RECOGNITION OF SPORTS EXERCISES USING INERTIAL SENSOR TECHNOLOGY
Pascal Krutz
pascal.krutz@mb.tu-chemnitz.deChemnitz University of Technology (Germany)
https://orcid.org/0009-0002-1962-983X
Matthias Rehm
Chemnitz University of Technology (Germany)
https://orcid.org/0000-0001-7354-3856
Holger Schlegel
Chemnitz University of Technology (Germany)
Martin Dix
Chemnitz University of Technology, Fraunhofer IWU (Germany)
https://orcid.org/0000-0002-2344-1656
Abstract
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 was 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 were implemented. The functionalities to be realised included 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 were used for the training of classifiers and artificial neural networks (ANN). These were iteratively optimised in their corresponding hyper parameters for the data structure to be learned. The most reliable models were 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 was also displayed graphically, which enabled statements to be made about potential causes for incorrect assignments. In this context, especially the transition areas between the classes were 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 %.
Supporting Agencies
Keywords:
machine learning, neural networks, classifier, human activity recognitionReferences
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
DOI: https://doi.org/10.15358/0340-1650-2019-11-34
Google Scholar
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
DOI: https://doi.org/10.1007/s11042-022-13990-x
Google Scholar
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
Google Scholar
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
DOI: https://doi.org/10.3390/s22072489
Google Scholar
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
DOI: https://doi.org/10.3390/s20082216
Google Scholar
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
Google Scholar
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
DOI: https://doi.org/10.1007/978-3-031-13321-3_4
Google Scholar
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
Google Scholar
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-deeplearning.html
Google Scholar
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
DOI: https://doi.org/10.3390/s19030714
Google Scholar
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
DOI: https://doi.org/10.3390/s20174685
Google Scholar
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
Google Scholar
Authors
Pascal Krutzpascal.krutz@mb.tu-chemnitz.de
Chemnitz University of Technology Germany
https://orcid.org/0009-0002-1962-983X
Authors
Matthias RehmChemnitz University of Technology Germany
https://orcid.org/0000-0001-7354-3856
Authors
Holger SchlegelChemnitz University of Technology Germany
Authors
Martin DixChemnitz University of Technology, Fraunhofer IWU Germany
https://orcid.org/0000-0002-2344-1656
Statistics
Abstract views: 255PDF downloads: 126
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in Applied Computer Science are open-access and distributed under the terms of the Creative Commons Attribution 4.0 International License.
Similar Articles
- Monika KULISZ, Justyna KUJAWSKA, Zulfiya AUBAKIROVA, Gulnaz ZHAIRBAEVA, Tomasz WAROWNY, PREDICTION OF THE COMPRESSIVE STRENGTH OF ENVIRONMENTALLY FRIENDLY CONCRETE USING ARTIFICIAL NEURAL NETWORK , Applied Computer Science: Vol. 18 No. 4 (2022)
- Rowell HERNANDEZ, Robert ATIENZA, CAREER TRACK PREDICTION USING DEEP LEARNING MODEL BASED ON DISCRETE SERIES OF QUANTITATIVE CLASSIFICATION , Applied Computer Science: Vol. 17 No. 4 (2021)
- Mouna TARIK, Ayoub MNIAI, Khalid JEBARI, HYBRID FEATURE SELECTION AND SUPPORT VECTOR MACHINE FRAMEWORK FOR PREDICTING MAINTENANCE FAILURES , Applied Computer Science: Vol. 19 No. 2 (2023)
- Saheed A. ADEWUYI, Segun AINA, Adeniran I. OLUWARANTI, A DEEP LEARNING MODEL FOR ELECTRICITY DEMAND FORECASTING BASED ON A TROPICAL DATA , Applied Computer Science: Vol. 16 No. 1 (2020)
- Wafaa Mustafa HAMEED, Asan Baker KANBAR, USING GA FOR EVOLVING WEIGHTS IN NEURAL NETWORKS , Applied Computer Science: Vol. 15 No. 3 (2019)
- Olufemi Folorunso, Olufemi Akinyede, Kehinde Agbele, ARDP: SIMPLIFIED MACHINE LEARNING PREDICTOR FOR MISSING UNIDIMENSIONAL ACADEMIC RESULTS DATASET , Applied Computer Science: Vol. 19 No. 1 (2023)
- Dias Satria, PREDICTING BANKING STOCK PRICES USING RNN, LSTM, AND GRU APPROACH , Applied Computer Science: Vol. 19 No. 1 (2023)
- Wulan Dewi, Wiranto Herry Utomo, PLANT CLASSIFICATION BASED ON LEAF EDGES AND LEAF MORPHOLOGICAL VEINS USING WAVELET CONVOLUTIONAL NEURAL NETWORK , Applied Computer Science: Vol. 17 No. 1 (2021)
- Mohanad ABDULHAMID, Njagi KINYUA, SOFTWARE FOR RECOGNITION OF CAR NUMBER PLATE , Applied Computer Science: Vol. 16 No. 1 (2020)
- Zahid Zamir, CAN THE SYSTEM, INFORMATION, AND SERVICE QUALITIES IMPACT EMPLOYEE LEARNING, ADAPTABILITY, AND JOB SATISFACTION? , Applied Computer Science: Vol. 19 No. 1 (2023)
<< < 1 2 3 4 5 6 7 8 9 10 > >>
You may also start an advanced similarity search for this article.
