3 August 2020 in IEEE Transactions on Neural Networks and Learning Systems
In the context of motor imagery, electroencephalography (EEG) data vary from subject to subject such that the performance of a classifier trained on data of multiple subjects from a specific domain typically degrades when applied to a different subject. While collecting enough samples from each subject would address this issue, it is often too time-consuming and impractical. To tackle this problem, we propose a novel end-to-end deep domain adaptation method to improve the classification performance on a single subject (target domain) by taking the useful information from multiple subjects (source domain) into consideration. Especially, the proposed method jointly optimizes three modules, including a feature extractor, a classifier, and a domain discriminator. The feature extractor learns the discriminative latent features by mapping the raw EEG signals into a deep representation space. A center loss is further employed to constrain an invariant feature space and reduce the intrasubject nonstationarity. Furthermore, the domain discriminator matches the feature distribution shift between source and target domains by an adversarial learning strategy. Finally, based on the consistent deep features from both domains, the classifier is able to leverage the information from the source domain and accurately predict the label in the target domain at the test time. To evaluate our method, we have conducted extensive experiments on two real public EEG data sets, data set IIa, and data set IIb of brain-computer interface (BCI) Competition IV. The experimental results validate the efficacy of our method. Therefore, our method is promising to reduce the calibration time for the use of BCI and promote the development of BCI.
1 August 2020 in Medical Image Analysis
1 July 2021 in IEEE Transactions on Medical Imaging
As the labeled anomalous medical images are usually difficult to acquire, especially for rare diseases, the deep learning based methods, which heavily rely on the large amount of labeled data, cannot yield a satisfactory performance. Compared to the anomalous data, the normal images without the need of lesion annotation are much easier to collect. In this paper, we propose an anomaly detection framework, namely $\mathbb {SALAD}$ , extracting $\mathbb {S}$ elf-supervised and tr $\mathbb {A}$ ns $\mathbb {L}$ ation-consistent features for $\mathbb {A}$ nomaly $\mathbb {D}$ etection. The proposed SALAD is a reconstruction-based method, which learns the manifold of normal data through an encode-and-reconstruct translation between image and latent spaces. In particular, two constraints ( i.e. , structure similarity loss and center constraint loss) are proposed to regulate the cross-space ( i.e. , image and feature) translation, which enforce the model to learn translation-consistent and representative features from the normal data. Furthermore, a self-supervised learning module is engaged into our framework to further boost the anomaly detection accuracy by deeply exploiting useful information from the raw normal data. An anomaly score, as a measure to separate the anomalous data from the healthy ones, is constructed based on the learned self-supervised-and-translation-consistent features. Extensive experiments are conducted on optical coherence tomography (OCT) and chest X-ray datasets. The experimental results demonstrate the effectiveness of our approach.
25 February 2020 in IEEE Transactions on Cognitive and Developmental Systems
Human emotion recognition could greatly contribute to human-computer interaction with promising applications in artificial intelligence. One of the challenges in recognition tasks is learning effective representations with stable performances from electroencephalogram (EEG) signals. In this paper, we propose a novel deep-learning framework, named channel-fused dense convolutional network, for EEG-based emotion recognition. First, we use a 1D convolution layer to receive weighted combinations of contextual features along the temporal dimension from EEG signals. Next, inspired by state-of-the-art object classification techniques, we employ 1D dense structures to capture electrode correlations along the spatial dimension. The developed algorithm is capable of handling temporal dependencies and electrode correlations with effective feature extraction from noisy EEG signals. Finally, we perform extensive experiments based on two popular EEG emotion datasets. Results indicate that our framework achieves prominent average accuracies of 90.63% and 92.58% on the SEED and DEAP datasets respectively, which both receive better performances than most of the compared studies. The novel model provides an interpretable solution with excellent generalization capacity for broader EEG-based classification tasks.
15 February 2021 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
Electroencephalogram (EEG) has been widely used in brain computer interface (BCI) due to its convenience and reliability. The EEG-based BCI applications are majorly limited by the time-consuming calibration procedure for discriminative feature representation and classification. Existing EEG classification methods either heavily depend on the handcrafted features or require adequate annotated samples at each session for calibration. To address these issues, we propose a novel dynamic joint domain adaptation network based on adversarial learning strategy to learn domain-invariant feature representation, and thus improve EEG classification performance in the target domain by leveraging useful information from the source session. Specifically, we explore the global discriminator to align the marginal distribution across domains, and the local discriminator to reduce the conditional distribution discrepancy between sub-domains via conditioning on deep representation as well as the predicted labels from the classifier. In addition, we further investigate a dynamic adversarial factor to adaptively estimate the relative importance of alignment between the marginal and conditional distributions. To evaluate the efficacy of our method, extensive experiments are conducted on two public EEG datasets, namely, Datasets IIa and IIb of BCI Competition IV. The experimental results demonstrate that the proposed method achieves superior performance compared with the state-of-the-art methods.