Liang Xie

Liang Xie

Auto-generated profile, based on publicly available information

Liang Xie

Defense Innovation Institute, Academy of Military Sciences (AMS), Beijing, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 March 2021 in Frontiers in Human Neuroscience
Verified
Journal Article
Open access
YPYu Pei
Yu Pei
ZLZhiguo Luo
Zhiguo Luo
YYYe Yan
Ye Yan
HYHuijiong Yan
Huijiong Yan
JJJing Jiang
Jing Jiang
EYErwei Yin
Erwei Yin
The quality and quantity of training data are crucial to the performance of a deep-learning-based brain-computer interface (BCI) system. However, it is not practical to record EEG data over several long calibration sessions. A promising time- and cost-efficient solution is artificial data generation or data augmentation (DA). Here, we proposed a DA method for the motor imagery (MI) EEG signal called brain-area-recombination (BAR). For the BAR, each sample was first separated into two ones (named half-sample) by left/right brain channels, and the artificial samples were generated by recombining the half-samples. We then designed two schemas (intra- and adaptive-subject schema) corresponding to the single- and multi-subject scenarios. Extensive experiments using the classifier of EEGnet were conducted on two public datasets under various training set sizes. In both schemas, the BAR method can make the EEGnet have a better performance of classification (p < 0.01). To make a comparative investigation, we selected two common DA methods (noise-added and flipping), and the BAR method beat them (p < 0.05). Further, using the proposed BAR for augmentation, EEGnet achieved up to 8.3% improvement than a typical decoding algorithm CSP-SVM (p < 0.01), note that both the models were trained on the augmented dataset. This study shows that BAR usage can significantly improve the classification ability of deep learning to MI-EEG signals. To a certain extent, it may promote the development of deep learning technology in the field of BCI.

14 March 2025 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
YPYu Pei
Yu Pei
SZShaokai Zhao
Shaokai Zhao
LXLiang Xie
Liang Xie
ZLZhiguo Luo
Zhiguo Luo
DZDongdong Zhou
Dongdong Zhou
EYErWei Yin
ErWei Yin
Negative emotion recognition during manipulation task plays crucial role in human-machine interaction, where diverse cognitive variables coexist and influence each other. However, traditional emotion experiments often overemphasize emotion induction while overlooking other practical cognitive tasks, which leads participants to suffer from simplistic emotional experiences and ultimately compromises the real-world applicability of the emotional data collected. To incorporate critical cognitive variables into emotion elicitation, we utilize joystick-based real-time emotion annotation to encourage subjects to continuously feel emotional intensity, to advisedly decide when to manipulate the joystick, and to physically operate it. Consequently, at least two essential cognitive variables—decision-making and action—are integrated into emotion perception. Following this, we develop a novel negative emotion dataset called CRED, which includes a variety of physiological data, particularly Electroencephalograph (EEG). To assess the stability of emotional EEG patterns, we employ strict statistical analysis and a dual-branch transformer (DBT) with the gradient-based attribution method on the proposed CRED. Additionally, two well-known public datasets (SEED, and SEED-V) are used to verify the DBT. Compared to traditional methods, DBT improves classification accuracy by approximately 5% on CRED and by around 2% on the public datasets. The experimental results indicate that the occipital lobe plays a crucial role in the discrimination of negative emotions; the critical frequency bands vary between the five emotions in the CRED. Specifically, the low-delta rhythm is associated with anger, while fear is influenced by both theta and alpha rhythms; disgust is found to be significant in the theta rhythm; and for neutral emotions, both low-delta and alpha rhythms are identified as crucial. In summary, our findings demonstrate the existence of stable emotional EEG patterns when additional cognitive variables are involved. The CRED and the source codes will be released at https://huggingface.co/datasets/peiyu999/CRED.

10 April 2024 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
LYLu Yue
Lu Yue
DZDongliang Zhou
Dongliang Zhou
LXLiang Xie
Liang Xie
FZFeitian Zhang
Feitian Zhang
YYYe Yan
Ye Yan
EYErWei Yin
ErWei Yin
The task of vision-and-language navigation in continuous environments (VLN-CE) aims at training an autonomous agent to perform low-level actions to navigate through 3D continuous surroundings using visual observations and language instructions. The significant potential of VLN-CE for mobile robots has been demonstrated across a large number of studies. However, most existing works in VLN-CE focus primarily on transferring the standard discrete vision-and-language navigation (VLN) methods to continuous environments, overlooking the problem of collisions. Such oversight often results in the agent deviating from the planned path or, in severe instances, the agent being trapped in obstacle areas and failing the navigational task. To address the above-mentioned issues, this letter investigates various collision scenarios within VLN-CE and proposes a classification method to predicate the underlying causes of collisions. Furthermore, a new VLN-CE algorithm, named Safe-VLN, is proposed to bolster collision avoidance capabilities including two key components, i.e., a waypoint predictor and a navigator. In particular, the waypoint predictor leverages a simulated 2D LiDAR occupancy mask to prevent the predicted waypoints from being situated in obstacle-ridden areas. The navigator, on the other hand, employs the strategy of ‘re-selection after collision’ to prevent the robot agent from becoming ensnared in a cycle of perpetual collisions. The proposed Safe-VLN is evaluated on the R2R-CE, the results of which demonstrate an enhanced navigational performance and a statistically significant reduction in collision incidences.

18 September 2023 in IEEE Transactions on Cognitive and Developmental Systems
Verified
Journal Article
Closed access
YZYakun Zhang
Yakun Zhang
HCHuihui Cai
Huihui Cai
JWJinghan Wu
Jinghan Wu
LXLiang Xie
Liang Xie
MXMinpeng Xu
Minpeng Xu
EYErWei Yin
ErWei Yin
Machine learning techniques have achieved great success in electromyography (EMG) decoding, but EMG-based cross-subject silent speech recognition (SSR) received less attention because of its high individual variability. Therefore, this paper explores the field of cross-subject SSR to improve the recognition performance of EMG data collected from new subjects. Firstly, this paper reports on applying time-series features and one-dimensional convolutional neural networks (1D-CNN) for cross-subject SSR. Secondly, this paper proposes using a conditional domain adversarial network (CDAN) to solve the problem of reduced cross-subject SSR accuracy in the few samples’ datasets. It innovatively integrates the maximum mean difference (MMD) loss to get an improved condition domain adversarial network (ICDAN). While 1D-CNN is a feature extraction network that can meet the needs of cross subject silent speech recognition in large datasets, the recognition effect will be weakened in small datasets. Adding an ICDAN network after the feature extraction network can improve the problem of data distribution differences between the two domains, and further enhance recognition performance. The results show that the 1D-CNN model based on time-series features yields better results in the SSR of new subjects, and the ICDAN model can further improve the classification accuracy of cross-subjects in a few sample datasets by 14.88%.

19 January 2024 in Journal of Integrative Neuroscience
Verified
Journal Article
Open access
PDF file
XWXiaomin Wang
Xiaomin Wang
YPYu Pei
Yu Pei
ZLZhiguo Luo
Zhiguo Luo
SZShaokai Zhao
Shaokai Zhao
LXLiang Xie
Liang Xie
DMDong Ming
Dong Ming
Background: Affective computing has gained increasing attention in the area of the human-computer interface where electroencephalography (EEG)-based emotion recognition occupies an important position. Nevertheless, the diversity of emotions and the complexity of EEG signals result in unexplored relationships between emotion and multichannel EEG signal frequency, as well as spatial and temporal information. Methods: Audio-video stimulus materials were used that elicited four types of emotions (sad, fearful, happy, neutral) in 32 male and female subjects (age 21–42 years) while collecting EEG signals. We developed a multidimensional analysis framework using a fusion of phase-locking value (PLV), microstates, and power spectral densities (PSDs) of EEG features to improve emotion recognition. Results: An increasing trend of PSDs was observed as emotional valence increased, and connections in the prefrontal, temporal, and occipital lobes in high-frequency bands showed more differentiation between emotions. Transition probability between microstates was likely related to emotional valence. The average cross-subject classification accuracy of features fused by Discriminant Correlation Analysis achieved 64.69%, higher than that of single mode and direct-concatenated features, with an increase of more than 7%. Conclusions: Different types of EEG features have complementary properties in emotion recognition, and combining EEG data from three types of features in a correlated way, improves the performance of emotion classification.

10 March 2025 in Neural Networks
Verified
Journal Article
Closed access
SWSen Wang
Sen Wang
DZDongliang Zhou
Dongliang Zhou
LXLiang Xie
Liang Xie
CXChao Xu
Chao Xu
YYYe Yan
Ye Yan
EYErWei Yin
ErWei Yin