Behavioral Biometric-Based Human Identification from 3D Skeletal Motion Using Convolutional Neural Networks

Endang Sri Rahayu; Mauridhi Hery Purnomo

doi:10.48084/etasr.12883

Authors

Endang Sri Rahayu Department of Electrical Engineering, Universitas Jayabaya, Jakarta, Indonesia
Mauridhi Hery Purnomo Department of Computer Engineering, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia

Volume: 15 | Issue: 6 | Pages: 28640-28645 | December 2025 | https://doi.org/10.48084/etasr.12883

Received: 23 June 2025 | Revised: 21 August 2025 and 5 September 2025 | Accepted: 7 September 2025 | Online: 1 October 2025

Corresponding author: Endang Sri Rahayu

Abstract

Accurate and reliable human identification is needed to provide personalized services in conjunction with current and future technological developments. This study presents a motion-based human identification approach that utilizes 3D skeleton data to capture unique individual motion patterns. Joint coordinates are processed to extract spatial and temporal features through two Convolutional Neural Network (CNN) models with different depths. Evaluation on the UTKinect-Action3D dataset (20 joints, 10 subjects, nine actions) shows that the deeper model achieves 98.25% accuracy, whereas the lighter model achieves 96.97%. To assess generalization, both models are further tested on the Florence 3D Actions dataset with 15 joints, achieving accuracies of 85.53% and 83.55%, respectively. These findings confirm that detailed motion representation significantly improves identification performance and demonstrate that CNN-based models can effectively recognize individuals based on body motion patterns.

Keywords:

biometrics, CNN, identification, skeletal

Downloads

Download data is not yet available.

References

P. Limcharoen, N. Khamsemanan, and C. Nattee, "Gait Recognition and Re-Identification Based on Regional LSTM for 2-Second Walks," IEEE Access, vol. 9, pp. 112057–112068, 2021. DOI: https://doi.org/10.1109/ACCESS.2021.3102936

E. M. Saoudi, J. Jaafari, and S. J. Andaloussi, "Advancing human action recognition: A hybrid approach using attention-based LSTM and 3D CNN," Scientific African, vol. 21, Sept. 2023, Art. no. e01796. DOI: https://doi.org/10.1016/j.sciaf.2023.e01796

D. S. Rao, K. Ramyasree, S. M. K. M. A. Ahmad, and M. S. Rao, "DHAR-Net: A Deep Learning Framework for Hybrid Applications that Combines Motion and Depth Data to Improve Human Action Recognition," International Journal of Intelligent Engineering and Systems, vol. 18, no. 3, pp. 133–149, Apr. 2025. DOI: https://doi.org/10.22266/ijies2025.0430.10

R. T. Yunardi, T. A. Sardjono, and R. Mardiyanto, "Enhancing Surveillance Vision-Based Human Action Recognition Using Skeleton Joint Swing and Angle Feature and Modified AlexNet-LSTM," International Journal of Intelligent Engineering and Systems, vol. 18, no. 1, pp. 754–768, Feb. 2025. DOI: https://doi.org/10.22266/ijies2025.0229.53

S. Msaad, Y. W. K. Zoetgnandé, J. L. Dillenseger, and G. Carrault, "Detecting change in the routine of the elderly," Measurement: Sensors, vol. 24, Dec. 2022, Art. no. 100418. DOI: https://doi.org/10.1016/j.measen.2022.100418

H. U. R. Khalid, A. Gorji, A. Bourdoux, S. Pollin, and H. Sahli, "Multi-View CNN-LSTM Architecture for Radar-Based Human Activity Recognition," IEEE Access, vol. 10, pp. 24509–24519, 2022. DOI: https://doi.org/10.1109/ACCESS.2022.3150838

R. K. Athota and D. Sumathi, "Human activity recognition based on hybrid learning algorithm for wearable sensor data," Measurement: Sensors, vol. 24, Dec. 2022, Art. no. 100512. DOI: https://doi.org/10.1016/j.measen.2022.100512

S. Gupta, "Deep learning based human activity recognition (HAR) using wearable sensor data," International Journal of Information Management Data Insights, vol. 1, no. 2, Nov. 2021, Art. no. 100046. DOI: https://doi.org/10.1016/j.jjimei.2021.100046

T. Zhang et al., "A Joint Deep Learning and Internet of Medical Things Driven Framework for Elderly Patients," IEEE Access, vol. 8, pp. 75822–75832, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.2989143

F. Sun, W. Zang, R. Gravina, G. Fortino, and Y. Li, "Gait-based identification for elderly users in wearable healthcare systems," Information Fusion, vol. 53, pp. 134–144, Jan. 2020. DOI: https://doi.org/10.1016/j.inffus.2019.06.023

J. Park, W. S. Lim, D. W. Kim, and J. Lee, "GTSNet: Flexible architecture under budget constraint for real-time human activity recognition from wearable sensor," Engineering Applications of Artificial Intelligence, vol. 124, Sept. 2023, Art. no. 106543. DOI: https://doi.org/10.1016/j.engappai.2023.106543

N. Halim, "Stochastic recognition of human daily activities via hybrid descriptors and random forest using wearable sensors," Array, vol. 15, Sep. 2022, Art. no. 100190. DOI: https://doi.org/10.1016/j.array.2022.100190

A. Ustad et al., "Validation of an Activity Type Recognition Model Classifying Daily Physical Behavior in Older Adults: The HAR70+ Model," Sensors, vol. 23, no. 5, Jan. 2023, Art. no. 2368. DOI: https://doi.org/10.3390/s23052368

S. Natarajan, R. Rathinasabapathy, A. R. Aravind, V. Chandra, and D. Deepa, "Fingerprint Revelation: Unveiling the Brilliance of Biometric Identity with SpatioTemporalNet," International Journal of Intelligent Engineering and Systems, vol. 18, no. 1, pp. 446–462, Feb. 2025. DOI: https://doi.org/10.22266/ijies2025.0229.32

S. Raziani and M. Azimbagirad, "Deep CNN hyperparameter optimization algorithms for sensor-based human activity recognition," Neuroscience Informatics, vol. 2, no. 3, Sept. 2022, Art. no. 100078. DOI: https://doi.org/10.1016/j.neuri.2022.100078

E. García, M. Villar, M. Fáñez, J. R. Villar, E. De La Cal, and S. B. Cho, "Towards effective detection of elderly falls with CNN-LSTM neural networks," Neurocomputing, vol. 500, pp. 231–240, Aug. 2022. DOI: https://doi.org/10.1016/j.neucom.2021.06.102

J. Chen, J. Wang, Q. Yuan, and Z. Yang, "CNN-LSTM Model for Recognizing Video-Recorded Actions Performed in a Traditional Chinese Exercise," IEEE Journal of Translational Engineering in Health and Medicine, vol. 11, pp. 351–359, 2023. DOI: https://doi.org/10.1109/JTEHM.2023.3282245

D. Arifoglu and A. Bouchachia, "Activity Recognition and Abnormal Behaviour Detection with Recurrent Neural Networks," Procedia Computer Science, vol. 110, pp. 86–93, Jan. 2017. DOI: https://doi.org/10.1016/j.procs.2017.06.121

Y. Hu et al., "Harmonic Loss Function for Sensor-Based Human Activity Recognition Based on LSTM Recurrent Neural Networks," IEEE Access, vol. 8, pp. 135617–135627, 2020. DOI: https://doi.org/10.1109/ACCESS.2020.3003162

"UTKinect-Action3D Dataset." [Online]. Available: http://cvrc.ece.utexas.edu/KinectDatasets/HOJ3D.html.

L. Xia, C. C. Chen, and J. K. Aggarwal, "View invariant human action recognition using histograms of 3D joints," in 2012 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, RI, USA, June 2012, pp. 20–27. DOI: https://doi.org/10.1109/CVPRW.2012.6239233

"Florence 3D Actions Dataset." [Online]. Available: https://www.micc.unifi.it/resources/datasets/florence-3d-actions-dataset/.

L. Seidenari, V. Varano, S. Berretti, A. Del Bimbo, and P. Pala, "Recognizing Actions from Depth Cameras as Weakly Aligned Multi-part Bag-of-Poses," in 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, OR, USA, Jun. 2013, pp. 479–485. DOI: https://doi.org/10.1109/CVPRW.2013.77

S. M. E. Hossain, S. O. F. Khairy, A. Soosaimanickam, and A. M. Raisuddin, "Effective Classifier Identification in Biometric Pattern Recognition," Engineering, Technology & Applied Science Research, vol. 14, no. 5, pp. 16604–16608, Oct. 2024. DOI: https://doi.org/10.48084/etasr.7424

A. Batouche, S. Meshoul, H. Shaiba, and M. Batouche, "A Novel Approach to Enhanced Cancelable Multi-Biometrics Personal Identification Based on Incremental Deep Learning," Computers, Materials & Continua, vol. 83, no. 2, pp. 1727–1752, 2025. DOI: https://doi.org/10.32604/cmc.2025.063227