Accurate User Identity Verification Using Gyroscope Signatures and Machine Learning Models

Latrisha S. Cardinas; Lea Jane M. Malificiado

doi:https://doi.org/10.47001/ICJES/2025.406005

Authors

Latrisha S. Cardinas

Department of Computer Science and Technology, Visayas State University, Philippines

Lea Jane M. Malificiado

Department of Computer Science and Technology, Visayas State University, Philippines

Abstract

The paper introduces a machine learning-driven approach for biometric signature classification, aimed at identifying and categorizing users based on unique patterns extracted from accelerometer and gyroscope sensor data. This methodology involves capturing user-specific signature data through prescribed movements using sensor-equipped devices. Subsequent feature extraction and machine learning model utilization enable accurate user classification grounded on distinct sensor data patterns. The versatility of this technology spans diverse applications, offering robust solutions for secure user authentication, access control, and tailored device interactions where precise user identity verification is essential.

Keywords

Machine Learning Biometric Accelerometer Gyroscope

Citation of this Article

Latrisha S. Cardinas, & Lea Jane M. Malificiado. (2025). Accurate User Identity Verification Using Gyroscope Signatures and Machine Learning Models. International Current Journal of Engineering and Science - ICJES, 4(6), 26-30. Article DOI: https://doi.org/10.47001/ICJES/2025.406005

References

Griechisch, E., Malk, M. I., & Liwicki, M. (2013). Online Signature Analysis Based on Accelerometric and Gyroscopic Pens and Legendre Series. 2013 12th International Conference on Document Analysis and Recognition, Washington, DC, USA, 2013, pp. 374-378, doi: 10.1109/ICDAR.2013.82.
Taimoor, M., Butt, H., Khadim, T., Ehatisham-ul-Haq, M., Raheel, A., & Arsalan, A. (2020). REALME: An Approach for Handwritten Signature Verification based on Smart Wrist Sensor. 2020 IEEE 23rd International Multitopic Conference (INMIC), Bahawalpur, Pakistan, 2020, pp. 1-6, doi: 10.1109/INMIC50486.2020.9318184.
Wehbi, M., Luge, D., Hamann, T., Barth, J., Kaempf, P., Zanca, D., & Eskofier, B. M. (2022). Surface-free multi-stroke trajectory reconstruction and word recognition using an imu-enhanced digital pen. Sensors, 22(14), 5347.
Subedi, D., Chitrakar, D., Yung, I., Zhu, Y., Su, Y. -H., & Huang, K. (2023). Biometric Signature Authentication with Low Cost Embedded Stylus. 2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Seattle, WA, USA, 2023, pp. 834-839, doi: 10.1109/AIM46323.2023.10196285.
Li, G., Zhang, L., & Sato, H. (2021). In-air Signature Authentication Using Smartwatch Motion Sensors. 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), Madrid, Spain, 2021, pp. 386-395, doi: 10.1109/COMPSAC51774.2021.00061.
Gupta, R., Chaudhary, S., Vedant, A., Choudhury, N. P., & Ladwani, V. (2022). Gesture Detection Using Accelerometer and Gyroscope. In Emerging Research in Computing, Information, Communication and Applications: Proceedings of ERCICA 2022 (pp. 99-116). Singapore: Springer Nature Singapore.
Brockly, M., Guest, R., Elliott, S., & Scott, J. (2011). Dynamic signature verification and the human biometric sensor interaction model. 2011 Carnahan Conference on Security Technology, Barcelona, Spain, 2011, pp. 1-6, doi: 10.1109/CCST.2011.6095937.
Deselaers, T., Keysers, D., Hosang, J., & Rowley, H. A. (2015). GyroPen: Gyroscopes for Pen-Input With Mobile Phones. IEEE Transactions on Human-Machine Systems, 45(2), 263-271, April 2015, doi: 10.1109/THMS.2014.2365723.
Schrapel, M., Grannemann, D., & Rohs, M. (2022). Sign H3re: Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen. In Proceedings of Mensch und Computer 2022 (pp. 209- 218).

[1] Griechisch, E., Malk, M. I., & Liwicki, M. (2013). Online Signature Analysis Based on Accelerometric and Gyroscopic Pens and Legendre Series. 2013 12th International Conference on Document Analysis and Recognition, Washington, DC, USA, 2013, pp. 374-378, doi: 10.1109/ICDAR.2013.82.

[2] Taimoor, M., Butt, H., Khadim, T., Ehatisham-ul-Haq, M., Raheel, A., & Arsalan, A. (2020). REALME: An Approach for Handwritten Signature Verification based on Smart Wrist Sensor. 2020 IEEE 23rd International Multitopic Conference (INMIC), Bahawalpur, Pakistan, 2020, pp. 1-6, doi: 10.1109/INMIC50486.2020.9318184.

[3] Wehbi, M., Luge, D., Hamann, T., Barth, J., Kaempf, P., Zanca, D., & Eskofier, B. M. (2022). Surface-free multi-stroke trajectory reconstruction and word recognition using an imu-enhanced digital pen. Sensors, 22(14), 5347.

[4] Subedi, D., Chitrakar, D., Yung, I., Zhu, Y., Su, Y. -H., & Huang, K. (2023). Biometric Signature Authentication with Low Cost Embedded Stylus. 2023 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), Seattle, WA, USA, 2023, pp. 834-839, doi: 10.1109/AIM46323.2023.10196285.

[5] Li, G., Zhang, L., & Sato, H. (2021). In-air Signature Authentication Using Smartwatch Motion Sensors. 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), Madrid, Spain, 2021, pp. 386-395, doi: 10.1109/COMPSAC51774.2021.00061.

[6] Gupta, R., Chaudhary, S., Vedant, A., Choudhury, N. P., & Ladwani, V. (2022). Gesture Detection Using Accelerometer and Gyroscope. In Emerging Research in Computing, Information, Communication and Applications: Proceedings of ERCICA 2022 (pp. 99-116). Singapore: Springer Nature Singapore.

[7] Brockly, M., Guest, R., Elliott, S., & Scott, J. (2011). Dynamic signature verification and the human biometric sensor interaction model. 2011 Carnahan Conference on Security Technology, Barcelona, Spain, 2011, pp. 1-6, doi: 10.1109/CCST.2011.6095937.

[8] Deselaers, T., Keysers, D., Hosang, J., & Rowley, H. A. (2015). GyroPen: Gyroscopes for Pen-Input With Mobile Phones. IEEE Transactions on Human-Machine Systems, 45(2), 263-271, April 2015, doi: 10.1109/THMS.2014.2365723.

[9] Schrapel, M., Grannemann, D., & Rohs, M. (2022). Sign H3re: Symbol and X-Mark Writer Identification Using Audio and Motion Data from a Digital Pen. In Proceedings of Mensch und Computer 2022 (pp. 209- 218).