Body Area Networks: Smart IoT and Big Data for Intelligent Health Management. 14th EAI International Conference, BODYNETS 2019, Florence, Italy, October 2-3, 2019, Proceedings

Research Article

Motion Recognition for Smart Sports Based on Wearable Inertial Sensors

  • @INPROCEEDINGS{10.1007/978-3-030-34833-5_10,
        author={Huihui Wang and Lianfu Li and Hao Chen and Yi Li and Sen Qiu and Raffaele Gravina},
        title={Motion Recognition for Smart Sports Based on Wearable Inertial Sensors},
        proceedings={Body Area Networks:  Smart IoT and Big Data for Intelligent Health Management. 14th EAI International Conference, BODYNETS 2019, Florence, Italy, October 2-3, 2019, Proceedings},
        proceedings_a={BODYNETS},
        year={2019},
        month={11},
        keywords={Body sensor network Information fusion Motion recognition Wearable computing Micro-electro-mechanical sensor},
        doi={10.1007/978-3-030-34833-5_10}
    }
    
  • Huihui Wang
    Lianfu Li
    Hao Chen
    Yi Li
    Sen Qiu
    Raffaele Gravina
    Year: 2019
    Motion Recognition for Smart Sports Based on Wearable Inertial Sensors
    BODYNETS
    Springer
    DOI: 10.1007/978-3-030-34833-5_10
Huihui Wang1,*, Lianfu Li1,*, Hao Chen1,*, Yi Li1, Sen Qiu2, Raffaele Gravina3
  • 1: Dalian Neusoft University of Information
  • 2: Dalian University of Technology
  • 3: University of Calabria
*Contact email: wanghuihui@neusoft.edu.cn, lilianfu@neusoft.edu.cn, chenhao@neusoft.edu.cn

Abstract

With the development of wearable technology and inertial sensor technology, the application of wearable sensors in the field of sports is becoming more extensive. The notion of Body Sensor Network (BSN) brings unique human-computer interaction mode and gives users a brand new experience. In terms of smart sports, BSN can be applied to table tennis training by detecting individual stroke motion and recognizing different technical movements, which provide a training evaluation for the players to improve their sport skills. A portable six-degree-of-freedom inertial sensor system was adopted to collect data in this research. After data pre-processing, triaxial angular velocity and triaxial acceleration data were used for table tennis stroke motion recognition. The classification and recognition of stroke action were achieved based on Support Vector Machine (SVM) algorithm after Principal Component Analysis (PCA) dimension reduction, and the recognition rate of five typical strokes can reach up to using the trained classification model. It can be assumed that BSN has practical significance and broad application prospects.