The decoding of motor imagery (MI) in electroencephalography (EEG) relies on the in-depth exploration of its spatio-temporal features. However, existing methods have struggled to capture the spatio-temporal dynamics of brain networks, lacking mechanisms for noise-robust extraction of key spatial features from multiple perspectives and failing to adequately model spatio-temporal interaction relationships. To address these challenges, this study proposes MBDSTGAT, a multi-branch dynamic spatio-temporal graph attention network with topology perturbation. The proposed network integrates three core components: a Multi-Mode Topology Perturbation (MTP) mechanism, a Multi-Branch Dynamic Strong-Connection Attention (MBDSCA) fusion structure, and a Segmented Spatio-Temporal Graph (SSTG) modeling strategy. The MTP mechanism enhances model robustness through three perturbation modes, namely edge, edge-weight, and hybrid, which simulate the variability of brain connectivity. The MBDSCA module employs multiple branches with distinct parameter matrices to extract multi-perspective spatial features, where each branch uses an annealing-based Top-K neighbor selection strategy embedded in the message-passing process of the graph attention network to dynamically emphasize salient and strongly connected neural interactions. Finally, the SSTG strategy integrates spatial features and temporal segments into a unified graph, in which a spatio-temporal graph attention network models cross-scale dependencies to refine discriminative representations. In large-scale cross-session and cross-subject experiments, the proposed network achieved average accuracies of 97.76% and 82.34%, 86.57% and 67.50%, and 98.75% and 87.55% on the HGD, BCIC-IV-2a, and self-collected VR-MI datasets, respectively, outperforming existing methods and reaching state-of-the-art levels. In conclusion, MBDSTGAT effectively models the spatio-temporal dynamics of EEG signals and demonstrates superior MI decoding performance. The code and self-collected dataset for this study are openly available at https://github.com/shanmaojimu/MBDSTGAT.

The automatic detection of epilepsy based on electroencephalography (EEG) has been proven effective under feature learning models. However, the practical implementation often encounters challenges from noise contamination presented in EEG signals. To address issues related to noise interference, we proposed a robust feature learning model for EEG-based epilepsy detection using Manhattan distance and L1 regularization. Specifically, we introduced Manhattan distance to construct the weight of the L1 regularization term in LASSO and obtained epilepsy-related information in the spectrum components of the original EEG signals and the differentiated signals through the LASSO-based feature selection. We verified the performance of our proposed model using the public EEG dataset. The model achieved the best performance, outperforming competing models. In addition, we tested the performance under noise interference by simulating EEG signal noise, indicating that our model is robust in EEG-based epilepsy detection.

With the increasing need for safeguarding confidential and secure healthcare information, Blockchain has become a pioneering approach to managing medical data due to its decentralized structure, resistance to tampering, and high level of transparency. Protocols for Asynchronous Byzantine Fault Tolerance (BFT) are fundamental for maintaining the depend-ability and uniformity of distributed systems. Nonetheless, these mechanisms still face challenges in terms of performance and efficiency. This work introduces an efficient parallel asynchronous BFT agreement (ParaBFT). First, we replace the traditional ABA with MVBA, enabling the processing of multiple values or proposals in each round of decision-making, which significantly enhances decision-making efficiency. Then, to optimize the message processing flow, ParaBFT incorporates a First-In-First-Out (FIFO) queue as a buffer pool, ensuring the simplicity and fairness of the processing logic. Finally, our experimental analysis reveals that ParaBFT offers enhanced throughput and reduced latency for managing large-scale transactions.

Brain-computer interface (BCI) enables direct communication between the brain and external devices, with applications in areas like patient assistance, entertainment, military, and smart homes. Motor imagery EEG signals, generated by imagining specific movements, are critical for BCI systems as they can control external devices. To enhance the decoding accuracy of motor imagery EEG signals, this paper proposes a novel machine learning framework composed of three main modules. Firstly, a multi-band spatial feature learning technique is devised to identify discriminative spatial features from different frequency ranges and aggregate them to exploit the crucial complementary information among them. Subsequently, to further optimize the extracted features, a regularized feature selection method based on Elastic Net is introduced. This method automates the selection of the most significant features by considering both the relationship between features and the objective task, as well as the inter-feature relationships, leading to a more comprehensive feature selection. Finally, the optimized features are input into a heterogeneous ensemble classifier, which integrates the strengths of various base classifiers to enhance classification accuracy and robustness. Experiments on several publicly available datasets demonstrate that our proposed method achieves superior performance in contrast to existing alternatives.

Bees play an important role in agricultural production. However, beekeeping relies on experienced beekeepers to take time and effort to maintain the bee colonies. To lower the threshold of beekeeping and improve efficiency, we proposed a sound-based bee colony state analysis model using compact Mel frequency cepstral coefficient (MFCC) patterns. Facing high-dimensional bee colony sound signals, we obtained MFCCs from the signals and constructed a set of filters to extract MFCC-based compact features called compact MFCC patterns. After extracting compact features, the feature set was given to the support vector machine classifier. We recorded the sounds of bee colonies under normal conditions and in the absence of the queen bee to verify the proposed model. While significantly compressing the dimensionality of MFCCs, the model still achieved an accuracy score of 99.30% in distinguishing the presence of the queen bee. The extracted compact MFCC patterns effectively and compactly characterize the information related to the bee colony states in the bee colony sound signals, giving the model an excellent ability to discriminate the state of the bee colony.

Depression is a kind of mental illness that is harmful to the development of society. Electroencephalography (EEG) is a promising tool in the area of auxiliary diagnosing diseases. In this paper, we develop a mutual information-based least absolute shrinkage and selection operator (MI-LASSO) model to learn representative features from the power spectral density (PSD) ratio extracted from data. Specifically, MI-LASSO adds an adaptive weight based on mutual information to LASSO, which can discriminate weights of different features. Following the feature selection accomplished by MI-LASSO, the feature set is input into the classifier. We design a stacking ensemble classifier composed of support vector machine (SVM), adaptive boosting (AdaBoost), random forest (RF), and K-nearest neighbor (KNN). Compared to independent classifiers, stacking has a stronger ability to recognize depression. The proposed framework is validated on the open datasets: MODMA and the dataset from Hospital Universiti Sains Malaysia (HUSM). The best classification accuracy on MODMA achieved 99.025%. The best classification accuracy on the second dataset achieved 99.06%. The results indicate that our framework outperforms other EEG-based methods in the identification of depression. We conducted several experiments whose results demonstrate our framework can effectively assist in the diagnosis of depression based on EEG.

Self-supervised learning (SSL) is a challenging task in sleep stage classification (SSC) that is capable of mining valuable representations from unlabeled data. However, traditional SSL methods typically focus on single-view learning and do not fully exploit the interactions among information across multiple views. In this study, we focused on a multi-domain view of the same EEG signal and developed a self-supervised multi-view representation learning framework via time series and time-frequency contrasting (MV-TTFC). In the MV-TTFC framework, we built-in a cross-domain view contrastive learning prediction task to establish connections between the temporal view and time-frequency (TF) view, thereby enhancing the information exchange between multiple views. In addition, to improve the quality of the TF view inputs, we introduced an enhanced multisynchrosqueezing transform, which can create high energy concentration TF image views to compensate for the inaccurate representations in traditional TF processing techniques. Finally, integrating temporal, TF, and fusion space contrastive learning effectively captured the latent features in EEG signals. We evaluated MV-TTFC based on two real-world SSC datasets (SleepEDF-78 and SHHS) and compared it with baseline methods in downstream tasks. Our method exhibited state-of-the-art performance, achieving accuracies of 78.64% and 81.45% with SleepEDF-78 and SHHS, respectively, and macro F1-scores of 70.39% with SleepEDF-78 and 70.47% with SHHS.

In order to control the first wave of COVID-19 pandemic in 2020, many models have shown effectiveness in predicting the spread of new coronary pneumonia and the different interventions. However, few models can collect large amounts of high-quality real-time data faster under the premise of protecting privacy, considering the impact of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) variant and the mass vaccination program as a new intervention. Therefore, we developed a mobile intelligent application that can collect a large amount of real-time data while protecting privacy and conducted a feasibility study by defining a new COVID-19 mathematical model SEMCVRD. By simulating different intervention measures, the prediction model of the mobile intelligent application used in this article simulates the epidemic situation in the U.K. as an example. The findings are as below: the optimal intervention strategy is to suppress the intervention at$P=3$(intervention intensity: the average number of contacts per person per day) before the end of March 2021, then gradually release the intervention intensity at a rate of$P+2$, and finally release the intensity to$P=9$in June 2021. The COVID-19 pandemic will end at the end of June 2021, when the total number of deaths will reach 128772. This strategy will be able to balance the tradeoff between loss of life and economic loss. Compared with the official statistics released by the U.K. government on May 31, 2021, our model can accurately predict the relative error rate of the total number of cases is less than 6.9%, and the relative error rate of the total number of deaths is less than 1%. Furthermore, the model is also suitable for collecting data from countries/regions around the world.

Electroencephalography (EEG) is a unique and valuable ancillary examination, which is essential for the diagnosis and analysis of various neurological diseases. Deep learning methods have been demonstrated to be very promising for challenging EEG screening tasks. However, most of them mainly focus on improving the representation ability by increasing the network depth and width, and cannot take full advantage of the rich hierarchical feature information. More importantly, the importance of utilizing the spatial information between features in a network model is ignored. To this end, a novel multi-level feature fusion capsule network (MFF-CapsNet) is proposed for accurate and efficient EEG pathology detection. Firstly, we devise a new lightweight feature fusion module as a basic unit of feature extraction, through concatenating different level feature maps densely. And then, the innovative CapsNet structure enables it to well capture the significant spatial relationship among different features. Especially, compared with the original CapsNet, we design two particular layers in this structure to reduce the number of parameters, memory, as well as computation, so that the probability of overfitting can be lessened. The experimental outcomes show that MFF-CapsNet can effectively differentiate EEG recordings as pathological or healthy, and its performance is better than the current advanced methodologies, which is the first to meet the requirement of clinical application.

Electroencephalogram (EEG) is widely used to diagnose many neurological and psychiatric brain disorders. The correct interpretation of EEG data is critical to avoid misdiagnosis. However, the analysis of EEG data requires trained specialists and may vary from expert to expert. Meanwhile, it can be challenging and time-consuming to assess the EEG data since these signals may last several hours or days. Therefore, rapid and accurate classification of EEG data may be a key step towards interpreting EEG records. In this study, a novel deep learning model with an end-to-end structure is proposed to distinguish normal and abnormal EEG signals automatically. For this purpose, we investigate the possibility of combining the core ideas of inception and residual architectures into a hybrid model to improve classification performance. We evaluated the proposed method through extensive experiments on a real-world dataset, and it shows feasibility and effectiveness. Compared to previous studies on the same data, our method outperforms other existing EEG signal methods. Thus, the proposed method can aid clinicians to automatically detect brain activity.

The basic method and concept of time series feature extraction is applied to anomaly analysis of seismic data. A new method for piecewise representation based on morphological feature points and a new feature extraction method are proposed. The experimental results show that the proposed piecewise representation method can achieve smaller fitting error and retain the morphological features of the original data better than existing approaches when applied to three real world datasets. The experimental results also illustrate that the proposed method for feature extraction can extract changes in electromagnetic data and distinguish the extent of abnormal changes in real world datasets. In one case, the results show that the approach could identify change features that might be related to an earthquake.