期刊文献+

基于表面肌电信号的虚拟座舱动作模式识别

Pattern Recognition of Movement Based on sEMG in Virtual Cockpit Environment
下载PDF
导出
摘要 在虚拟座舱交互头部运动中,长时间使用虚拟现实头盔时仿真参与者会出现了失去方向、恶心呕吐等仿真病。其中,仿真病产生的最重要的原因是视觉延迟。针对突然的头部运动产生的视觉延迟问题,提出了一种基于表面肌电(s EMG)信号的头部动作模式识别的算法。运用算法可成功地从胸锁乳突肌和头夹肌中识别出上仰、旋转和侧弯3种头部运动动作。实验结果表明,径向基函数神经网络具有识别能力强和学习速度快等优点,在模式识别领域具有广阔的发展前景。 Simulation participants will lose the direction and appear the simulation of disease such as nausea and vomiting when they wear virtual reality helmet for a long time in virtual cockpit interaction head movement environment.Visual lag is the most important cause which generates the simulation disease.In view of visual lag problem caused by sudden rapid head movement,this paper presents a pattern recognition algorithm of head movement based on surface EMG signals .Applying this algorithm can successfully identify three types of movements of human head:nose-up pitch,rotating and lateral bending from cleidomastoid and musculi splenius capitis.The experimental result shows that RBF neural network has a great potential development in the field of pattern recognition because of the advantages such as high pattern recognition ability,fast learning speed,etc.
出处 《航空计算技术》 2015年第5期28-32,共5页 Aeronautical Computing Technique
基金 国家自然科学基金项目资助(51205195 61039002) 江苏省自然科学基金项目资助(BK20130981) 南京航空航天大学研究生创新基金项目资助(KFJJ20130223 KFJJ201472)
关键词 虚拟座舱 表面肌电信号 特征提取 径向基函数神经网络 模式识别 visual cockpit surface electromyography signal feature extraction radial basis function neural network pattern recognition
  • 相关文献

参考文献9

  • 1陈浩磊,邹湘军,陈燕,陈燕(2),刘天湖.虚拟现实技术的最新发展与展望[J].中国科技论文在线,2011,6(1):1-5. 被引量:183
  • 2Barniv Y, Aguilar M, Hasanbelliu E. Using EMG to Antici- pate Head Motion for Virtual-environment Applications[J]. Biomedical Engineering, IEEE Transactions on, 2005, 52 (6) : 1078 - 1093.
  • 3Karlsson L, Hammarberg B, St/llberg E. An Application of a Muscle Model to Study Electromyographic Signals [ J ]. Com- puter Methods and Programs in Biomedicine, 2003,71 ( 3 ) : 225 - 233.
  • 4Sommerich C M,.Ioines S M B, Hermans V, et al. Use of Sur- face Electromyography to Estimate Neck Muscle Activity [ J ]. Journal of Electromyography and Kinesiology, 2000,10 (6) :377 - 398.
  • 5雷敏,王志中.肌电假肢控制中的表面肌电信号的研究进展与展望[J].中国医疗器械杂志,2001,25(3):156-160. 被引量:37
  • 6Zalzala A M S, Chaiyaratana N. Myoelectric Signal Classifica- tion Using Evolutionary Hybrid RBF- MLP Networks [ C ]// Evolutionary Computation, 2000. Proceedings of the 2000 Congress on. IEEE, 2000:691 - 698.
  • 7Khezri M, Jahed M. Real- time Intelligent Pattern Recognition Algorithm for Surface EMG Signals[J]. Biomed Eng Online, 2007,6(45) :1 - 12.
  • 8Naik G R, Kumar D K. Twin SVM for Gesture Classification Using the Surface Eleetromyogram [ J ]. Information Technol- ogy in Biomedicine, IEEE Transactions on, 2010,14 ( 2 ) : 301 - 308.
  • 9Englehart K, Hudgin B, Parker P. A Wavelet- based Contin- uous Classification Seheme for Muhifunetion Myoeleetrie Control[ J ]. Biomedical Engineering, IEEE Transactions on, 2001,48(3) :302 -311.

二级参考文献31

共引文献218

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部