Electroencephalography (EEG)-based emotion recognition is an important element in psychiatric health diagnosis for patients. However, the underlying EEG sensor signals are always non-stationary if they are sampled from different experimental sessions or subjects. This results in the deterioration of the classification performance. Domain adaptation methods offer an effective way to reduce the discrepancy of marginal distribution. However, for EEG sensor signals, both marginal and conditional distributions may be mismatched. In addition, the existing domain adaptation strategies always require a high level of additional computation. To address this problem, a novel strategy named adaptive subspace feature matching (ASFM) is proposed in this paper in order to integrate both the marginal and conditional distributions within a unified framework (without any labeled samples from target subjects). Specifically, we develop a linear transformation function which matches the marginal distributions of the source and target subspaces without a regularization term. This significantly decreases the time complexity of our domain adaptation procedure. As a result, both marginal and conditional distribution discrepancies between the source domain and unlabeled target domain can be reduced, and logistic regression (LR) can be applied to the new source domain in order to train a classifier for use in the target domain, since the aligned source domain follows a distribution which is similar to that of the target domain. We compare our ASFM method with six typical approaches using a public EEG dataset with three affective states: positive, neutral, and negative. Both offline and online evaluations were performed. The subject-to-subject offline experimental results demonstrate that our component achieves a mean accuracy and standard deviation of 80.46% and 6.84%, respectively, as compared with a state-of-the-art method, the subspace alignment auto-encoder (SAAE), which achieves values of 77.88% and 7.33% on average, respectively. For the online analysis, the average classification accuracy and standard deviation of ASFM in the subject-to-subject evaluation for all the 15 subjects in a dataset was 75.11% and 7.65%, respectively, gaining a significant performance improvement compared to the best baseline LR which achieves 56.38% and 7.48%, respectively. The experimental results confirm the effectiveness of the proposed method relative to state-of-the-art methods. Moreover, computational efficiency of the proposed ASFM method is much better than standard domain adaptation; if the numbers of training samples and test samples are controlled within certain range, it is suitable for real-time classification. It can be concluded that ASFM is a useful and effective tool for decreasing domain discrepancy and reducing performance degradation across subjects and sessions in the field of EEG-based emotion recognition.

Motor imagery EEG classification plays a crucial role in non-invasive Brain-Computer Interface (BCI) research. However, the performance of classification is affected by the non-stationarity and individual variations of EEG signals. Simply pooling EEG data with different statistical distributions to train a classification model can severely degrade the generalization performance. To address this issue, the existing methods primarily focus on domain adaptation, which requires access to the test data during training. This is unrealistic and impractical in many EEG application scenarios. In this paper, we propose a novel multi-source domain generalization framework called EEG-DG, which leverages multiple source domains with different statistical distributions to build generalizable models on unseen target EEG data. We optimize both the marginal and conditional distributions to ensure the stability of the joint distribution across source domains and extend it to a multi-source domain generalization framework to achieve domain-invariant feature representation, thereby alleviating calibration efforts. Systematic experiments conducted on a simulative dataset, BCI competition IV 2a, 2b, and OpenBMI datasets, demonstrate the superiority and competitive performance of our proposed framework over other state-of-the-art methods. Specifically, EEG-DG achieves average classification accuracies of 81.79% and 87.12% on datasets IV-2a and IV-2b, respectively, and 78.37% and 76.94% for inter-session and inter-subject evaluations on dataset OpenBMI, which even outperforms some domain adaptation methods. Our code is available at https://github.com/zxchit2022/EEG-DG for evaluation.

Gait phase analysis is widely used in disease diagnosis, rehabilitation training, and other fields by studying the characteristics of human gait. It systematically evaluates human body’s skeletal muscles and nerves with combined disciplines. Microelectromechanical system (MEMS) inertial sensors are extensively used in attitude detection because of its high-precision, portability, and good real-time performance in time-domain analysis. In this article, we presented a multi-degree-of-freedom MEMS gait detection method, which resolved the problems of single sensor and limited gait phase. We designed a sensor-based gait signal acquisition system, in which gait data acquisition program and feature analysis algorithm were compiled to verify the feasibility of the proposed method. We performed coordinate transformation and corrected position information to eliminate the gait phase detection error caused by random noise interference. Acceleration and angular velocity information were collected from 20 experimenters. We applied an adaptive threshold gait phase detection algorithm to classify the gait information collected by single sensor. To improve the results of gait phase classification, we used multisensor redundant measurement to analyze characteristics of five gait phases. The acceleration and angular velocity information collected by the three sensors placed at instep, ankle, and thigh were input into support vector machine (SVM). The classification results of the five gait phases are approximately 90%. Lastly, we built a human body structure model to simulate human motion in real time, realizing the real-time gait phase detection, which proves effectiveness of the proposed algorithm.

Gait has been widely used in the fields of elderly care, posture correction, and identity recognition. By analyzing and processing the motion parameters and attitude data collected by the sensor, the current gait was determined. In order to pointedly prevent falling in daily life, we proposed a gait pattern classification method based on multisensor. Falling and the gait patterns (standing, sitting/rising, squatting/rising, walking, and running) that falling is likely to happen in daily life were distinguished. Besides, we integrated pressure signals with acceleration signals to compensate for the insufficient data provided by single sensor that cannot fully reflect the complex human motion and solved the problem that falling detection based on acceleration signals is prone to misclassify because certain postures are of similar acceleration changes with falling. For further data analysis, the collected gait data were then transmitted to upper machine for signal processing through the designed wireless network. Combined with the characteristics of gait patterns, we analyzed the corresponding pressure signals, acceleration signals, and resultant acceleration signals. Wavelet energy entropy features and wavelet packet energy features were subsequently extracted from the collected gait data. Finally, we input the randomly selected test data into the established extreme learning machine (ELM) and $K$ -nearest neighbor (KNN) model to test gait pattern recognition effects. The performance of ELM algorithm was better in terms of processing time and classification results, with the highest average identification accuracy, precision, and recall rate of 0.974, 0.937, and 0.936, respectively. Besides, precision–recall (PR) curve was optimal, with the largest area of 0.973. Our presented algorithm responded rapidly and prevented falling in daily lifetime, which can be applied to health monitoring systems to detect daily activities of the elderly promptly.