V.D. Dementiev1, N.A. Borsuk2, T.A. Onufrieva3

1-3 Kaluga Branch of the Bauman Moscow State Technical University (Kaluga, Russia)

1 vadim23dem@yandex.ru, 2 borsuk.65@yandex.ru, 3 onufrievata@bmstu.ru

This paper addresses the problem of contactless biometric authentication for industrial enterprise access control, where traditional methods – fingerprint scanners, face recognition terminals, and proximity cards – face practical limitations due to hygiene requirements, personal protective equipment, and high personnel throughput at checkpoints. The proposed solution is based on Wi-Fi Channel State Information (CSI) analysis combined with machine learning, enabling passive identification of employees as they pass through a designated control zone without any deliberate interaction with the system.

The physical basis of the approach lies in the unique way each individual modulates radio signal propagation. A person's anthropometric characteristics determine the effective scattering cross-section of their body, producing distinctive amplitude patterns across signal subcarriers, while involuntary micro-movements such as breathing and cardiac activity introduce low-frequency phase modulations in the 0.1…3 Hz range. These individual-specific patterns constitute the biometric signature extracted by the system. Since manually engineering features that capture such subtle radio-physical phenomena is practically infeasible, a machine learning model is essential for automatic discovery of discriminative representations in high-dimensional time-series CSI data.

The system hardware employs ESP32 microcontrollers placed 3 meters apart at 1.5-meter height, forming a control zone in which human presence substantially modulates the received signal across 52 OFDM subcarriers sampled at 100 Hz. The signal preprocessing pipeline consists of four sequential stages: temporal averaging to suppress high-frequency noise, a robust Hampel outlier filter based on median absolute deviation, a fifth-order Butterworth low-pass filter isolating the biomechanically relevant frequency band below 10 Hz, and linear phase calibration compensating for hardware clock instabilities. The processed data is segmented into one-second overlapping windows, each forming a classification sample.

The core contribution of the work is a specialized Dual-Branch Transformer architecture that processes amplitude and phase CSI characteristics through independent encoder branches. This design choice is motivated by the physically distinct nature of the two signal components: amplitude primarily encodes anthropometric information, while phase is more sensitive to fine-grained displacement dynamics. Processing them jointly would risk one modality dominating the learned representation. Each branch applies a linear projection of the 52-subcarrier input to a 32-dimensional space, adds sinusoidal positional encoding to preserve temporal structure, and passes the sequence through a Transformer encoder with four attention heads. The self-attention mechanism explicitly models pairwise dependencies across all time steps within the window, making it well-suited for capturing periodic micro-movement patterns that span several hundred milliseconds. Branch outputs are mean-pooled, concatenated, and passed to a linear classifier. The resulting model contains only 15,742 parameters, making it trainable on modest enterprise-scale datasets.

Experimental evaluation on a dataset of three employees and an Empty Zone class achieved an overall classification accuracy of 92.3%, with the Empty Zone class reaching perfect 100% accuracy – a critical property ensuring the system never grants access when no person is present. All misclassifications occurred exclusively between employee classes, with per-user accuracy ranging from 81.0% to 92.2% depending on anthropometric distinctiveness. An additional experiment demonstrated that raising device placement height from 1.0 to 1.5 meters improved overall accuracy to 96.0%, due to more favorable signal incidence angles and reduced floor-reflection interference.

The real-time recognition module operates as a five-state finite automaton, requiring three consecutive presence detections for initial triggering, five consistent predictions for signal stabilization, and a five-second majority voting procedure for final identification. End-to-end latency from zone entry to identification onset is under one second. Field tests confirmed recognition confidence levels of 85.7…96.5% across successful sessions, with the system running on a standard personal computer without hardware acceleration.

The results demonstrate the practical feasibility of passive Wi-Fi CSI-based biometric authentication for industrial access control, establishing a foundation for deployments in environments where contact-based biometrics are constrained by hygiene, safety, or operational requirements.

Dementiev V.D., Borsuk N.A., Onufrieva T.A. Features of technical implementation of biometric authentication system based on Wi-Fi channel state information analysis // Information-measuring and Control Systems. 2026. V. 24. № 3. P. 33−43. DOI: https://doi.org/10.18127/j20700814-202603-04

1. Avola D., Bernardini A., Danese F., Lezoche M., Mancini M., Pannone D., Ranaldi A. Transformer-Based Person Identification via Wi-Fi CSI Amplitude and Phase Perturbations. arXiv preprint arXiv:2507.12854. 2025. https://arxiv.org/abs/2507.12854.
2. Sistemy Wi-Fi Sensing: kak opredelit prisutstvie i aktivnost lyudei cherez analiz radiosignalov. VAS Experts. https://habr.com/ru/companies/vasexperts/articles/946574/. (in Russian)
3. Yanagimoto H., Tokioka W., Hashimoto K. Human Detection with WiFi CSI. Department of Applied Mathematics and Statistics. Institute of Technology of Cambodia. 2024. https://www.researchgate.net/publication/385393909_Human_Detection_with_WiFi_CSI.
4. Kotaru M., Joshi K., Bharadia D., Katti S. SpotFi: Decimeter Level Localization Using WiFi. Proceedings of ACM SIGCOMM. 2015. P. 269−282. https://dl.acm.org/doi/10.1145/2785956.2787487.
5. Ma Y., Zhou G., Wang S. WiFi Sensing with Channel State Information: A Survey. ACM Computing Surveys. 2019. V. 52. № 3. article no. 46. https://dl.acm.org/doi/10.1145/3310194.
6. Using CSI from Wi-Fi-Enabled IoT for Authentication. Axiros Blog. https://www.axiros.com/blog/2021/07/19/using-csi-from-wi-fi-enabled-iot-for-authentication.
7. Chen X., Liu Y., Zhang X. et al. CSI-Based Human Activity Recognition: A Survey. IEEE Access. 2024. https://arxiv.org/html/2507.12854v1.
8. Iroanwusi C.G., Davies I.N., Bassey A.T. Secure Biometric Signal Processing: A Review. International Journal of Computer Science and Multimedia Technology. October 2025. V. 11. № 9. P. 93−107. DOI:10.56201/ijcsmt.vol.11.no9.2025.pg93.107. https://www.researchgate.net/publication/396237837_Secure_Biometric_Signal_Processing_A_Review.
9. Ghazali K.W.M., Zaidi N.I.N., Azman F.N., Mohammed N. Multi-Modal Biometric Authentication System Using Score Fusion Techniques. International Journal of Research and Innovation in Social Science (IJRISS). December 2025. V. 9. № 11. P. 3507−3514. DOI:10.47772/IJRISS.2025.91100278.
   https://www.researchgate.net/publication/398419445_Multi-Modal_Biometric_Authentication_System_Using_Score_Fusion_Techniques.
10. Rozanov I., Sotnikov A., Kim T. Simulation model parameter optimization method for multidimensional signals. Journal of Physics: Conference Series. 2024. V. 2701. № 1. Article № 012023. DOI: 10.1088/1742-6596/2701/1/012023. https://www.scopus.com/record/display.url?eid=2-s2.0-85187211454&origin=resultslist.
11. Gorshkov Y.G. Visualization of a Person's Emotional Tension by a Speech Signal. Scientific Visualization. 2023. V. 15. № 2. P. 102−112. DOI: 10.26583/sv.15.2.09. https://www.scopus.com/record/display.url?eid=2-s2.0-85165159178&origin=resultslist.
12. Informatsionno-izmeritelnye i upravlyayushchie sistemy. M.: Radiotekhnika. 2025. ISSN 2070-0814.  http://radiotec.ru/ru/journal/Information-measuring_and_Control_Systems/number/2025-6. (in Russian)