eISSN: 3087-4319 editor@aimjournals.com
All Journals
Submit your article

International Journal of Next-Generation Engineering and Technology

Open Access Peer Review International
Open Access

The Convergence of Spatiotemporal Deep Learning and Trustworthy Biometrics: A Comprehensive Review of Human Activity Recognition, Ethical Governance, And Security Paradigms

DOI
PDF
Dr. Simona Kript 1 ,
4 Department of Computer Science and Engineering, University of Melbourne, Australia

Abstract

The rapid evolution of Artificial Intelligence (AI) has catalyzed a paradigm shift in how human behaviors are monitored, analyzed, and secured. This research article provides an extensive investigation into the intersection of spatiotemporal dynamics in human activity recognition (HAR) and the multi-faceted landscape of AI-driven biometrics. By synthesizing a decade of advancements in video action recognition-ranging from 3D convolutional neural networks (3D CNNs) to hybrid Long Short-Term Memory (LSTM) architectures-this study delineates the technical progression of motion analysis. Parallel to these technical strides, we evaluate the socio-technical dimensions of biometric systems, including facial recognition, behavioral biometrics for financial security, and medical clinical applications. Central to this analysis is the concept of "Trustworthy AI," encompassing explainability, fairness across demographic groups, and adversarial robustness. The article explores the ethical tensions between pervasive surveillance and privacy rights, particularly in public spaces and retail environments. Furthermore, we examine the systemic biases inherent in commercial algorithms regarding race and gender, supported by contemporary empirical data. Finally, this work outlines the future research directions necessary to reconcile high-performance activity recognition with the requirements of an AI Bill of Rights, ensuring that the next generation of biometric passports and behavioral security measures are both technically resilient and socially equitable.

Keywords

Human Activity Recognition, Spatiotemporal Dynamics, Trustworthy AI, Behavioral Biometrics

References

📄 Huang, X. et al. (2023). A review of video action recognition based on 3D convolution. Comput. Electr. Eng.
📄 Hu, M. (2022). Biometrics and an AI Bill of Rights. Technology and Society Magazine, 41(2), 63–69.
📄 Korgialas, C., Pantraki, E., Bolari, A., Sotiroudi, M., and Kotropoulos, C. (2023). Face aging by explainable conditional adversarial autoencoders. Journal of Imaging, 9(5), 96.
📄 Kumar, P. et al. (2023). Artificial intelligence in healthcare: review, ethics, trust challenges & future research directions. Eng. Appl. Artif. Intell.
📄 Lai, K., Oliveira, H. C., Hou, M., Yanushkevich, S. N., and Shmerko, V. P. (2020). Risk, trust, and bias: Causal regulators of biometric-enabled decision support. IEEE Access, 8, 148779–148792.
📄 Lavanya, P., Devi, G., and Rao, K. (2021). LBPH-Based Face Recognition System for Attendance Management. Proceedings of the 3rd International Conference on Intelligent Human Computer Interaction (IHCI), 61–70.
📄 Li, B., Qi, P., Liu, B., Di, S., Liu, J., Pei, J., and Zhou, B. (2023). Trustworthy AI: From principles to practices. ACM Computing Surveys (CSUR), 55(9), 1–46.
📄 Lin, Y. S., Liu, Z. Y., Chen, Y. A., Wang, Y. S., Chang, Y. L., and Hsu, W. H. (2021). xCos: An explainable cosine metric for face verification task. ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 17(3s), 1–16.
📄 Lu, H. Y. (2020). Med Metrics: Biometrics Passports in Medical and Clinical Healthcare That Enable AI and Blockchain. 2020 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), 67–71.
📄 Ma, C.-Y. et al. (2019). TS-LSTM and temporal-inception: exploiting spatiotemporal dynamics for activity recognition. Signal Process. Image Commun.
📄 Majd, M. et al. (2020). Correlational convolutional LSTM for human action recognition. Neurocomputing.
📄 McStay, A. (2020). Emotional AI, soft biometrics and the surveillance of emotional life: An unusual consensus on privacy. Int. J. Commun., 14, 1327–1346.
📄 Merhav, N. (2018). Ensemble performance of biometric authentication systems based on secret key generation. IEEE Transactions on Information Theory, 65(4), 2477–2491.
📄 Moraes, T. G., Almeida, E. C., and de Pereira, J. R. L. (2021). Smile, you are being identified! Risks and measures for the use of facial recognition in (semi-) public spaces. AI and Ethics, 1(2), 159–172.
📄 Muhammad, K. (2021). Human action recognition using attention based LSTM network with dilated CNN features. Future Generat. Comput. Syst.
📄 Nagpal, S., Singh, M., Narain, S., and Bhatnagar, S. (2023). Privacy-enabled biometric authentication using deep learning. Computers & Security, 125, 103014.
📄 Nanni, L., Brahnam, S., and Lumini, A. (2020). Deep learning for ear biometrics: A survey. Neurocomputing, 383, 107–120.
📄 Nwoye, C. I., and Thompson, K. A. (2020). Facial recognition technology in modern society: Challenges and legal implications. International Journal of Law and Information Technology, 28(2), 187–213.
📄 Patel, V. M., Smith, L. N., Guerra, L. M., Nasrabadi, N. M., and Chellappa, R. (2019). Automatic target recognition in forward-looking infrared imagery: A survey. IEEE Access, 7, 104379–104388.
📄 Phillips, P. J. and Przybocki, M. (2020). Four Principles of Explainable AI as Applied to Biometrics and Facial Forensic Algorithms. 2020 11th IEEE International Conference on Biometrics Theory, Applications and Systems (BTAS), 1–8.
📄 Ray, A. et al. (2023). Transfer learning enhanced vision-based human activity recognition: a decade-long analysis. Int. J. Inf. Manag. Data Insights.
📄 Rodgers, W., Yeung, F., Odindo, C., and Degbey, W. Y. (2021). Artificial intelligence-driven music biometrics influencing customers' retail buying behavior. J. Bus. Res., 126(C), 401–414.
📄 Siddiqui, S., Naseer, S., Rana, A., and Afzal, M. (2021). A survey of deep learning techniques for biometric identification. Journal of King Saud University-Computer and Information Sciences, 33(10), 1284–1292.
📄 Singh, S., Singhal, A., and Jain, A. (2021). Face recognition with mask using deep learning techniques. Journal of Ambient Intelligence and Humanized Computing, 12, 9435–9446.
📄 Sousa, A., Salami, H., and Soltanalian, M. (2021). Adversarial robustness of biometric recognition: A comprehensive survey. IEEE Transactions on Artificial Intelligence, 3(4), 611–628.
📄 Uluturk, T. E., Uygun, E., and Yildiz, S. (2023). Face anti-spoofing by using a deep multi-scale neural network architecture. Neural Computing and Applications, 35, 5145–5161.
📄 Valiveti, S. S. S. (2025). AI-Driven Behavioral Biometrics for 401(k) Account Security. International Research Journal of Advanced Engineering and Technology, 2(06), 23-26. https://doi.org/10.55640/irjaet-v02i06-04
📄 Vanarase, T., Koike, K., and Hsu, Y. (2023). Fairness in facial recognition: Do race and gender affect the accuracy of commercial automatic face recognition algorithms? IEEE Access, 11, 5719–5736.

Similar Articles

1-10 of 40

You may also start an advanced similarity search for this article.