Parkinson's disease (PD) is a complicated neurological ailment that affects both the physical and mental wellness of elderly individuals which makes it problematic to diagnose in its initial stages. Electroencephalogram (EEG) promises to be an efficient and cost-effective method for promptly detecting cognitive impairment in PD. Nevertheless, prevailing diagnostic practices utilizing EEG features have failed to examine the functional connectivity among EEG channels and the response of associated brain areas causing an unsatisfactory level of precision. Here, we construct an attention-based sparse graph convolutional neural network (ASGCNN) for diagnosing PD. Our ASGCNN model uses a graph structure to represent channel relationships, the attention mechanism for selecting channels, and the L1 norm to capture channel sparsity. We conduct extensive experiments on the publicly available PD auditory oddball dataset, which consists of 24 PD patients (under ON/OFF drug status) and 24 matched controls, to validate the effectiveness of our method. Our results show that the proposed method provides better results compared to the publicly available baselines. The achieved scores for Recall, Precision, F1-score, Accuracy and Kappa measures are 90.36%, 88.43%, 88.41%, 87.67%, and 75.24%, respectively. Our study reveals that the frontal and temporal lobes show significant differences between PD patients and healthy individuals. In addition, EEG features extracted by ASGCNN demonstrate significant asymmetry in the frontal lobe among PD patients. These findings can offer a basis for the establishment of a clinical system for intelligent diagnosis of PD by using auditory cognitive impairment features.

Objective. Major depressive disorder (MDD) is a prevalent psychiatric disorder whose diagnosis relies on experienced psychiatrists, resulting in a low diagnosis rate. As a typical physiological signal, electroencephalography (EEG) has indicated a strong association with human beings’ mental activities and can be served as an objective biomarker for diagnosing MDD. Approach. The basic idea of the proposed method fully considers all the channel information in EEG-based MDD recognition and designs a stochastic search algorithm to select the best discriminative features for describing the individual channels. Main results. To evaluate the proposed method, we conducted extensive experiments on the MODMA dataset (including dot-probe tasks and resting state), a 128-electrode public EEG-based MDD dataset including 24 patients with depressive disorder and 29 healthy controls. Under the leave-one-subject-out cross-validation protocol, the proposed method achieved an average accuracy of 99.53% in the fear-neutral face pairs cued experiment and 99.32% in the resting state, outperforming state-of-the-art MDD recognition methods. Moreover, our experimental results also indicated that negative emotional stimuli could induce depressive states, and high-frequency EEG features contributed significantly to distinguishing between normal and depressive patients, which can be served as a marker for MDD recognition. Significance. The proposed method provided a possible solution to an intelligent diagnosis of MDD and can be used to develop a computer-aided diagnostic tool to aid clinicians in early diagnosis for clinical purposes.

One of the primary challenges in Electroencephalogram (EEG) emotion recognition lies in developing models that can effectively generalize to new unseen subjects, considering the significant variability in EEG signals across individuals. To address the issue of subject-specific features, a suitable approach is to employ projection dictionary learning, which enables the identification of emotion-relevant features across different subjects. To accomplish the objective of pattern representation and discrimination for subject-independent EEG emotion recognition, we utilized the fast and efficient projection dictionary pair learning (PDPL) technique. PDPL involves the joint use of a synthesis dictionary and an analysis dictionary to enhance the representation of features. Additionally, to optimize the parameters of PDPL, which depend on experience, we applied the genetic algorithm (GA) to obtain the optimal solution for the model. We validated the effectiveness of our algorithm using leave-one-subject-out cross validation on three EEG emotion databases: SEED, MPED, and GAMEEMO. Our approach outperformed traditional machine learning methods, achieving an average accuracy of 69.89% on the SEED database, 24.11% on the MPED database, 64.34% for the two-class GAMEEMO, and 49.01% for the four-class GAMEEMO. These results highlight the potential of subject-independent EEG emotion recognition algorithms in the development of intelligent systems capable of recognizing and responding to human emotions in real-world scenarios.

Objective . A brain–computer interface (BCI) equips humans with the ability to control computers and technical devices mentally. However, the enormous data and the existing irrelevant features of the electrocorticogram signal limit the performance of the classifier. To address these problems, a novel signal processing framework for a binary motor imagery-based BCI system (MI–BCI) is proposed in this paper. Approach . Stockwell transform and Bayesian linear discriminant analysis were applied to feature extraction and classification, respectively, and a genetic algorithm (GA) was used in the process of feature selection to extract the most relevant features for classification. The superiority of the algorithm is demonstrated through test results based on the BCI Competition III dataset I. Main results . By comparing the processes with or without feature selection, the performance of the classification was proven to improve using the GA. By adjusting the parameters of the GA, the best feature set (selected 48.6% features) was selected to achieve classification sensitivity, specificity, precision, and accuracy of 94%, 98%, 97.9%, and 96%, respectively, exceeding the results of the existing state-of-the art algorithms. Significance . As the proposed method can reduce the number of features and select the best feature set, its classification performance was improved and the classification time was shortened; thus, it can be applied to various BCI systems.

Brain-computer interface (BCI) is a system for communication and control between the human brain and computers or other electronic devices. However, multichannel signal acquisition, which is time-consuming, laborious, and not conducive to subsequent real-time signal processing, can cause channel redundancy. When designing a BCI system, the selection of the optimal channels that match the expected pattern of potential cortical activity is useful for classifying brain activity during a mental task. The Stockwell transform and Bayesian linear discriminant analysis were applied to feature extraction and classification, respectively, and a genetic algorithm (GA) was used in the process of channel selection to extract the most relevant channel for classification. The superior performance of the algorithm is demonstrated by the test results on BCI Competition III dataset I. For a motor imagery paradigm, we show that the number of used channels can be reduced significantly, and the classification performance of the classifier can be improved. By comparing the performances of the algorithm with or without channel selection, the best channel combination was selected, and only 28 out of the 64 acquisition electrodes were used to realize classification sensitivity, specificity, precision, accuracy and Kappa coefficient values of 98%, 96%, 96.08%, 97% and 0.94, respectively, thereby outperforming existing algorithms. The proposed algorithm can reduce the number of channels and select the best channel combination to improve the classification performance, thereby overcoming the redundant channel problem. In addition, the signal processing framework that is adopted by this research can serve as a reference for related BCI application system research.

In this paper, we focus on a challenging, but interesting, task in speech emotion recognition (SER), i.e., cross-corpus SER. Unlike conventional SER, a feature distribution mismatch may exist between the labeled source (training) and target (testing) speech samples in cross-corpus SER because they come from different speech emotion corpora, which degrades the performance of most well-performing SER methods. To address this issue, we propose a novel transfer subspace learning method called multiple distribution-adapted regression (MDAR) to bridge the gap between speech samples from different corpora. Specifically, MDAR aims to learn a projection matrix to build the relationship between the source speech features and emotion labels. A novel regularization term called multiple distribution adaption (MDA), consisting of a marginal and two conditional distribution-adapted operations, is designed to collaboratively enable such a discriminative projection matrix to be applicable to the target speech samples, regardless of speech corpus variance. Consequently, by resorting to the learned projection matrix, we are able to predict the emotion labels of target speech samples when only the source label information is given. To evaluate the proposed MDAR method, extensive cross-corpus SER tasks based on three different speech emotion corpora, i.e., EmoDB, eNTERFACE, and CASIA, were designed. Experimental results showed that the proposed MDAR outperformed most recent state-of-the-art transfer subspace learning methods and even performed better than several well-performing deep transfer learning methods in dealing with cross-corpus SER tasks.