摘要
为提高人体下肢步态相位识别准确率以实现外骨骼机器人控制,采用一种改进的粒子群优化MPSO-BP神经网络方法识别不同运动模式下的人体步态相位。通过自适应调整学习因子构造MPSO-BP神经网络分类器,以多种传感信息组成的特征向量样本集训练神经网络分类器,用于识别人体下肢在平地行走、上楼梯和起坐三种典型运动模式下的步态相位。实验结果表明,MPSO-BP神经网络分类器能有效识别三种不同运动模式的步态相位,识别准确率均达到96%以上,识别性能优于传统的BP神经网络模型和粒子群优化神经网络模型。
To improve the accuracy rate of human gait phase recognition for controlling the exoskeleton robot, an approach based on Modified Particle Swarm Optimization algorithm-Back Propagation(MPSO-BP)neural network is utilized to divide three types of gait into different phases. Firstly, the MPSO-BP neural network classifier is constructed through regulating the learning factor adaptively, and then the classifier is trained using sample set containing multisensor information. Secondly, test the classifier on gait phase recognition in three types of human gait including walk,upstairs and sit-down. The experimental results show that the MPSO-BP neural network classifier can successfully increase the accuracy rate up to averaged 96% above, which is superior to the BP neural network and the particle swarm optimization BP neural network methods.
引文
[1]夏懿.基于足底压力分布的步行行为感知关键技术研究[D].合肥:中国科学技术大学,2013.
[2]薛召军,靳静娜,明东,等.步态识别研究现状与进展[J].生物医学工程学杂志,2008,25(5):1217-1221.
[3]沈金虎.基于全方向下肢康复训练机器人的步态检测与分析[D].沈阳:沈阳工业大学,2012.
[4]Kawamoto H,Sankai Y.Power assist method based on phase sequence and muscle force condition for HAL[J].Advanced Robotics,2005,19(7):717-734.
[5]Bae J,Kong K,Byl N,et al.A mobile gait monitoring system for gait analysis[C]//International Conference on Rehabilitation Robotics,USA,2009:73-79.
[6]Rossi S M M,Crea S,Donati M,et al.Gait segmentation using bipedal foot pressure patterns[C]//The Fourth IEEE RAS/EMBS International Conference on Biomedical Robotics and Biomechatronics,Roman,Italy,2012.
[7]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):1183-1187.
[8]刘磊,杨鹏,刘作军.基于多源信息和粒子群优化算法的下肢运动模式识别[J].浙江大学学报:工学版,2015,49(3):439-447.
[9]Khan S U,Yang S,Wang L,et al.A modified particle swarm optimization algorithm for global optimizations of inverse problems[J].IEEE Transactions on Magnetics,2016,52(3):1-4.
[10]刘渊,李群,王晓锋.基于攻击图和改进粒子群算法的网络防御策略[J].计算机工程与应用,2016,52(8):120-124.
[11]Ling S H,Iu H,Leung F H F,et al.Improved hybrid particle swarm optimized wavelet neural network for modeling the development of fluid dispensing for electronic packing[J].IEEE Transactions on Industrial Electronics,2008,55(9):3447-3460.
[12]雷瑞龙,侯立刚,曹江涛.基于多策略的多目标粒子群优化算法[J].计算机工程与应用,2016,52(8):19-24.
[13]Clerc M,Kennedy J.The particle swarm-explosion,stability,and convergence in a multidimensional complex space[J].IEEE Transactions on Evolutionary Computation,2002,6(1):58-73.
[14]郑成闻,宋全军,佟丽娜,等.一种柔性双足压力检测装置与步态分析系统设计研究[J].传感技术学报,2010,23(12):1704-1708.
[15]白大鹏,张立勋.助行机器人起坐机构运动分析及实验[J].机器人,2013,35(6):757-761.