Design of ping-pong recognition based on S_Kohonen neural network

被引：0
|
作者：
Li B. [1 ]
Jin P. [1 ]
Wu Z. [1 ]
机构：
[1] School of Electronic and Information Engineering, South China University of Technology, Guangzhou
来源：
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2020年 / 48卷 / 03期
关键词：
Micro-electro-mechanical system sensor; Smart ping-pong bracelet; S_Kohonen neural network; Wavelet transform;
D O I：
10.13245/j.hust.200310
中图分类号：
学科分类号：
摘要：
In order to solve the problem of no real-time recognition, low recognition rate and poor endurance of wearable devices caused by high complexity of recognition algorithms in ping-pong recognition method, a real-time recognition method was proposed for ping-pong based on S_Kohonen(supervised Kohonen) neural network optimized by genetic algorithm, and the system design was completed. The single MPU6050 six-axis acceleration sensor was used to collect motion signal, and the start and end of the action was extracted by the endpoint detection algorithm. The motion signal was decomposed into three layers based on db4 wavelet, and the six common ping-pong motions was recognized by the S_Kohonen neural network optimized by algorithm optimization. The experiment result shows that the average offline recognition rate is 99.17%, the average real-time recognition rate is 91.67%, the standby power consumption is 0.28 mW, the power consumption of the operation mode is 14 mW and the recognition time is 2 ms. It proves that the method recognizes fast, and has low power consumption and high accuracy. © 2020, Editorial Board of Journal of Huazhong University of Science and Technology. All right reserved.
引用
收藏
页码：52 / 56
页数：4
相关论文
共 9 条
  • [1] Mitchell E., Monaghan D., Connor O.N., Classification of sporting activities using smartphone accelerometers, Sensors, 13, 4, pp. 5317-5337, (2013)
  • [2] Liu K., Yen C., Chang L., Et al., Wearable sensor-based activity recognition for housekeeping task, Proc of IEEE International Conference on Wearable & Implantable Body Sensor Networks, pp. 67-70, (2017)
  • [3] Yang W., Wang C., Chen C., Et al., Motion-pattern recognition system using a wavelet-neural network, IEEE Transactions on Consumer Electronics, 65, 2, pp. 170-178, (2019)
  • [4] Sadkhan S.B., Jawad S.F., Handwritten recognition based on hybrid ann and wavelet transformation, Proc of 2018 Al-Mansour International Conference on New Trends in Computing, Communication, and Information Technology (NTCCIT), pp. 76-80, (2018)
  • [5] Tang P., Fang H., Si H., Maximal relevance feature selection for human activity recognition in smart home, Proc of 2018 Chinese Control and Decision Conference (CCDC), pp. 4264-4268, (2018)
  • [6] Xu H., Huang Z., Wang J., Et al., Study on fast human activity recognition based on optimized feature selection, Proc of 2017 16th International Symposium on Distributed Computing and Applications to Business, Engineering and Science (DCABES), pp. 109-112, (2017)
  • [7] Holland J.H., Adaptation in Natural and Artificial System, (1992)
  • [8] Melssen W.J., Wehrens R., Buydens L.M., Et al., Supervised Kohonen networks for classification problems, Chemometrics and Intelligent Laboratory Systems, 83, 2, pp. 99-113, (2006)
  • [9] Li Z., Antao T., Yang L., Et al., Hand gesture recognition of sEMG based on modified Kohonen network, Proc of International Conference on Electronics Communications and Control, pp. 1476-1479, (2011)
1