首页|Xi’an Jiaotong University Reports Findings in Robotics (Crossdomain prediction approach of human lower limb voluntary movement intention for exoskeleton robot based on EEG signals)
Xi’an Jiaotong University Reports Findings in Robotics (Crossdomain prediction approach of human lower limb voluntary movement intention for exoskeleton robot based on EEG signals)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Robotics is the subjec t of a report. According to news originating from Shaanxi, People’s Republic of China, by NewsRx correspondents, research stated, “Exoskeleton robot control sho uld ideally be based on human voluntary movement intention. The readiness potent ial (RP) component of the motion-related cortical potential is observed before m ovement in the electroencephalogram and can be used for intention prediction.” Our news journalists obtained a quote from the research from Xi’an Jiaotong Univ ersity, “However, its single-trial features are weak and highly variable, and ex isting methods cannot achieve high crosstemporal and cross-subject accuracies i n practical online applications. Therefore, this work aimed to combine a deep co nvolutional neural network (CNN) framework with a transfer learning (TL) strateg y to predict the lower limb voluntary movement intention, thereby improving the accuracy while enhancing the model generalization capability; this would also pr ovide sufficient processing time for the response of the exoskeleton robotic sys tem and help realize robot control based on the intention of the human body. The signal characteristics of the RP for lower limb movement were analyzed, and a p arameter TL strategy based on CNN was proposed to predict the intention of volun tary lower limb movements. We recruited 10 subjects for offline and online exper iments. Multivariate empirical-mode decomposition was used to remove the artifac ts, and the moment of onset of voluntary movement was labeled using lower limb e lectromyography signals during network training. The RP features can be observed from multiple data overlays before the onset of voluntary lower limb movements, and these features have long latency periods. The offline experimental results showed that the average movement intention prediction accuracy was 95.23 % ? 1.25% for the right leg and 91.21% ? 1.48% for the left leg, which showed good cross-temporal and cross-subject generalizat ion while greatly reducing the training time. Online movement intention predicti on can predict results about 483.9 ? 11.9 ms before movement onset with an avera ge accuracy of 82.75 %.”
ShaanxiPeople’s Republic of ChinaAsi aEmerging TechnologiesMachine LearningRobotRobotics
NETL
NSTL
