24 March 2021 in IEEE Transactions on Affective Computing
A common drawback of EEG-based emotion recognition is that volume conduction effects of the human head introduce interchannel dependence and result in highly correlated information among most EEG features. These highly correlated EEG features cannot provide extra useful information, and they actually reduce the performance of emotion recognition. However, the existing feature selection methods, commonly used to remove redundant EEG features for emotion recognition, ignore the correlation between the EEG features or utilize a greedy strategy to evaluate the interdependence, which leads to the algorithms retaining the correlated and redundant features with similar feature scores in the EEG feature subset. To solve this problem, we propose a novel EEG feature selection method for emotion recognition, termed global redundancy minimization in orthogonal regression (GRMOR). GRMOR can effectively evaluate the dependence among all EEG features from a global view and then select a discriminative and nonredundant EEG feature subset for emotion recognition. To verify the performance of GRMOR, we utilized three EEG emotional data sets (DEAP, SEED, and HDED) with different numbers of channels (32, 62, and 128). The experimental results demonstrate that GRMOR is a promising tool for redundant feature removal and informative feature selection from highly correlated EEG features.
1 December 2018 in Computers in Biology and Medicine
26 June 2023 in IEEE Transactions on Instrumentation and Measurement
Regarding cognitive workload recognition, electroencephalography (EEG) signals are nonstationary across time and vary from different subjects, thus hindering the cross-subject recognition performance. Though subject calibration or collecting massive training data may ease the above problem, it is generally time-consuming and expensive. In this paper, we propose a Deep Domain Adaptation (DDA) scheme for EEG-based cross-subject cognitive workload recognition, using the knowledge from the existing subjects (source domain) to improve the recognition performance of a new subject (target domain). Precisely, the proposed DDA method composes four modules, EEG features extractor, label classifier, feature distribution alignment, and domain discriminator. The model starts with the EEG feature extractor to learn the shallow feature representation for both domains. The label classifier further learns the deep representation and trains the classifier supervised. Finally, the feature distribution alignment matches the shallow feature distribution discrepancy, and the domain discriminator matches the deep distribution discrepancy by the adversarial training with the feature extractor. It not only learns domain-invariant features but also achieves robust domain-adaptive cross-subject recognition results in an end-to-end training framework. We conduct experiments to classify low and high workloads on a self-designed EEG dataset and one public EEG dataset. Experimental results demonstrate that our DDA scheme significantly outperforms the baselines and other state-of-the-art methods with improvements of 2% to 9% in terms of recognition accuracy.
18 January 2024 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Due to the problem of a small amount of EEG samples and relatively high dimensionality of electroencephalogram (EEG) features, feature selection plays an essential role in EEG-based emotion recognition. However, current EEG-based emotion recognition studies utilize a problem transformation approach to transform multi-dimension emotional labels into single-dimension labels, and then implement commonly used single-label feature selection methods to search feature subsets, which ignores the relations between different emotional dimensions. To tackle the problem, we propose an efficient EEG feature selection method for multi-dimension emotion recognition (EFSMDER) via local and global label relevance. First, to capture the local label correlations, EFSMDER implements orthogonal regression to map the original EEG feature space into a low-dimension space. Then, it employs the global label correlations in the original multi-dimension emotional label space to effectively construct the label information in the low-dimension space. With the aid of local and global relevance information, EFSMDER can conduct representational EEG feature subset selection. Three EEG emotional databases with multi-dimension emotional labels were used for performance comparison between EFSMDER and fourteen state-of-the-art methods, and the EFSMDER method achieves the best multi-dimension classification accuracies of 86.43, 84.80, and 97.86 percent on the DREAMER, DEAP, and HDED datasets, respectively.
8 February 2023 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Individual differences among different subjects pose a great challenge to motor imagery (MI) decoding. Multi-source transfer learning (MSTL) is one of the most promising ways to reduce individual differences, which can utilize rich information and align the data distribution among different subjects. However, most MSTL methods in MI-BCI combine all data in the source subjects into a single mixed domain, which will ignore the effect of important samples and the large differences in multiple source subjects. To address these issues, we introduce transfer joint matching and improve it to multi-source transfer joint matching (MSTJM) and weighted MSTJM (wMSTJM). Different from previous MSTL methods in MI, our methods align the data distribution for each pair of subjects, and then integrate the results by decision fusion. Besides that, we design an inter-subject MI decoding framework to verify the effectiveness of these two MSTL algorithms. It mainly consists of three modules: covariance matrix centroid alignment in the Riemannian space, source selection in the Euclidean space after tangent space mapping to reduce negative transfer and computation overhead, and further distribution alignment by MSTJM or wMSTJM. The superiority of this framework is verified on two common public MI datasets from BCI competition IV. The average classification accuracy of the MSTJM and wMSTJ methods outperformed other state-of-the-art methods by at least 4.24% and 2.62% respectively. It’s promising to advance the practical applications of MI-BCI.
16 September 2024 in IEEE Transactions on Industrial Informatics
Although advances in deep learning technologies have greatly facilitated the brain intention decoding from electroencephalogram (EEG) in motor imagery brain–computer interfaces (MI-BCIs), significant individual differences hinder the practical cross-subject MI-BCI applications. Unlike other existing domain adversarial transfer networks that focus on designing different discriminators to reduce individual differences, inspired by the motor lateralization phenomenon, we innovatively utilize transformer and the spatiotemporal pattern differences of EEG as prior knowledge to enhance the feature discriminability in our brain decoding adversarial network. In addition, to address adversarial network decision boundaries bias toward the source domain, we propose a data augmentation method, EEGMix to rapidly mix and enrich the target domain data. With an adaptive adversarial factor, our decoding model reduces the differences in marginal and conditional distribution simultaneously. Three public MI datasets, 2a, 2b, and OpenBMI verified our model's effectiveness. The accuracy achieved 77.49%, 85.19%, and 79.37%, superior to other state-of-the-art algorithms.