Smart Lock System using IoT
Keywords:
Access control systems, Dynamic time warping (DTW), ESP32, Heart-rate biometrics, IoT smart lock, Multimodal authentication, Photoplethysmography (PPG), Physiological signals, Speaker verification, Voice biometricsAbstract
Multimodal biometric smart-lock system integrates heart-rate waveform authentication with phrase-dependent voice verification for secure IoT access control. Photoplethysmography (PPG)-based biometrics provide inherent liveness and individualized cardiovascular patterns, while voice features offer behavioral discrimination and phrase-level security. The proposed system uses a MAX3010x optical sensor for real-time PPG acquisition, followed by filtering, segmentation, and dynamic time warping (DTW) alignment to match input signals with enrolled templates. Voice authentication applies Mel-Frequency Cepstral Coefficients (MFCCs) for speaker verification. Both modalities operate on an ESP32 platform, enabling real-time processing. Results show that multimodal fusion significantly reduces false acceptance rates compared to single-modal systems. The system demonstrates reliable, low-cost, and liveness-assured user authentication suitable for secure IoT environments.
References
N. Karimian, Z. Guo, M. Tehranipoor, D. Forte, “Human recognition from photoplethysmography (PPG) based on non-fiducial features”, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2017). March 2017, New Orleans, Louisiana, USA. doi: https://doi.org/10.1109/ICASSP.2017.7953035
A. Sarkar, A. L. Abbott, Z. Doerzaph, “Biometric authentication using photoplethysmography signals”, IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS 2016). pp. 6–9, September 2016, Niagara Falls, New York, USA. doi: https://doi.org/10.1109/BTAS.2016.7791193
O. R. Patil, et al, “A non-contact PPG biometric system based on deep neural network”, 2018 IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS 2018). 22–25 October 2018, Redondo Beach, California, USA. doi: https://doi.org/10.1109/BTAS.2018.8698552
D. Y. Hwang, B. Taha, D. S. Lee, D. Hatzinakos, “Evaluation of the time stability and uniqueness in PPG-based biometric system”, IEEE Transactions on Information Forensics and Security (TIFS). July 2020. doi: https://doi.org/10.1109/TIFS.2020.3006313
D. Biswas, et al, “CorNET: Deep learning framework for PPG-based heart rate estimation and biometric identification in ambulant environment”, IEEE Transactions on Biomedical Circuits and Systems (TBCAS) 2019. doi: https://doi.org/10.1109/TBCAS.2019.2892297
I. Everson et al, “Biometric Net: Deep-learning based biometric identification using wrist-worn PPG”, IEEE International Symposium on Circuits and Systems, 2018. Florence, Italy, 2018, pp. 1-5, doi: https://doi.org/10.1109/ISCAS.2018.8350983
S. Salvador, P. Chan, “Toward accurate dynamic time warping in linear time and space (FastDTW)”, Intelligent Data Analysis: An International Journal, 2007. vol. 11, no. 5, pp. 561–580. doi: https://doi.org/10.3233/IDA-2007-11508
S. M. Alghamdi, S. Kammoun Jarraya and F. Kateb, “Enhancing security in multimodal biometric fusion: Analyzing adversarial attacks: IEEE Access, vol. 12, pp. 106133–106145, 2024, doi: https://doi.org/10.1109/ACCESS.2024.3435527
A. Cherry, A. Nasser, W. Salameh, M. Abou Ali, and M. Hajj-Hassan, “Real-time PPG-based biometric identification: Advancing security with 2D Gram matrices and deep learning models,” Sensors, vol. 25, no. 1, p. 40, Dec. 2024, doi: https://doi.org/10.3390/s25010040
M. Boukhechba, L. Cai, C. Wu, and L. E. Barnes, “ActiPPG: Using deep neural networks for activity recognition from wrist-worn photoplethysmography (PPG) sensors,” Smart Health, vol. 14, p. 100082, Dec. 2019, doi: https://doi.org/10.1016/j.smhl.2019.100082
H. -C. Chang, T. Wang, C. -A. Liao and T. -T. Liu, “A low-power PPG processor for real-time biometric identification and heart rate estimation,” IEEE Transactions on Circuits and Systems II: Express Briefs, vol. 70, no. 10, pp. 3932–3936, Oct. 2023, doi: https://doi.org/10.1109/TCSII.2023.3291891
D. Shah and V. Haradi, “IoT-based biometrics implementation on Raspberry Pi,” Procedia Computer Science, vol. 79, pp. 328–336, 2016, doi: https://doi.org/10.1016/j.procs.2016.03.043
Y. Xu, Z. Wang, and X. Liu, “Photoplethysmogram (PPG)-based biometric identification using 2D signal transformation and multi-scale feature fusion,” Sensors, vol. 25, no. 15, p. 4849, Aug. 2025, doi: https://doi.org/10.3390/s25154849
T. Kinnunen and H. Li, “An overview of text-independent speaker recognition: From features to supervectors,” Speech Communication, vol. 52, no. 1, pp. 12–40, Jan. 2010, doi: https://doi.org/10.1016/j.specom.2009.08.009
A. R. Kavsaoğlu, K. Polat, M. R. Bozkurt and H. Muthusamy, “Feature extraction for biometric recognition with photoplethysmography signals,” 2013 21st Signal Processing and Communications Applications Conference (SIU), Haspolat, Turkey, 2013, pp. 1–4, doi: https://doi.org/10.1109/SIU.2013.6531568
