Human Activity Recognition Based on Acceleration Signal and Evolutionary RBF Neural Network
LU Xian-Ling, WANG Hong-Bin, XU Xian
Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education,Jiangnan University, Wuxi 214122 School of Internet of Things Engineering, Jiangnan University, Wuxi 214122
Abstract To obtain a satisfactory recognition rate,a radial basis function(RBF) neural network classifier trained by the hierarchy genetic algorithm (HGA) is utilized to classify human body activities using the acceleration signal. By exploring the interquartile range, a fitness function is proposed to enhance the crossover of the parameter genes in HGA and determine the distance between the offspring and the boundary of coding space automatically. Thus, the empirical setting in the previous algorithms is avoided. With the arithmetic crossover, the offspring with high fitness is chosen. By comparing fitness values between the uniform mutation offspring and the non-uniform mutation offspring, the structure and parameters of RBF network are jointly optimized. The experimental results on actual subject testing data indicate that the radial basis function neural network classifier trained by the proposed method produces smaller errors than those trained by the traditional HGA. A higher recognition rate of testing data is obtained.
LU Xian-Ling,WANG Hong-Bin,XU Xian. Human Activity Recognition Based on Acceleration Signal and Evolutionary RBF Neural Network[J]. , 2015, 28(12): 1127-1136.
[1] Aggarwal J K, Xia L. Human Activity Recognition from 3D Data: A Review. Pattern Recognition Letters, 2014, 48: 70-80 [2] Siddiqi M H, Ali R, Rana M S, et al. Video-Based Human Activity Recognition Using Multilevel Wavelet Decomposition and Stepwise Linear Discriminant Analysis. Sensors, 2014, 14(4): 6370-6392 [3] Wang L M, Qiao Y, Tang X O. Latent Hierarchical Model of Temporal Structure for Complex Activity Classification. IEEE Trans on Image Processing, 2013, 23(2): 810-822 [4] Mimura K, Kishino H, Karino G, et al. Potential of a Smartphone as a Stress-Free Sensor of Daily Human Behavior. Behavioural Brain Research, 2015, 276: 181-189 [5] Trost S G, Zheng Y L, Wong W K. Machine Learning for Activity Recognition: Hip versus Wrist Data. Physiological Measurement, 2014, 35(11): 2183-2189 [6] Ghasemzadeh H, Jafari R. Physical Movement Monitoring Using Body Sensor Networks: A Phonological Approach to Construct Spatial Decision Tress. IEEE Trans on Industrial Informatics, 2010, 7(1): 66-77 [7] Dai K, Yu H Y, Li Q. A Multi-class Feature Selection Algorithm Based on Support Vector Machine. Pattern Recognition and Artificial Intelligence, 2014, 27(5): 463-471 (in Chinese) (代 琨,于宏毅,李 青.一种基于支持向量机的特征选择算法.模式识别与人工智能, 2014, 27(5): 463-471) [8] Ruch N, Joss F, Jimmy G, et al. Neural Network versus Activity-Specific Prediction Equations for Energy Expenditure Estimation in Children. Journal of Applied Physiology, 2013, 115(9): 1229-1236 [9] Yao D L, Chen H W, Yin J P. Multi-chain ANN-HMM Recognition Model and Its Application. Pattern Recognition and Artificial Intelligence, 2000, 13(1): 1-6 (in Chinese) (姚丹霖,陈火旺,殷建平.多链ANN-HMM识别模型及其应用.模式识别与人工智能, 2000, 13(1): 1-6) [10] Gyorbíró N, Fbin , Hományi G. An Activity Recognition System for Mobile Phones. Mobile Networks and Applications, 2009, 14(1): 82-91 [11] Khan A M, Lee Y K, Lee S Y, et al. A Triaxial Accelerometer-Based Physical-Activity Recognition via Augmented-Signal Features and a Hierarchical Recognizer. IEEE Trans on Information Technology in Biomedicine, 2010, 14(5): 1166-1172 [12] Chen J, Kuo Y H, Li J D, et al. Neural Network Application in Automatic Recognition of Communication Signals // Proc of the 5th International Conference on Computational Intelligence and Multimedia Applications. Xi′an, China, 2003: 457-462 [13] Ghosh D K, Ari S. A Static Hand Gesture Recognition Algorithm Using K-mean Based Radial Basis Function Neural Network // Proc of the 8th International Conference on Information, Communications and Signal Processing. Singapore, Singapore, 2011. DOI: 10.1109/ICICS.2011.6174264 [14] Su S, Duan X Z, Chan W L, et al. Erroneous Measurement Detection in Substation Automation System Using OLS Based RBF Neural Network. International Journal of Electrical Power & Energy Systems, 2009, 31(7/8): 351-355 [15] Khazaee A. Automated Cardiac Beat Classification Using RBF Neural Networks. International Journal of Modern Education and Computer Science, 2013, 5(3): 42-48 [16] Xing Z Y, Zhang Y, Qin Y, et al. A Hierarchical Genetic Algorithm Based RBF Neural Network Approach for Modelling of Electrohydraulic System // Proc of the ICROS-SICE International Joint Conference. Fukuoka, Japan, 2009: 1018-1022 [17] Xing Z Y, Pang X M, Ji H Y, et al. Hierarchical Genetic Algorithm Based RBF Neural Networks and Application for Modelling of the Automatic Depth Control Electrohydraulic System. International Journal of Control, Automation, and Systems, 2011, 9(4): 759-767 [18] Yang J, Wang S Q, Chen N J, et al. Wearable Accelerometer Based Extendable Activity Recognition System // Proc of the IEEE International Conference on Robotics and Automation. Anchorage, USA, 2010: 3641-3647 [19] Xue Y, Jin L W. Discrimination between Upstairs and Downstairs Based on Accelerometer. IEICE Trans on Information and Systems, 2011, 94-D(6): 1173-1177 [20] Han J W, Kamber M. Data Mining: Concepts and Techniques. San Francisco, USA: Morgan Kaufmann Publishers, 2011 [21] Leung F H F, Lam H K, Ling S H. Tuning of the Structure and Parameters of a Neural Network Using an Improved Genetic Algorithm. IEEE Trans on Neural Networks, 2003, 14(1): 79-88 [22] Ding S F, Xu L, Su C Y, et al. An Optimizing Method of RBF Neural Network Based on Genetic Algorithm. Neural Computing and Applications, 2012, 21(2): 333-336
2015, Vol. 28 
