Bingyang Teng

Bingyang Teng

Auto-generated profile, based on publicly available information

Bingyang Teng

College of Electrical and Control Engineering, Xian University of Science and Technology, Xian, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
12 March 2024 in IEEE Transactions on Biomedical Engineering
Verified
Journal Article
Closed access
HPHongguang Pan
Hongguang Pan
YWYiran Wang
Yiran Wang
ZLZhuoyi Li
Zhuoyi Li
XCXin Chu
Xin Chu
BTBingyang Teng
Bingyang Teng
HGHongzheng Gao
Hongzheng Gao
Some classification studies of brain–computer interface (BCI) based on speech imagery show potential for improving communication skills in patients with amyotrophic lateral sclerosis (ALS). However, current research on speech imagery is limited in scope and primarily focuses on vowels or a few selected words. In this paper, we propose a complete research scheme for multi-character classification based on EEG signals derived from speech imagery. Firstly, we record 31 speech imagery contents, including 26 alphabets and 5 commonly used punctuation marks, from seven subjects using a 32-channel electroencephalogram (EEG) device. Secondly, we introduce the wavelet scattering transform (WST), which shares a structural resemblance to Convolutional Neural Networks (CNNs), for feature extraction. The WST is a knowledge-driven technique that preserves high-frequency information and maintains the deformation stability of EEG signals. To reduce the dimensionality of wavelet scattering coefficient features, we employ Kernel Principal Component Analysis (KPCA). Finally, the reduced features are fed into an Extreme Gradient Boosting (XGBoost) classifier within a multi-classification framework. The XGBoost classifier is optimized through hyperparameter tuning using grid search and 10-fold cross-validation, resulting in an average accuracy of 78.73% for the multi-character classification task. We utilize t-Distributed Stochastic Neighbor Embedding (t-SNE) technology to visualize the low-dimensional representation of multi-character speech imagery. This visualization effectively enables us to observe the clustering of similar characters. The experimental results demonstrate the effectiveness of our proposed multi-character classification scheme. Furthermore, our classification categories and accuracy exceed those reported in existing research.

16 September 2024 in IEEE Transactions on Cognitive and Developmental Systems
Verified
Journal Article
Closed access
HPHongguang Pan
Hongguang Pan
STShiyu Tong
Shiyu Tong
XWXuqiang Wei
Xuqiang Wei
BTBingyang Teng
Bingyang Teng
The fatigue factor is widely recognized as a primary contributor to accidents in the mining industry. Proactively recognizing fatigue states in miners before starting work can effectively establish a safety boundary for both miners safety and coal mine production. Therefore, this study designs a fatigue state recognition system for miners based on a multi-modal extraction and fusion framework. Firstly, the system is equipped with various sensors, a core processor and a display to collect and process physiological data such as electrocardiogram (ECG), electrodermal activity (EDA), blood pressure (BP), blood oxygen saturation (SpO2), skin temperature (SKT), as well as facial data, and to present fatigue state, respectively. Secondly, based on the multi-modal feature extraction and fusion framework, after the necessary preprocessing steps, the system extracts physiological features by time and frequency domain analysis, extracts facial features by ResNeXt-50 and gated recurrent unit (GRU), and fuses multi-features by Transformer+. Finally, in the comprehensive lab for coal-related programs of Xi’an University of Science and Technology, we test the system and build a multimodal dataset, and the results demonstrate an average accuracy of 93.15%.