机器人2026，Vol.48Issue(2)：363-374,12.DOI:10.13973/j.cnki.robot.240302
基于OmniXceptionDBN的表面肌电信号智能识别方法
An Intelligent Recognition Method of Surface Electromyography Signal Based on OmniXceptionDBN
摘要
Abstract
Surface electromyography(sEMG)has important theoretical research value and practical application significance in fields such as human-computer interaction(HCI),but existing methods often face challenges of significantly reduced accuracy and high computational complexity when processing signals from multiple subjects.To address these issues,a robust and intelligent sEMG recognition method based on the multi-scale integrated sequence deep belief network(OmniXceptionDBN)is proposed.Firstly,the raw signals is processed using singular spectrum analysis and fast Fourier transform,and then the OmniXceptionDBN algorithm is constructed by combining XceptionTime,OmniScaleCNN,and deep belief networks(DBN)for sEMG recognition and experimental verification.The results indicate that algorithm achieves a classification accuracy of 97.2%for a single individual subjects and 85.9%for multiple subjects without any additional operations.The proposed approach effectively addresses the challenges of accuracy degradation and high computational complexity by traditional methods in cross-subject signal processing,providing an efficient and robust solution for the field of sEMG intelligent recognition.关键词
表面肌电信号/深度信念网络/动作识别/特征提取Key words
surface electromyography signal/deep belief networks/action recognition/feature extraction引用本文复制引用
赵孝礼,宋艺博,胡渊豪,赵思源,何显松,张站,姚建勇,严颖,邵海东..基于OmniXceptionDBN的表面肌电信号智能识别方法[J].机器人,2026,48(2):363-374,12.基金项目
国家重点研发计划(2024YFB4709600) （2024YFB4709600）
国家自然科学基金(52205062) （52205062）
江苏省自然科学基金(BK20220950) （BK20220950）
智控实验室开放基金(ICL-2023-0305) （ICL-2023-0305）
国防科技大学装备状态感知与敏捷保障全国重点实验室基金(6142003202415) （6142003202415）
国家市场监督管理总局高参数电梯智能运维重点实验室开放课题(JSTJ-IOMHL-202503) （JSTJ-IOMHL-202503）
上海航天科技创新基金(SAST2024-055) （SAST2024-055）
民用航天预研项目(D020110). （D020110）
