Abstract
Gait authentication as a technique that can continuously provide identity recognition on mobile devices for security has been investigated by academics in the community for decades. However, most of the existing work achieves insufficient generalization to complex real-world environments due to the complexity of the noisy real-world gait data. To address this limitation, we propose an intelligent Implicit Real-time Gait Authentication (IRGA) system based on Deep Neural Networks (DNNs) for enhancing the adaptability of gait authentication in practice. In the proposed system, the gait data (whether with complex interference signals) will first be processed sequentially by the imperceptible collection module and data preprocessing module for improving data quality. In order to illustrate and verify the suitability of our proposal, we provide analysis of the impact of individual gait changes on data feature distribution. Finally, a fusion neural network composed of a Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) is designed to perform feature extraction and user authentication. We evaluate the proposed IRGA system in heterogeneous complex scenarios and present start-of-the-art comparisons on three datasets. Extensive experiments demonstrate that the IRGA system achieves improved performance simultaneously in several different metrics.
- [1] . 2020. Sensor-based continuous authentication of smartphones’ users using behavioral biometrics: A contemporary survey. IEEE Internet of Things Journal 8, 1 (2020), 65–84.Google Scholar
Cross Ref
- [2] . 2020. Sensor-based continuous authentication of smartphones’ users using behavioral biometrics: A contemporary survey. IEEE Internet of Things Journal 8, 1 (2020), 65–84.Google Scholar
Cross Ref
- [3] . 2006. K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing 54, 11 (2006), 4311–4322.Google Scholar
Digital Library
- [4] . 2022. Real-world smartphone-based gait recognition. Computers & Security 113 (2022), 102557.Google Scholar
Digital Library
- [5] . 2017. Human identification using selected features from finger geometric profiles. IEEE Transactions on Systems, Man, and Cybernetics: Systems 50, 3 (2017), 747–761.Google Scholar
Cross Ref
- [6] . 1994. Using dynamic time warping to find patterns in time series.. In KDD Workshop. AAAI Press, Seattle, WA, 359–370.Google Scholar
- [7] . 2010. Toward unconstrained ear recognition from two-dimensional images. IEEE Transactions on Systems, Man, and Cybernetics– Part A: Systems and Humans 40, 3 (2010), 486–494.Google Scholar
Digital Library
- [8] . 2020. ContAuth: Continual learning framework for behavioral-based user authentication. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 4, 4 (2020), 1–23.Google Scholar
Digital Library
- [9] . 2022. Knowledge-guided multi-label few-shot learning for general image recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 3 (2022), 1371–1384.Google Scholar
Cross Ref
- [10] . 2019. Multi-step data prediction in wireless sensor networks based on one-dimensional CNN and bidirectional LSTM. IEEE Access 7 (2019), 117883–117896.Google Scholar
Cross Ref
- [11] . 2017. A gait recognition method for human following in service robots. IEEE Transactions on Systems, Man, and Cybernetics: Systems 48, 9 (2017), 1429–1440.Google Scholar
Cross Ref
- [12] . 2018. Analysis of spatio-temporal representations for robust footstep recognition with deep residual neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence 41, 2 (2018), 285–296.Google Scholar
Digital Library
- [13] . 2018. IDNet: Smartphone-based gait recognition with convolutional neural networks. Pattern Recognition 74 (2018), 25–37.Google Scholar
Digital Library
- [14] . 2007. Spoof attacks on gait authentication system. IEEE Transactions on Information Forensics and Security 2, 3 (2007), 491–502.Google Scholar
Digital Library
- [15] . 2019. Abnormal gait recognition algorithm based on LSTM-CNN fusion network. IEEE Access 7 (2019), 163180–163190.Google Scholar
Cross Ref
- [16] . 2018. Human action monitoring for healthcare based on deep learning. IEEE Access 6 (2018), 52277–52285.Google Scholar
Cross Ref
- [17] . 2016. Deep Learning. MIT Press, London, England.Google Scholar
Digital Library
- [18] . 2021. C2CL: Contact to contactless fingerprint matching. IEEE Transactions on Information Forensics and Security 17 (2021), 196–210.Google Scholar
Digital Library
- [19] . 2007. Gait modeling for human identification. In Proceedings 2007 IEEE International Conference on Robotics and Automation. IEEE, Rome, Italy, 4833–4838.Google Scholar
Cross Ref
- [20] . 2022. An empirical study of the impact of masks on face recognition. Pattern Recognition 122 (2022), 108308.Google Scholar
Digital Library
- [21] . 2022. Examining the current status and emerging trends in continuous authentication technologies through citation network analysis. Computing Surveys 55, 6 (2022), 1–31.Google Scholar
Digital Library
- [22] . 2021. DeepVS2.0: A saliency-structured deep learning method for predicting dynamic visual attention. International Journal of Computer Vision 129, 1 (2021), 203–224.Google Scholar
Digital Library
- [23] . 2021. Real time gait based person authentication using deep hybrid network. In 2021 IEEE 4th International Conference on Knowledge Innovation and Invention (ICKII’21). IEEE, Taichung, Taiwan, 155–159.Google Scholar
Cross Ref
- [24] . 2019. Mobile platform continuous authentication scheme based on gait characteristics. Journal on Communications 40, 7 (2019), 126.Google Scholar
- [25] . 2020. Behavioral biometrics for continuous authentication in the Internet-of-Things era: An artificial intelligence perspective. IEEE Internet of Things Journal 7, 9 (2020), 9128–9143.Google Scholar
Cross Ref
- [26] . 2021. Softwarized attention-based context-aware group recommendation technology in event-based industrial cyber-physical systems. IEEE Transactions on Industrial Informatics 17, 10 (2021), 6894–6905.Google Scholar
Cross Ref
- [27] . 2020. Continuous authentication by free-text keystroke based on CNN and RNN. Computers & Security 96 (2020), 101861.Google Scholar
Cross Ref
- [28] . 2017. Exploring finger vein based personal authentication for secure IoT. Future Generation Computer Systems 77 (2017), 149–160.Google Scholar
Digital Library
- [29] . 2018. Accelerometer-based gait recognition using PCA & LDA algorithms. In 2018 IEEE 23rd International Conference on Digital Signal Processing (DSP’18). IEEE, Shanghai, China, 1–4.Google Scholar
Cross Ref
- [30] . 1998. Cubic spline interpolation. College of the Redwoods 45, 1 (1998), 1049–1060.Google Scholar
- [31] . 2019. You walk, we authenticate: Lightweight seamless authentication based on gait in wearable IoT systems. IEEE Access 7 (2019), 37883–37895.Google Scholar
Cross Ref
- [32] . 2014. The largest inertial sensor-based gait database and performance evaluation of gait-based personal authentication. Pattern Recognition 47, 1 (2014), 228–237.Google Scholar
Digital Library
- [33] . 2016. Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16, 1 (2016), 115.Google Scholar
Cross Ref
- [34] . 2012. Zee: Zero-effort crowdsourcing for indoor localization. In Proceedings of the 18th Annual International Conference on Mobile Computing and Networking. ACM, Istanbul, Turkey, 293–304.Google Scholar
Digital Library
- [35] . 2019. Multi-task self-supervised learning for human activity detection. Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 3, 2 (2019), 1–30.Google Scholar
Digital Library
- [36] . 2022. Deep gait recognition: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 1 (2022), 264–284.Google Scholar
Cross Ref
- [37] . 2017. Performance analysis of multi-motion sensor behavior for active smartphone authentication. IEEE Transactions on Information Forensics and Security 13, 1 (2017), 48–62.Google Scholar
Cross Ref
- [38] . 2018. Accelerometer-based speed-adaptive gait authentication method for wearable IoT devices. IEEE Internet of Things Journal 6, 1 (2018), 820–830.Google Scholar
Cross Ref
- [39] . 2008. Visualizing data using t-SNE. Journal of Machine Learning Research 9, 11 (2008), 2579–2605.Google Scholar
- [40] . 2016. The MobiAct dataset: Recognition of activities of daily living using smartphones. In International Conference on Information and Communication Technologies for Ageing Well and e-Health, Vol. 2. SCITEPRESS, Rome, Italy, 143–151.Google Scholar
Cross Ref
- [41] . 2019. Gait analysis in unconstrained environments. PhD thesis, Ph. D. dissertation, Electrical and Computer Engineering, Instituto Superior.Google Scholar
- [42] . 2016. A discriminative feature learning approach for deep face recognition. In European Conference on Computer Vision. Springer, Cham, 499–515.Google Scholar
Cross Ref
- [43] . 2018. KEH-Gait: Using kinetic energy harvesting for gait-based user authentication systems. IEEE Transactions on Mobile Computing 18, 1 (2018), 139–152.Google Scholar
Digital Library
- [44] . 2017. Gait-Watch: A context-aware authentication system for smart watch based on gait recognition. In Proceedings of the 2nd International Conference on Internet-of-Things Design and Implementation. ACM, New York, NY, 59–70.Google Scholar
Digital Library
- [45] . 2021. Gait-based implicit authentication using edge computing and deep learning for mobile devices. Sensors 21, 13 (2021), 4592.Google Scholar
Cross Ref
- [46] . 2013. Palm-print classification by global features. IEEE Transactions on Systems, Man, and Cybernetics: Systems 43, 2 (2013), 370–378.Google Scholar
Cross Ref
- [47] . 2014. Accelerometer-based gait recognition by sparse representation of signature points with clusters. IEEE Transactions on Cybernetics 45, 9 (2014), 1864–1875.Google Scholar
Cross Ref
- [48] . 2022. On learning disentangled representations for gait recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 1 (2022), 345–360.Google Scholar
Digital Library
- [49] . 2020. Deep learning-based gait recognition using smartphones in the wild. IEEE Transactions on Information Forensics and Security 15 (2020), 3197–3212.Google Scholar
Index Terms
IRGA: An Intelligent Implicit Real-time Gait Authentication System in Heterogeneous Complex Scenarios
Recommendations
Analysis and evaluation of hemiplegic gait based on wearable sensor network
Highlights- Quantitative analysis and evaluation of hemiplegic gait based on body sensor network.
AbstractHemiplegia is a common symptom of acute cerebrovascular disease, and most patients with hemiplegia have abnormal gaits. Descriptive evaluation methods are commonly used in clinical for gait analysis, and outcomes are overly reliant on ...
Performance Evaluation of Jaipur Knee Joint through Kinematics and Kinetics Gait Symmetry with Unilateral Transfemoral Indian Amputees
Gait analysis is considered as the most systematic study of human motion. The analysis of gait includes visual and analytical perception of the individual, augmentation of various mechanical instrumentations for measuring movement of body, muscles ...
A real-time topography of maximum contact pressure distribution at medial tibiofemoral knee implant during gait
Knee contact pressure is a crucial factor in the knee rehabilitation programs. Although contact pressure can be estimated using finite element analysis, this approach is generally time-consuming and does not satisfy the real-time requirements of a ...






Comments