汇报时间：2023年7月5日(星期三) 上午10: 00

汇报地点：创新港 2号巨构 2-3-161会议室

汇报人：贾亚光

国际会议信息

会议名称：The 20th International Conference on Ubiquitous Robots (UR 2023)

会议时间：June 25-28, 2023

会议地点：Hawai’i Convention Center, Honolulu, Hawaii, United States of American

会议简介：Since its inception in 2004, Ubiquitous Robots has now established itself as a leading mid-size robotics conference, bringing together robotics researchers from around the world who share the vision that robots, like mobile phones, will become ubiquitous in our daily lives, and help connect and empower humans. Robotics is the ultimate interdisciplinary field, and Ubiquitous Robots invites contributions from the entire foundational spectrum—design, perception, manipulation, interfaces, mobility, intelligence—and application domains—industrial, social, transportation, medical, rehabilitation, healthcare, agriculture, construction, security, disaster, and many others. Ubiquitous Robots 2023 promises to be an exciting and innovative event, with oral presentations, spotlight talks, posters, focus sessions, workshops, tutorials, and other new formats that will engage participants.

参会论文信息

Title: Improving the Recognition Accuracy by Solving the Inherent Data Imbalance Problem of ErrP with Generative Adversarial Network

Author: Yaguang Jia, Tangfei Tao, Guanghua Xu, Min Li, Sicong Zhang, Chengcheng Han, Qingqiang Wu, Jinju Pei, Xiaoqing Lv, and Zhilei Shi

Abstract: Brain-computer interface (BCI) has broad application prospects in rehabilitation, neural prosthesis, and exoskeletons. Current electroencephalography (EEG) based BCIs, especially motor imagery (MI) based BCIs, suffer from low recognition accuracy due to their limited signal-to-noise ratio (SNR) and high non-stationarity, which hinders their practical applications. Integrating error-related potential (ErrP) to construct a hybrid BCI and correct the recognition results of the main BCI modal is an effective way to improve the overall performance of BCI system. However, the inherent data imbalance of ErrP leads to the unbalanced classification accuracy, in which the recognition accuracy is low in error trials that makes the system cannot efficiently correct the classification results of the main BCI mode. This study constructed a generative adversarial network (GAN) and used it to generate new data to address the data imbalance of ErrP for the first time. An EEGNET was realized to assess the classification result of the proposed method. The quantitative assessment indicates that the constructed GAN works well in generating new ErrP data. Statistical analysis shows that the proposed method simultaneously improves the degree of inter-class balance of the accuracy and the overall accuracy. The proposed method enhances the self-correction ability of BCI and facilitates its practical application.

欢迎有兴趣的同学届时参加。