental arch lines, and low robustness, providing intelligent methods for dental diagnosis and improve the work efficiency of doctors.

Magnetic resonance imaging(MRI) can obtain multi-modal images with different contrast, which provides rich information for clinical diagnosis. However, some contrast images are not scanned or the quality of the acquired images cannot meet the diagnostic requirements due to the difficulty of patient's cooperation or the limitation of scanning conditions. Image synthesis techniques have become a method to compensate for such image deficiencies. In recent years, deep learning has been widely used in the field of MRI synthesis. In this paper, a synthesis network based on multi-modal fusion is proposed, which firstly uses a feature encoder to encode the features of multiple unimodal images separately, and then fuses the features of different modal images through a feature fusion module, and finally generates the target modal image. The similarity measure between the target image and the predicted image in the network is improved by introducing a dynamic weighted combined loss function based on the spatial domain and K-space domain. After experimental validation and quantitative comparison, the multi-modal fusion deep learning network proposed in this paper can effectively synthesize high-quality MRI fluid-attenuated inversion recovery (FLAIR) images. In summary, the method proposed in this paper can reduce MRI scanning time of the patient, as well as solve the clinical problem of missing FLAIR images or image quality that is difficult to meet diagnostic requirements.

Precise segmentation of lung field is a crucial step in chest radiographic computer-aided diagnosis system. With the development of deep learning, fully convolutional network based models for lung field segmentation have achieved great effect but are poor at accurate identification of the boundary and preserving lung field consistency. To solve this problem, this paper proposed a lung segmentation algorithm based on non-local attention and multi-task learning. Firstly, an encoder-decoder convolutional network based on residual connection was used to extract multi-scale context and predict the boundary of lung. Secondly, a non-local attention mechanism to capture the long-range dependencies between pixels in the boundary regions and global context was proposed to enrich feature of inconsistent region. Thirdly, a multi-task learning to predict lung field based on the enriched feature was conducted. Finally, experiments to evaluate this algorithm were performed on JSRT and Montgomery dataset. The maximum improvement of Dice coefficient and accuracy were 1.99% and 2.27%, respectively, comparing with other representative algorithms. Results show that by enhancing the attention of boundary, this algorithm can improve the accuracy and reduce false segmentation.

Accurate segmentation of pediatric echocardiograms is a challenging task, because significant heart-size changes with age and faster heart rate lead to more blurred boundaries on cardiac ultrasound images compared with adults. To address these problems, a dual decoder network model combining channel attention and scale attention is proposed in this paper. Firstly, an attention-guided decoder with deep supervision strategy is used to obtain attention maps for the ventricular regions. Then, the generated ventricular attention is fed back to multiple layers of the network through skip connections to adjust the feature weights generated by the encoder and highlight the left and right ventricular areas. Finally, a scale attention module and a channel attention module are utilized to enhance the edge features of the left and right ventricles. The experimental results demonstrate that the proposed method in this paper achieves an average Dice coefficient of 90.63% in acquired bilateral ventricular segmentation dataset, which is better than some conventional and state-of-the-art methods in the field of medical image segmentation. More importantly, the method has a more accurate effect in segmenting the edge of the ventricle. The results of this paper can provide a new solution for pediatric echocardiographic bilateral ventricular segmentation and subsequent auxiliary diagnosis of congenital heart disease.

An in-depth understanding of the mechanism of lower extremity muscle coordination during walking is the key to improving the efficacy of gait rehabilitation in patients with neuromuscular dysfunction. This paper investigates the effect of changes in walking speed on lower extremity muscle synergy patterns and muscle functional networks. Eight healthy subjects were recruited to perform walking tasks on a treadmill at three different speeds, and the surface electromyographic signals (sEMG) of eight muscles of the right lower limb were collected synchronously. The non-negative matrix factorization (NNMF) method was used to extract muscle synergy patterns, the mutual information (MI) method was used to construct the alpha frequency band (8-13 Hz), beta frequency band (14-30 Hz) and gamma frequency band (31-60 Hz) muscle functional network, and complex network analysis methods were introduced to quantify the differences between different networks. Muscle synergy analysis extracted 5 muscle synergy patterns, and changes in walking speed did not change the number of muscle synergy, but resulted in changes in muscle weights. Muscle network analysis found that at the same speed, high-frequency bands have lower global efficiency and clustering coefficients. As walking speed increased, the strength of connections between local muscles also increased. The results show that there are different muscle synergy patterns and muscle function networks in different walking speeds. This study provides a new perspective for exploring the mechanism of muscle coordination at different walking speeds, and is expected to provide theoretical support for the evaluation of gait function in patients with neuromuscular dysfunction.

The setting and adjustment of ventilator parameters need to rely on a large amount of clinical data and rich experience. This paper explored the problem of difficult decision-making of ventilator parameters due to the time-varying and sudden changes of clinical patient's state, and proposed an expert knowledge-based strategies for ventilator parameter setting and stepless adaptive adjustment based on fuzzy control rule and neural network. Based on the method and the real-time physiological state of clinical patients, we generated a mechanical ventilation decision-making solution set with continuity and smoothness, and automatically provided explicit parameter adjustment suggestions to medical personnel. This method can solve the problems of low control precision and poor dynamic quality of the ventilator's stepwise adjustment, handle multi-input control decision problems more rationally, and improve ventilation comfort for patients.

In response to the problem that the traditional lower limb rehabilitation scale assessment method is time-consuming and difficult to use in exoskeleton rehabilitation training, this paper proposes a quantitative assessment method for lower limb walking ability based on lower limb exoskeleton robot training with multimodal synergistic information fusion. The method significantly improves the efficiency and reliability of the rehabilitation assessment process by introducing quantitative synergistic indicators fusing electrophysiological and kinematic level information. First, electromyographic and kinematic data of the lower extremity were collected from subjects trained to walk wearing an exoskeleton. Then, based on muscle synergy theory, a synergistic quantification algorithm was used to construct synergistic index features of electromyography and kinematics. Finally, the electrophysiological and kinematic level information was fused to build a modal feature fusion model and output the lower limb motor function score. The experimental results showed that the correlation coefficients of the constructed synergistic features of electromyography and kinematics with the clinical scale were 0.799 and 0.825, respectively. The results of the fused synergistic features in the K -nearest neighbor (KNN) model yielded higher correlation coefficients ( r = 0.921, P < 0.01). This method can modify the rehabilitation training mode of the exoskeleton robot according to the assessment results, which provides a basis for the synchronized assessment-training mode of "human in the loop" and provides a potential method for remote rehabilitation training and assessment of the lower extremity.

Bl factor is a key system parameter of the resonant blood viscoelastic sensor. In this paper, a dynamic measurement system for the spatial distribution of Bl factor based on velocity amplitude and motional impedance was designed. The system extracted the velocity amplitude and motional impedance of the coil under the dynamic condition of driving the sensor to generate simple harmonic oscillations using laser displacement and impedance analysis combined with in-phase/quadrature demodulation algorithm, and controlled the equilibrium position of the coil by adjusting the direct current component of the excitation current to realize the position scanning. In the position interval of [-240, 240] μm, the maximum coefficient of variation of the measurement results was 0.077 3%, and the maximum relative error to the simulation results was 2.937 9%, with a linear fitting correlation coefficient R 2 = 0.996 8. The system can be used to accurately measure the spatial distribution of Bl factor of the resonant blood viscoelastic sensor, which provides a technical support for the verification of the design of the sensor magnetic circuit.

Ultra-rapid cooling and rewarming rate is a critical technical approach to achieve ice-free cells during the freezing and melting process. A set of ultra-rapid solid surface freeze-thaw visualization system was developed based on a sapphire flim, and experiments on droplet freeze-thaw were carried out under different cryoprotectant components, volumes and laser energies. The results showed that the cooling rate of 1 μL mixed cryoprotectant [1.5 mol/L propylene glycol (PG) + 1.5 mol/L ethylene glycol (EG) + 0.5 mol/L trehalose (TRE)] could be 9.2×10 3 °C/min. The volume range of 1-8 μL droplets could be vitrified. After comparing the proportions of multiple cryoprotectants, the combination of equal proportion mixed permeability protectant and trehalose had the best vitrification freezing effect and more uniform crystallization characteristics. During the rewarming operation, the heating curve of glassy droplets containing gold nanoparticles was measured for the first time under the action of 400-1 200 W laser power, and the rewarming rate was up to the order of 10 6 °C/min. According to the droplet images of different power rewarming processes, the laser power range for ice-free rewarming with micron-level resolution was clarified to be 1 400-1 600 W. The work of this paper simultaneously realizes the ultra-high-speed temperature ramp-up, transient visual observation and temperature measurement of droplets, providing technical means for judging the ice free droplets during the freeze-thaw process. It is conducive to promoting the development of ultra-rapid freeze-thaw technology for biological cells and tissues.

Transcranial electric stimulation (TES) is a non-invasive, economical, and well-tolerated neuromodulation technique. However, traditional TES is a whole-brain stimulation with a small current, which cannot satisfy the need for effectively focused stimulation of deep brain areas in clinical treatment. With the deepening of the clinical application of TES, researchers have constantly investigated new methods for deeper, more intense, and more focused stimulation, especially multi-electrode stimulation represented by high-precision TES and temporal interference stimulation. This paper reviews the stimulation optimization schemes of TES in recent years and further analyzes the characteristics and limitations of existing stimulation methods, aiming to provide a reference for related clinical applications and guide the following research on TES. In addition, this paper proposes the viewpoint of the development direction of TES, especially the direction of optimizing TES for deep brain stimulation, aiming to provide new ideas for subsequent research and application.

Chromatin three-dimensional genome structure plays a key role in cell function and gene regulation. Single-cell Hi-C techniques can capture genomic structure information at the cellular level, which provides an opportunity to study changes in genomic structure between different cell types. Recently, some excellent computational methods have been developed for single-cell Hi-C data analysis. In this paper, the available methods for single-cell Hi-C data analysis were first reviewed, including preprocessing of single-cell Hi-C data, multi-scale structure recognition based on single-cell Hi-C data, bulk-like Hi-C contact matrix generation based on single-cell Hi-C data sets, pseudo-time series analysis, and cell classification. Then the application of single-cell Hi-C data in cell differentiation and structural variation was described. Finally, the future development direction of single-cell Hi-C data analysis was also prospected.

With the booming development of medical information technology and computer science, the medical services industry is gradually transiting from information technology to intelligence. The medical knowledge graph plays an important role in intelligent medical applications such as knowledge questions and answers and intelligent diagnosis, and is a key technology for promoting wise medical care and the basis for intelligent management of medical information. In order to fully exploit the great potential of knowledge graphs in the medical field, this paper focuses on five aspects: inter-drug relationship discovery, assisted diagnosis, personalized recommendation, decision support and intelligent prediction. The latest research progress on medical knowledge graphs is introduced, and relevant suggestions are made in light of the current challenges and problems faced by medical knowledge graphs to provide reference for promoting the wide application of medical knowledge graphs.

Stem cells have been regarded with promising application potential in tissue engineering and regenerative medicine due to their self-renewal and multidirectional differentiation abilities. However, their fate is relied on their local microenvironment, or niche. Recent studied have demonstrated that biophysical factors, defined as physical microenvironment in which stem cells located play a vital role in regulating stem cell committed differentiation. In vitro , synthetic physical microenvironments can be used to precisely control a variety of biophysical properties. On this basis, the effect of biophysical properties such as matrix stiffness, matrix topography and mechanical force on the committed differentiation of stem cells was further investigated. This paper summarizes the approach of mechanical models of artificial physical microenvironment and reviews the effects of different biophysical characteristics on stem cell differentiation, in order to provide reference for future research and development in related fields.

Idiopathic pulmonary fibrosis (IPF) is a progressive scar-forming disease with a high mortality rate that has received widespread attention. Epithelial mesenchymal transition (EMT) is an important part of the pulmonary fibrosis process, and changes in the biomechanical properties of lung tissue have an important impact on it. In this paper, we summarize the changes in the biomechanical microenvironment of lung tissue in IPF-EMT in recent years, and provide a systematic review on the effects of alterations in the mechanical microenvironment in pulmonary fibrosis on the process of EMT, the effects of mechanical factors on the behavior of alveolar epithelial cells in EMT and the biomechanical signaling in EMT, in order to provide new references for the research on the prevention and treatment of IPF.

Aiming at the human-computer interaction problem during the movement of the rehabilitation exoskeleton robot, this paper proposes an adaptive human-computer interaction control method based on real-time monitoring of human muscle state. Considering the efficiency of patient health monitoring and rehabilitation training, a new fatigue assessment algorithm was proposed. The method fully combined the human neuromuscular model, and used the relationship between the model parameter changes and the muscle state to achieve the classification of muscle fatigue state on the premise of ensuring the accuracy of the fatigue trend. In order to ensure the safety of human-computer interaction, a variable impedance control algorithm with this algorithm as the supervision link was proposed. On the basis of not adding redundant sensors, the evaluation algorithm was used as the perceptual decision-making link of the control system to monitor the muscle state in real time and carry out the robot control of fault-tolerant mechanism decision-making, so as to achieve the purpose of improving wearing comfort and improving the efficiency of rehabilitation training. Experiments show that the proposed human-computer interaction control method is effective and universal, and has broad application prospects.

Tremor is an involuntary and repetitive swinging movement of limb, which can be regarded as a periodic disturbance in tremor suppression system based on functional electrical stimulation (FES). Therefore, using repetitive controller to adjust the level and timing of FES applied to the corresponding muscles, so as to generate the muscle torque opposite to the tremor motion, is a feasible means of tremor suppression. At present, most repetitive control systems based on FES assume that tremor is a fixed single frequency signal, but in fact, tremor may be a multi-frequency signal and the tremor frequency also varies with time. In this paper, the tremor data of intention tremor patients are analyzed from the perspective of frequency, and an adaptive repetitive controller with internal model switching is proposed to suppress tremor signals with different frequencies. Simulation and experimental results show that the proposed adaptive repetitive controller based on parallel multiple internal models and series high-order internal model switching can suppress tremor by up to 84.98% on average, which is a significant improvement compared to the traditional single internal model repetitive controller and filter based feedback controller. Therefore, the adaptive repetitive control method based on FES proposed in this paper can effectively address the issue of wrist intention tremor in patients, and can offer valuable technical support for the rehabilitation of patients with subsequent motor dysfunction.

This paper studies the active force characteristics of the neck muscles under the condition of rapid braking, which can provide theoretical support for reducing the neck injury of pilots when carrier-based aircraft blocks the landing. We carried out static loading and real vehicle braking experiments under rapid braking conditions, collected the active contraction force and electromyography (EMG) signals of neck muscles, and analyzed the response characteristics of neck muscle active force response. The results showed that the head and neck forward tilt time was delayed and the amplitude decreased during neck muscle pre-tightening. The duration of the neck in the extreme position decreased, and the recovery towards the seat direction was faster. The EMG signals of trapezius muscle was higher than sternocleidomastoid muscle. This suggests that pilots can reduce neck injury by pre-tightening the neck muscles during actual braking flight. In addition, we can consider the design of relevant fittings for pre-tightening the neck muscles.

Coding with high-frequency stimuli could alleviate the visual fatigue of users generated by the brain-computer interface (BCI) based on steady-state visual evoked potential (SSVEP). It would improve the comfort and safety of the system and has promising applications. However, most of the current advanced SSVEP decoding algorithms were compared and verified on low-frequency SSVEP datasets, and their recognition performance on high-frequency SSVEPs was still unknown. To address the aforementioned issue, electroencephalogram (EEG) data from 20 subjects were collected utilizing a high-frequency SSVEP paradigm. Then, the state-of-the-art SSVEP algorithms were compared, including 2 canonical correlation analysis algorithms, 3 task-related component analysis algorithms, and 1 task discriminant component analysis algorithm. The results indicated that they all could effectively decode high-frequency SSVEPs. Besides, there were differences in the classification performance and algorithms' speed under different conditions. This paper provides a basis for the selection of algorithms for high-frequency SSVEP-BCI, demonstrating its potential utility in developing user-friendly BCI.

With inherent sparse spike-based coding and asynchronous event-driven computation, spiking neural network (SNN) is naturally suitable for processing event stream data of event cameras. In order to improve the feature extraction and classification performance of bio-inspired hierarchical SNNs, in this paper an event camera object recognition system based on biological synaptic plasticity is proposed. In our system input event streams were firstly segmented adaptively using spiking neuron potential to improve computational efficiency of the system. Multi-layer feature learning and classification are implemented by our bio-inspired hierarchical SNN with synaptic plasticity. After Gabor filter-based event-driven convolution layer which extracted primary visual features of event streams, we used a feature learning layer with unsupervised spiking timing dependent plasticity (STDP) rule to help the network extract frequent salient features, and a feature learning layer with reward-modulated STDP rule to help the network learn diagnostic features. The classification accuracies of the network proposed in this paper on the four benchmark event stream datasets were better than the existing bio-inspired hierarchical SNNs. Moreover, our method showed good classification ability for short event stream input data, and was robust to input event stream noise. The results show that our method can improve the feature extraction and classification performance of this kind of SNNs for event camera object recognition.

Patients with amyotrophic lateral sclerosis ( ALS ) often have difficulty in expressing their intentions through language and behavior, which prevents them from communicating properly with the outside world and seriously affects their quality of life. The brain-computer interface (BCI) has received much attention as an aid for ALS patients to communicate with the outside world, but the heavy device causes inconvenience to patients in the application process. To improve the portability of the BCI system, this paper proposed a wearable P300-speller brain-computer interface system based on the augmented reality (MR-BCI). This system used Hololens2 augmented reality device to present the paradigm, an OpenBCI device to capture EEG signals, and Jetson Nano embedded computer to process the data. Meanwhile, to optimize the system's performance for character recognition, this paper proposed a convolutional neural network classification method with low computational complexity applied to the embedded system for real-time classification. The results showed that compared with the P300-speller brain-computer interface system based on the computer screen (CS-BCI), MR-BCI induced an increase in the amplitude of the P300 component, an increase in accuracy of 1.7% and 1.4% in offline and online experiments, respectively, and an increase in the information transfer rate of 0.7 bit/min. The MR-BCI proposed in this paper achieves a wearable BCI system based on guaranteed system performance. It has a positive effect on the realization of the clinical application of BCI.