Abstract
This paper examines the impact of acceleration sensor localization on the performance of gait-based person identification. The novelty of the presented approach is the extension of the study to different types of ground substrates. A publicly available data corpus used in this study included gait cycles acquired using six sensor locations: trunk, right/left thigh, right/left shin, and right wrist. The results of two experiments conducted using the Support-vector machine (SVM) classifier are presented in the study. In the first one, classifiers were trained and validated using gait samples acquired on surfaces such as concrete, grass, cobblestone, slope, and stairs. In the second experiment, training was performed with pavement gait and validated with other substrates samples. For both presented scenarios, a pair of sensors located on the right thigh and right shank achieved the highest average identification rates.
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
Similar content being viewed by others
References
Sprager, S., Juric, M.B.: Inertial sensor-based gait recognition: a review. Sensors (Basel). 15(9), 22089–220127 (2015). https://doi.org/10.3390/s150922089
Atallah, L., et al.: Sensor placement for activity detection using wearable accelerometers. In: International Conference on Body Sensor Networks, pp. 24–29 (2010). https://doi.org/10.1109/BSN.2010.23
Zhang, Y., et al.: Accelerometer-based gait recognition by sparse representation of signature points with clusters. IEEE Trans. Cybern. 45(9), 1864–1875 (2015)
Panebianco, G.P., et al.: Analysis of the performance of 17 algorithms from a systematic review: influence of sensor position, analysed variable and computational approach in gait timing estimation from IMU measurements. Gait Posture. 66, 76–82 (2018)
Muaaz, M., Nickel, C.: Influence of different walking speeds and surfaces on accelerometer-based biometric gait recognition. In: 2012 35th International Conference on Telecommunications and Signal Processing, pp. 508–512 (2012)
Zhao, Y., Zhou, S.: Wearable device-based gait recognition using angle embedded gait dynamic images and a convolutional neural network. Sensors (Basel) 17(3), 478 (2017)
Wan, C., Wang, L., Phoha, V.V.: A survey on gait recognition. ACM Comput. Surv. 51, 1–35 (2018)
Sprager, S., Zazula, D.: Impact of different walking surfaces on gait identification based on higher-order statistics of accelerometer data. In: 2011 IEEE International Conference on Signal and Image Processing Applications, pp. 360–365 (2011)
Luo, Y., et al.: A database of human gait performance on irregular and uneven surfaces collected by wearable sensors. Sci. Data 7, 1–9 (2019)
Sawicki, A., Saeed, K.: Application of LSTM networks for human gait-based identification, theory and engineering of dependable computer systems and networks. Adv. Intell. Syst. Comput. 1389 (2021). https://doi.org/10.1007/978-3-030-76773-0_39
Subramanian, R., Sarkar, S.: Evaluation of Algorithms for Orientation Invariant Inertial Gait Matching. IEEE Transactions on Information Forensics and Security. p. 1. https://doi.org/10.1109/TIFS.2018.2850032 (2018)
Gadaleta, M., Rossi, M.: IDNet: smartphone-based gait recognition with convolutional neural networks. Pattern Recogn. 74, 1–10 (2018)
Hamdi M. M., Awad M. I., Abdelhameed M. M., Tolbah F. A.: Lower limb gait activity recognition using Inertial Measurement Units for rehabilitation robotics. In: International Conference on Advanced Robotics (ICAR), pp. 316–322 (2015)
Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1–30 (2006)
Olade, I., Fleming, C., Liang, H.N.: BioMove: biometric user identification from human kinesiological movements for virtual reality systems. Sensors 20, 2944 (2020). https://doi.org/10.3390/s20102944(2020)
Acknowledgment
This research was funded in whole or in part by National Science Centre, Poland 2021/41/N/ST6/02505. For the purpose of Open Access, the author has applied a CC-BY public copyright licence to any Author Accepted Manuscript (AAM) version arising from this submission.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Sawicki, A. (2022). Influence of Accelerometer Placement on Biometric Gait Identification. In: Zamojski, W., Mazurkiewicz, J., Sugier, J., Walkowiak, T., Kacprzyk, J. (eds) New Advances in Dependability of Networks and Systems. DepCoS-RELCOMEX 2022. Lecture Notes in Networks and Systems, vol 484. Springer, Cham. https://doi.org/10.1007/978-3-031-06746-4_25
Download citation
DOI: https://doi.org/10.1007/978-3-031-06746-4_25
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06745-7
Online ISBN: 978-3-031-06746-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)