Recognition of sports exercises using inertial sensor technology

• Autorzy: Krutz Pascal , Rehm Matthias , Schlegel Holger , Dix Martin

Identyfikatory

DOI

10.35784/acs-2023-10

• Języki publikacji: EN

Abstrakty

EN

Supervised learning as a sub-discipline of machine learning enables the recognition of correlations between input variables (features) and associated outputs (classes) and the application of these to previously unknown data sets. In addition to typical areas of application such as speech and image recognition, fields of applications are also being developed in the sports and fitness sector. The purpose of this work is to implement a workflow for the automated recognition of sports exercises in the Matlab® programming environment and to carry out a comparison of different model structures. First, the acquisition of the sensor signals provided in the local network and their processing is implemented. Realised functionalities include the interpolation of lossy time series, the labelling of the activity intervals performed and, in part, the generation of sliding windows with statistical parameters. The preprocessed data are used for the training of classifiers and artificial neural networks (ANN). These are iteratively optimised in their corresponding hyper parameters for the data structure to be learned. The most reliable models are finally trained with an increased data set, validated and compared with regard to the achieved performance. In addition to the usual evaluation metrics such as F1 score and accuracy, the temporal behaviour of the assignments is also displayed graphically, allowing statements to be made about potential causes of incorrect assignments. In this context, especially the transition areas between the classes are detected as erroneous assignments as well as exercises with insufficient or clearly deviating execution. The best overall accuracy achieved with ANN and the increased dataset was 93.7 %.

Słowa kluczowe

EN

human activity recognition; machine learning; neural networks; classifier

• Wydawca: Polskie Towarzystwo Promocji Wiedzy ; Lublin University of Technology
• Czasopismo: Applied Computer Science
• Rocznik: 2023
• Tom: Vol. 19, no 1
• Strony: 152--163
• Opis fizyczny: Bibliogr. 12 poz., fig., tab.

Twórcy

autor

Krutz Pascal

• Professorship for Production Systems and Processes, Chemnitz University of Technology, Chemnitz, Germany

autor

Rehm Matthias

• Professorship for Production Systems and Processes, Chemnitz University of Technology, Chemnitz, Germany

autor

Schlegel Holger

• Professorship for Production Systems and Processes, Chemnitz University of Technology, Chemnitz, Germany

autor

Dix Martin

• Professorship for Production Systems and Processes, Chemnitz University of Technology, Chemnitz, Germany
• Fraunhofer Institute for Machine Tools and Forming Technology IWU, Chemnitz, Germany

Bibliografia

• [1] Brühl, V. (2019). Künstliche Intelligenz, Maschinelles Lernen und Big Data—Grundlagen, Marktpotenziale und wirtschaftspolitische Relevanz. WiSt - Wirtschaftswissenschaftliches Studium, 48(11), 34–41. https://doi.org/10.15358/0340-1650-2019-11-34
• [2] Chakraborty, A., & Mukherjee, N. (2022). A deep-CNN based low-cost, multi-modal sensing system for efficient walking activity identification. Multimedia Tools and Applications. https://doi.org/10.1007/s11042-022-13990-x
• [3] Helten, T. (2013). Processing and tracking human motions using optical, inertial, and depth sensors. Universität des Saarlandes. https://publikationen.sulb.uni-saarland.de/handle/20.500.11880/26607
• [4] Hussain, A., Zafar, K., Baig, A. R., Almakki, R., AlSuwaidan, L., & Khan, S. (2022). Sensor-Based Gym Physical Exercise Recognition: Data Acquisition and Experiments. Sensors, 22(7), 2489. https://doi.org/10.3390/s22072489
• [5] Javed, A. R., Sarwar, M. U., Khan, S., Iwendi, C., Mittal, M., & Kumar, N. (2020). Analyzing the Effectiveness and Contribution of Each Axis of Tri-Axial Accelerometer Sensor for Accurate Activity Recognition. Sensors, 20(8), 2216. https://doi.org/10.3390/s20082216
• [6] Kautz, T. (2017). Acquisition, Filtering and Analysis of Positional and Inertial Data in Sports. FAU University Press. https://doi.org/10.25593/978-3-96147-065-5
• [7] Polo-Rodriguez, A., Montoro-Lendinez, A., Espinilla, M., & Medina-Quero, J. (2022). Classifying Sport-Related Human Activity from Thermal Vision Sensors Using CNN and LSTM. In P. L. Mazzeo, E. Frontoni, S. Sclaroff, & C. Distante (Eds.), Image Analysis and Processing. ICIAP 2022 Workshops (pp. 38–48). Springer International Publishing. https://doi.org/10.1007/978-3-031-13321-3_4
• [8] Schuldhaus, D. (2019). Human Activity Recognition in Daily Life and Sports Using Inertial Sensors. FAU University Press. https://doi.org/10.25593/978-3-96147-226-0
• [9] Sequence-to-Sequence Classification Using Deep Learning (n.d.). Mathworks. Retrieved February 21, 2023, from https://de.mathworks.com/help/deeplearning/ug/sequence-to-sequence-classification-using-deep-learning.html
• [10] Soro, A., Brunner, G., Tanner, S., & Wattenhofer, R. (2019). Recognition and Repetition Counting for Complex Physical Exercises with Deep Learning. Sensors, 19(3), 714. https://doi.org/10.3390/s19030714
• [11] Steels, T., Van Herbruggen, B., Fontaine, J., De Pessemier, T., Plets, D., & De Poorter, E. (2020). Badminton Activity Recognition Using Accelerometer Data. Sensors, 20(17), 4685. https://doi.org/10.3390/s20174685
• [12] Train Network with Numeric Features (n.d.). Mathworks. Retrieved February 21, 2023, from https://de.mathworks.com/help/deeplearning/ug/train-network-on-data-set-of-numeric-features.html