Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)
计算机技术、电子通信技术     
采用多核相关向量机的人体步态识别
刘磊, 杨鹏, 刘作军
1.郑州轻工业学院 建筑环境工程学院,郑州 450002
2.河北工业大学 控制科学与工程学院,天津 300130
3.智能康复装置与检测技术教育部工程研究中心,天津 300130
Locomotion-Mode recognition using multiple kernel relevance vector machine
LIU Lei, YANG Peng, LIU Zuo-jun
1. School of Building Environmental Engineering, Zhengzhou College of Light Industry, Zhengzhou 450002, China;
2. School of Control Science and Engineering, Hebei University of Technology, Tianjin 300130, China;
3. Engineering Research Center of Intelligent Rehabilitation and Detecting Technology, Tianjin 300130, China
 全文: PDF(1582 KB)   HTML
摘要：

为进一步提升人体步态识别的准确率,参考人体步态特点,选择下肢表面肌电信号(SEMG)、髋关节角度、膝关节角度作为步态识别信息源,提出一种基于多核相关向量机（MKRVM）的人体步态识别方法.该方法以多源信息特征值作为多核相关向量机的输入,通过实验对不同信号选取合适的核函数,利用萤火虫优化（GSO）算法确定核函数参数,输出为不同步态的概率.利用训练好的模型直接对新样本进行分类,将概率最高的步态模式作为识别结果.实验结果表明,该方法对于平地行走、上楼、下楼、上坡、下坡等步态的平均识别率为94.64%,优于单核支持向量机（SVM）等方法.
Abstract:
A Locomotion-Mode recognition method based on multiple kernel relevance vector machine (MKRVM) was proposed to improve recognition accuracy, which selected the surface electromyography (SEMG), hip joint angle and knee joint angle as the major information source of recognition according to the user’s locomotion modes characteristics. SEMG features and joint angle features were fused into a feature vector as the input of multiple kernel relevance vector machine learning model, and different kernel functions were chosen for each signal through experiment. Glowworm swarm optimization algorithm was used to optimize kernel function parameters. The output was the probability of each locomotion mode for this sample. New sample can be classified using the trained model, and the recognition result is the mode with the highest probability. Experiment results show that the average recognition accuracy of locomotion-modes, including level-ground walking, stairs ascent, stairs descent, upslope and downgrade, is 94.64%, which is superior to SVM method using single kernel function.
出版日期: 2017-03-01
CLC:  TP 391  
基金资助:

国家自然科学基金资助项目（61174009，61203323）；天津市自然科学基金项目资助项目（13JCQNJC03400）；2016年度河南省高等学校重点科研项目（16B413006）
通讯作者: 杨鹏，男，教授. ORCID: 0000-0003-3006-2184.     E-mail: kongzhi_xueke@163.com
作者简介: 刘磊(1984—),男，讲师，从事智能假肢、模式识别科研工作.ORCID:0000-0001-5720-4424. E-mail:liulei20060000@126.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　

引用本文:

刘磊, 杨鹏, 刘作军. 采用多核相关向量机的人体步态识别[J]. 浙江大学学报(工学版), 10.3785/j.issn.1008-973X.2017.03.018.

LIU Lei, YANG Peng, LIU Zuo-jun. Locomotion-Mode recognition using multiple kernel relevance vector machine. JOURNAL OF ZHEJIANG UNIVERSITY (ENGINEERING SCIENCE), 10.3785/j.issn.1008-973X.2017.03.018.

［1］ DATTA D, HOWITT J. Conventional versus microchip controlled pneumatic swing phase control for tranfemoral amputees: user’s verdict ［J］. Prosthesis and Orthotics International, 1998, 22(2): 129-135.
［2］ SUP F, BOHARA A, GOLDFARB M. Design and control of a powered transfemoral prosthesis ［J］. International Journal of Robotics Research, 2008, 27(2): 263-273.
［3］ HITT J, SUGAR T, HOLGATE M, et al. Robotic transtibial prosthesis with biomechanical energy regeneration ［J］. Industrial Robot, 2013,36(5): 441-447.
［4］ KAHLE J T, HIGHSMITH M J, HUBBARD S L. Comparison of non-microprocessor knee mechanism versus CLeg on prosthesis evaluation questionnaire, stumbles, falls, walking tests, stair descent, and knee preference ［J］. Journal of Rehabilitation Research and Development, 2008, 45(1): 1-14.
［5］ DINGWELL J B, DAVIS B L, FRAZIER D M. Use of an instrumented treadmill for real-time gait symmetryevaluation and feedback in normal and transtibial amputee subjects ［J］. Prosthetics and Orthotics International, 1996, 20(2): 101-110.
［6］ 谭冠政,吴立明.国内外人工腿（假肢）研究的进展及发展趋势 ［J］.机器人,2001,23(1)：91-96.
TAN Guan-zheng, WU Li-ming. Progress and development trend towards study of artificial legs (prostheses) in foreign countries and China ［J］. Robot, 2001,23(1): 91-96.
［7］ 喻洪流,钱省三,沈凌,等.基于小脑模型神经网络控制的步速跟随智能膝上假肢 ［J］.中国组织工程研究与临床康复,2007,11(31)： 6233-6235.
YU Hong-liu, QIAN Sheng-san, SHEN ling, et al. Intelligent above-knee prosthesis following healthy leg gait with cerebellar model articulation controller ［J］. Journal of Clinical Rehabilitative Tissue Engineering Research, 2007, 11(31): 6233-6235.
［8］ 王人成.我国假肢技术的研究与进展 ［J］.中国康复医学杂志,2012, 27(11): 1058-1060.
WANG Ren-cheng. The prosthetic technology research and development of our country ［J］. Chinese Journal of Rehabilitation Medicine, 2012, 27(11): 1058-1060.
［9］ 高云园,孟明,罗志增,等.利用多源运动信息的下肢假肢多模式多步态识别研究 ［J］.传感器技术学报.2011, 24(11): 1574-1578.
GAO Yun-yuan, MENG Ming, LUO Zhi-zeng, et al. Multi-Mode and gait phase recognition of lower limb prosthesis based on multi-source motion information ［J］. Chinese Journal of Sensors and Actuators, 2011,24(11): 1574-1578.
［10］ ZHANG F, LIU M, HUANG H. Effects of locomotion mode recognition errors on volitional control of powered above-knee prostheses ［J］. IEEE Transaction on Neural Systems and Rehabilitation Engineering, 2015,23(1): 64-72.
［11］ YOUNG A J, SIMON A M, HARGROVE L J. A training method for locomotion mode prediction using powered lower limb prostheses ［J］. IEEE Transaction on Neural Systems and Rehabilitation Engineering, 2014, 22(3): 671-677.
［12］ 佟丽娜,侯增广,彭亮.基于多路sEMG时序分析的人体运动模式识别方法［J］.自动化学报,2014,40(5): 810-820.
TONG Li-na, HOU Zeng-guang, PENG Liang. Multi-channel sEMG time series analysis based human motion recognition method ［J］. Acta Automatic Sinica, 2014,40(5): 810-820.
［13］ 马玉良,马云鹏,张启忠,等.GABP神经网络在下肢运动步态识别中的应用研究［J］.传感技术学报,2013,26(9): 1183-1188.
MA Yu-liang, MA Yun-peng, ZHANG Qi-zhong, et al. Gait phase recognition of lower limb based on GA optimized BP neural network ［J］. Chinese Journal of Sensors And Actuators. 2013, 26(9): 1183-1188.
［14］ 刘磊,杨鹏,刘作军.基于多源信息和广义回归神经网络的下肢运动模式识别［J］.机器人,2015,37(3):310-317.
LIU Lei, YANG Peng, LIU Zuo-jun. Lower limblocomotion modes recognition based on multiple-source information and general regression neural network ［J］. Robot. 2015, 37(3): 310-317.
［15］ 袁娜,杨鹏,刘作军.利用平均影响值和概率神经网络的步态识别［J］.哈尔滨工程大学学报,2015,36(2):1-5.
YUAN Na, YANG Peng, LIU Zuo-jun. Gait recognition based on the mean impact value and probability neural network ［J］. Journal of Harbin Engineering University. 2015, 36(2): 1-5.
［16］ 齐美彬,王倩,蒋建国.非规范视角步态识别研究［J］.仪器仪表学报,2008,29(10):2058-2061.
QI Meibin, WANG Qian, JIANG Jianguo. Research on nonstandard view gait identification ［J］. Chinese Journal of Scientific Instrument, 2008, 29 (10):2058-2061.
［17］ 佘青山,高云园,孟明.下肢EMG的小波支持向量机多类识别方法［J］.华中科技大学学报: 自然科学版,2010,38(10)：7579.
SHE Qing-shan, GAO Yun-yuan, MENG Ming. Multiclass recognition of lower limb EMG using wavelet SVM ［J］. Journal of Huazhong University of Science and Technology: Natural Science Edition. 2010,38(10)：75-79.
［18］ TIPPING M E. Sparse bayesian learning and the relevance vector machine ［J］. Journal of Machine Learning Research, 2001,1(3): 211-244.
［19］ LI W X, LIAN L M. Multiple faces tracking based on relevance vector machine ［J］. Journal of Software, 2012, 7(4): 810-813.
［20］ 汪洪桥,孙富春,蔡艳宁,等.多核学习方法［J］.自动化学报,2010,36(8): 1037-1049.
WANG Hong-qiao, SUN Fu-chun, CAI Yan-ning, et al. On multiple kernel learning methods ［J］.Acta Automatica Sinica. 2010, 36(8): 1037-1049.
［21］ 张凯军,梁循.一种改进的显性多核支持向量机［J］.自动化学报,2014,40(10): 2288-2294.
ZHANG Kai-jun, LIANG Dun. An improved domain multiple kernel support vector machine ［J］. Acta Automatica Sinica. 2014, 40(10): 2288-2294.
［22］ PSORAKIS I, DAMOULAS T, GIROLAMI M A. Multiclass relevance vector machines: sparsity and accuracy ［J］. IEEE Transactions on Neural Networks, 2010, 21(10): 1588-1598.
［23］ DAMOULAS T, GIROLAMI M A. Combining feature spaces for classification ［J］. Pattern Recognition, 2009, 42(11): 2671-2683.
［24］ HUANG H, ZHANG F, HARGROVE L J, et al.Continuous locomotionmode identification for prosthetic legs based on neuromuscularmechanical fusion ［J］. IEEE Transactions on Biomedical Engineering, 2011, 58(10): 2867-2875.
［25］ 陈玲玲.肌电信号的运动模式识别及其在膝上假肢中的应用研究［D］.天津：河北工业大学,2010: 56.
CHEN Ling-ling. Motion pattern recogniton based on emg and its application research on ak prosthesis ［D］. Tianjin: Hebei University of Technology. 2010: 56.
［26］ 丁其川,熊安斌,赵新刚,等.基于表面肌电的运动意图识别方法研究及应用综述［J］.自动化学报,2016,42(1): 13-25.
DING Qi-chuan, XIONG An-bin, ZHAO Xin-gang, et al. A review on researches and applications of sEMG-based motion intent recognition methods ［J］. Acta Automatica Sinica, 2016, 42(1): 13-25.
［27］ 何涛,胡洁,夏鹏,等.基于ReliefF算法与遗传算法的肌电信号特征选择［J］.上海交通大学学报, 2016,50(2)： 204-208.
HE Tao, ZOU Hu-Jie, XIA Peng, et al. Feature selection of EMG signal based on relieff algorithm andgenetic algorithm ［J］. Journal of Shanghai JiaotongUniversity, 2016, 50(2): 204-208.
［28］ 龙文,蔡绍洪,焦建军,等.求解约束优化问题的萤火虫算法及其工程应用［J］.中南大学学报：自然科学版,2015,46(4): 1260-1267.
LONG Wen, CAI Shao-hong, JIAO Jian-jun, et al. Firefly algorithm for solving constrained optimization problems and engineering applications ［J］. Journal of Central South University: Science and Technology, 2015, 46(4): 1260-1267.
［29］ 王雪刚,邹早建.基于果蝇优化算法的支持向量机参数优化在船舶操纵预报中的应用［J］.上海交通大学学报,2013,47(6): 884-888.
WANG Xue-gang, ZOU Zao-jian. FOA-based SVM parameter optimization and its application in ship manoeuvring prediction ［J］. Journal of Shanghai Jiaotong University, 2013, 47(6): 884-888.
[1] 郑守国,张勇德,谢文添,樊虎,王青. 基于数字孪生的飞机总装生产线建模[J]. 浙江大学学报(工学版), 2021, 55(5): 843-854.
[2] 张师林,马思明,顾子谦. 基于大边距度量学习的车辆再识别方法[J]. 浙江大学学报(工学版), 2021, 55(5): 948-956.
[3] 宋鹏,杨德东,李畅,郭畅. 整体特征通道识别的自适应孪生网络跟踪算法[J]. 浙江大学学报(工学版), 2021, 55(5): 966-975.
[4] 蔡君,赵罡,于勇,鲍强伟,戴晟. 基于点云和设计模型的仿真模型快速重构方法[J]. 浙江大学学报(工学版), 2021, 55(5): 905-916.
[5] 王虹力,郭斌,刘思聪,刘佳琪,仵允港,於志文. 边端融合的终端情境自适应深度感知模型[J]. 浙江大学学报(工学版), 2021, 55(4): 626-638.
[6] 张腾,蒋鑫龙,陈益强,陈前,米涛免,陈彪. 基于腕部姿态的帕金森病用药后开-关期检测[J]. 浙江大学学报(工学版), 2021, 55(4): 639-647.
[7] 郑英杰,吴松荣,韦若禹,涂振威,廖进,刘东. 基于目标图像FCM算法的地铁定位点匹配及误报排除方法[J]. 浙江大学学报(工学版), 2021, 55(3): 586-593.
[8] 雍子叶,郭继昌,李重仪. 融入注意力机制的弱监督水下图像增强算法[J]. 浙江大学学报(工学版), 2021, 55(3): 555-562.
[9] 于勇,薛静远,戴晟,鲍强伟,赵罡. 机加零件质量预测与工艺参数优化方法[J]. 浙江大学学报(工学版), 2021, 55(3): 441-447.
[10] 胡惠雅,盖绍彦,达飞鹏. 基于生成对抗网络的偏转人脸转正[J]. 浙江大学学报(工学版), 2021, 55(1): 116-123.
[11] 陈杨波,伊国栋,张树有. 基于点云特征对比的曲面翘曲变形检测方法[J]. 浙江大学学报(工学版), 2021, 55(1): 81-88.
[12] 段有康,陈小刚,桂剑,马斌,李顺芬,宋志棠. 基于相位划分的下肢连续运动预测[J]. 浙江大学学报(工学版), 2021, 55(1): 89-95.
[13] 张太恒,梅标,乔磊,杨浩杰,朱伟东. 纹理边界引导的复合材料圆孔检测方法[J]. 浙江大学学报(工学版), 2020, 54(12): 2294-2300.
[14] 梁栋,刘昕宇,潘家兴,孙涵,周文俊,金子俊一. 动态背景下基于自更新像素共现的前景分割[J]. 浙江大学学报(工学版), 2020, 54(12): 2405-2413.
[15] 晋耀,张为. 采用Anchor-Free网络结构的实时火灾检测算法[J]. 浙江大学学报(工学版), 2020, 54(12): 2430-2436.