X
Xun Chen
Researcher at University of Science and Technology of China
Publications - 230
Citations - 7083
Xun Chen is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Medicine. The author has an hindex of 27, co-authored 143 publications receiving 3549 citations. Previous affiliations of Xun Chen include University of British Columbia & Hefei University of Technology.
Papers
More filters
Patent
Intelligent text input method
TL;DR: In this paper, an intelligent text input method consisting of acquiring an electromyographic signal and a motion signal when a finger knocks in a current input mode is presented. But the method is limited to the condition of any plane or complete separation from a plane carrier and the limitation requirement of a traditional input keyboard on input equipment and an input plane is eliminated.
Frequency Information Enhanced Deep EEG Denoising Network for Ocular Artifact Removal
TL;DR: In this paper , a cross-domain framework was proposed to integrate knowledge of both time and frequency domains into a deep-learning model for ocular artifact removal from EEG recordings, which can be flexibly implemented on various deep denoising networks to improve their performance.
Proceedings ArticleDOI
Time varying brain connectivity modeling using FMRI signals
TL;DR: Simulation results demonstrate that the proposed method could improve the accuracy in estimating time-dependent connectivity patterns and is applied to real fMRI data set for studying time-varying resting-state brain connectivity networks.
Proceedings ArticleDOI
Investigation on the Contributions of Different Muscles to the Generated Force based on HD-sEMG and DBN *
TL;DR: The experimental result demonstrates that in multi-muscle contraction task, not all muscles are suitable for force estimation, the force estimation accuracy obtained using only one muscle approximates even exceeds that obtained using multiple muscles, and the relative contributions of different muscle groups to the force can be obtained according to the ranking of MIVs.
Journal ArticleDOI
Spatio-temporal MLP network for seizure prediction using EEG signals
TL;DR: Wang et al. as mentioned in this paper proposed an end-to-end epilepsy seizure prediction method based on multi-layer perceptrons (MLPs), which mainly contains two functional blocks: the denoising-weighted block and the MLPs block.