YANG Zhongliang,CHEN Yumiao.An sEMG approach to recognize the body language of the head based on the GGA-Elman network[J].CAAI Transactions on Intelligent Systems,2014,9(04):385-391.[doi:10.3969/j.issn.1673-4785.201310047]





An sEMG approach to recognize the body language of the head based on the GGA-Elman network
杨钟亮1 陈育苗2
1. 东华大学 机械工程学院, 上海 201620;
2. 东华大学 服装·艺术设计学院, 上海 200051
YANG Zhongliang1 CHEN Yumiao2
1. College of Mechanical Engineering, Donghua University, Shanghai 201620, China;
2. Fashion · Art Design Institute, Donghua University, Shanghai 200051, China
head movementbody languagesurface electromyographymuscletime domain analysisneural networkgenetic algorithmpattern recognition
为提高头部体态语言表达"同意"与"不同意"态度的识别效果, 提出结合贪心遗传算法和Elman神经网络的表面肌电识别方法。通过前导实验分别采集8名被试者点头与摇头时颈部肌肉的表面肌电信号, 利用Wilcoxon秩和检验提取具有显著性差异的10个肌电时域特征值, 进而基于贪心遗传算法优化的Elman神经网络建立体态语言识别模型。实验结果表明, 该模型能成功识别自发表达"同意"与"不同意"的头部体态语言, 与标准Elman神经网络和BP神经网络的识别模型相比, 相关系数更高、均方误差更小, 对测试集的正确识别率提高了3.2%以上, 从而验证了该方法的可靠性。
In order to improve the recognition effects of the "agreement" and "disagreement" attitudes expressed by the body language of the head movements, a surface electromyography (sEMG) approach in combination with the greedy genetic algorithm (GGA) and the Elman neural network is proposed. The sEMG signals of the neck muscles were detected while eight participants were nodding and shaking their heads respectively during a pilot experiment. By means of the Wilcoxon’s signed-rank test, ten features of the sEMG time domain indices were extracted with significant differences. Furthermore, the body language recognition model was constructed based on the Elman network optimized by GGA. Experimental results show that the model can successfully recognize the "agreement and disagreement" attitudes spontaneously expressed by the different body languages of the head. Compared with the recognition models using the standard Elman and BP network, the correlation coefficient of this present model is higher, the mean squared error is less, and the correct recognition rate of the test set is increases by over 3.2%, which demonstrate the reliability of this approach.


[1] DARWIN C. The expression of the emotions in man and animals[M]. 3rd ed. New York: Oxford University Press, 1998:28-68.
[2] MEHRABIAN A. Nonverbal communication[M]. Chicago: Aldine-Atherton, 1972: 1-15.
[3] FRAGOPANAGOS N, TAYLOR J G. Emotion recognition in human-computer interaction[J]. Neural Networks, 2005, 18(4): 389-405.
[4] EKMAN P. An argument for basic emotions[J]. Cognition and Emotion, 1992, 6(3/4): 169-200.
[5] COHEN S. A computerized scale for monitoring levels of agreement during a conversation[J]. University of Pennsylvania Working Papers in Linguistics, 2003, 8(1): 57-70.
[6] BOUSMALIS K, MEHU M, PANTIC M. Towards the automatic detection of spontaneous agreement and disagreement based on nonverbal behavior: a survey of related cues, databases, and tools[J]. Image and Vision Computing, 2013, 31(2): 203-221.
[7] VINCIARELLI A, PANTIC M, BOURLARD H. Social signal processing: survey of an emerging domain[J]. Image and Vision Computing, 2009, 27(12): 1743-1759.
[8] MURPHY-CHUTORIAN E, TRIVEDI M M. Head pose estimation in computer vision: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(4):607-626.
[9] ZHAO Yisu. Human emotion recognition from body language of the head using soft computing techniques[D]. Ottawa, Canada: University of Ottawa, 2012: 14-30.
[10] 王健. sEMG信号分析及其应用研究进展[J]. 体育科学, 2000, 20(4): 56-60.WANG Jian. Some advances in the research of sEMG signal analysis and its application[J]. Sport Science, 2000, 20(4): 56-60.
[11] AHSAN M R, IBRAHIMY M I, KHALIFA O O. EMG signal classification for human computer interaction: a review[J]. European Journal of Scientific Research, 2009, 33(3): 480-501.
[12] 张旭. 基于表面肌电信号的人体动作识别与交互[D]. 合肥:中国科学技术大学, 2010: 8-13.ZHANG Xu. Body gesture recognition and interaction based on surface electromyogram[D]. Hefei: University of Seience and Teehnology of China, 2010: 8-13.
[13] FRIDLUND A J, SCHWARTZ G E, FOWLER S C. Pattern recognition of self-reported emotional state from multiple-site facial EMG activity during affective imagery[J]. Psychophysiology, 1984, 21(6): 622-637.
[14] KAMIBAYASHI L K, RICHMOND F J R. Morphometry of human neck muscles[J]. Spine, 1998, 23(12): 1314-1323.
[15] 陈谦. sEMG技术在颈部肌肉活动评价中的应用[J]. 北京体育大学学报, 2008, 31(2): 226-228.CHEN Qian. Surface electromyography utilized in neck muscle activity evaluation[J]. Journal of Beijing Sport University, 2008, 31(2): 226-228.
[16] 吴剑锋. 基于肌电信号的人体下肢运动信息获取技术研究[D]. 杭州: 浙江大学, 2008: 48-49.WU Jianfeng. Research on human lower-limb motion information acquisition technology based on EMG[D]. Hangzhou: Zhejiang University, 2008: 48-49.
[17] 杨钟亮. 基于主客观联合测评的动态人机接触面工效学研究[D]. 杭州:浙江大学, 2012: 68-70.YANG Zhongliang. Ergonomics study of dynamic human-product contact surface based on subjective and objective evaluation[D]. Hangzhou: Zhejiang University, 2012: 68-70.
[18] LEE Z J, SU S F, LEE C Y. Efficiently solving general weapon-target assignment problem by genetic algorithms with greedy eugenics[J]. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, 2003, 33(1): 113-121.
[19] 张海兵, 徐诚, 李世永. 贪心遗传算法及其在武器目标分配问题中的应用[J]. 弹道学报, 2007, 19(2): 40-43.ZHANG Haibing, XU Bing, LI Shiyong. GGA and its application to weapon target assignment[J]. Journal of Ballistics, 2007, 19(2): 40-43.
[20] 魏英姿, 赵明扬, 张凤, 等. 贪心遗传算法求解组合优化问题[J]. 机械科学与技术, 2005, 24(1): 10-13.WEI Yingzi, ZHAO Mingyang, ZHANG Feng, et al. An effcient greedy genetic algorithm for combination optimization problems[J]. Mechanical Science and Technology, 2005, 24(1): 10-13.
[21] 陈谦, 杨红春, 王健. 不同负荷水平颈部肌肉等长收缩的平均肌电变化特征[J]. 浙江体育科学, 2010, 32(5): 91-95.CHEN Qian, YANG Hongchun, WANG Jian. The changes of AEM G of Neck muscles under isometric contraction at different load levels[J] Zhejiang Sport Science, 2010, 32(5): 91-95.


更新日期/Last Update: 1900-01-01