Abstract
At large scale sport events such as various running competitions and triathlons, the determination of split and finish times of athletes is mostly done with the help of Radio Frequency Identification (RFID). This work focuses on Ultra High Frequency (UHF) RFID systems, which consist of RFID transponders and RFID readers with appropriate antennas along the track. Recent improvements in the UHF-RFID technology open up new possibilities for analyzing additional data on top of the timing data. By modifying the placements of transponders and antennas and analyzing additional signal properties using Machine Learning algorithms, this paper outlines a way to classify the athlete’s movements based on RFID detections from an individual sports timing system. Findings derived from experiments with a proposed antenna and transponder setup in a lab environment are presented. A comparison of the k-Nearest Neighbor approach and the Decision Tree approach shows that they both yield a movement style classification accuracy of approximately 70%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Smartrac DogBone, Impinj Monza R6 chip, 860–960 MHz, linear polarization.
- 2.
Two time synchronized Impinj Speedway Revolution R420 readers (custom firmware).
References
Andersons, A., Ritter, S.: Advanced RFID applications for sports events management: the case of sportident in Latvia. Procedia Comput. Sci. 43, 78–85 (2015)
Annasaheb, A.B., Verma, V.K.: Data mining classification techniques: a recent survey. Int. J. Emerg. Technol. Eng. Res. (IJETER) 4, 51–54 (2016)
Breiman, L.: Some properties of splitting criteria. Mach. Learn. 24(1), 41–47 (1996)
Cunningham, P., Delany, S.J.: k-nearest neighbour classifiers. Multiple Classifier Syst. 34(8), 1–17 (2007)
Kolaja, J., Ehlerova, J.K.: Effectivity of sports timing RFID system, field study. In: 2019 IEEE International Conference on RFID Technology and Applications (RFID-TA), pp. 220–223. IEEE (2019)
Krigslund, R., Dosen, S., Popovski, P., Dideriksen, J.L., Pedersen, G.F., Farina, D.: A novel technology for motion capture using passive UHF RFID tags. IEEE Trans. Biomed. Eng. 60(5), 1453–1457 (2012)
Nikam, S.S.: A comparative study of classification techniques in data mining algorithms. Orient. J. Comput. Sci. Technol. 8(1), 13–19 (2015)
Polivka, M., Svanda, M., Hudec, P.: The optimization of the RFID system for the identification of sportsmen in mass races. In: 2007 European Microwave Conference, pp. 732–735. IEEE (2007)
Safavian, S.R., Landgrebe, D.: A survey of decision tree classifier methodology. IEEE Trans. Syst. Man Cybern. 21(3), 660–674 (1991)
Tuttle, J.R.: Traditional and emerging technologies and applications in the radio frequency identification (RFID) industry. In: 1997 IEEE Radio Frequency Integrated Circuits (RFIC) Symposium. Digest of Technical Papers, pp. 5–8. IEEE (1997)
Woellik, H., Mueller, A., Herriger, J.: Permanent RFID timing system in a track and field athletic stadium for training and analysing purposes. Procedia Eng. 72, 202–207 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Uran, C., Prossegger, M., Vock, S., Wöllik, H. (2020). A Machine Learning Approach for Classifying Movement Styles Based on UHF-RFID Detections. In: Fujita, H., Fournier-Viger, P., Ali, M., Sasaki, J. (eds) Trends in Artificial Intelligence Theory and Applications. Artificial Intelligence Practices. IEA/AIE 2020. Lecture Notes in Computer Science(), vol 12144. Springer, Cham. https://doi.org/10.1007/978-3-030-55789-8_77
Download citation
DOI: https://doi.org/10.1007/978-3-030-55789-8_77
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-55788-1
Online ISBN: 978-3-030-55789-8
eBook Packages: Computer ScienceComputer Science (R0)