Yuji WATANABE
- Division
- Mathematical and Material Science, Professor
- Academic Degree
- Ph.D. (Engineering)
| Research Field | Intelligent Informatics, Information Security |
|---|---|
| Keywords | Artificial Intelligence, Machine Learning, Security, Biometrics Authentication, Sensor Networks, Programming Education |
| Current Research Topics | (1) Behavior-based Biometrics Authentication on Mobile Device: We develop a behavior-based biometrics authentication system to continuously monitor user operations and behaviors in the background under various circumstances using multiple sensors built into mobile device such as smart phone. (2) Construction of Ambient Sensor Network And Motion Estimation Using Machine Learning: Using an ambient sensor network consisting of sensors installed in clothes, bed, treatment equipment, etc. and mobile devices, we apply machine learning including deep learning to the subject's motion data to estimate the subject's motion and state. (3) Teaching Support Using Machine Learning in Primary Programming Education: In elementary programming classes, we aim to create a programming education support system that accumulates the source code and the operation history of learners, systemizes teaching methods by machine learning, and presents the teaching methods to elementary, junior high and high school teachers. |
| Selected Publications | GI-SleepNet: A Highly Versatile Image-Based Sleep Classification Using a Deep Learning Algorithm, Clocks & Sleep, Vol.3, No.4, pp.581-597 (2021). Gait identification and authentication using LSTM based on 3-axis accelerations of smartphone, Procedia Computer Science, Vol.176, pp.3873-3880 (2020). Identification and features selection of elderly people based on accelerations of smartphone, Procedia Computer Science, Vol.159, pp.2629-2638 (2019). Long-term influence of user identification based on touch operation on smart phone, Procedia Computer Science, Vol.112, pp.2529-2536 (2017). Toward an Immunity-based Gait Recognition on Smart Phone: A Study of Feature Selection and Walking State Classification, Procedia Computer Science, Vol.96, pp.1790-1800 (2016). Toward Application of Immunity-based Model to Gait Recognition Using Smart Phone Sensors: A Study of Various Walking States, Procedia Computer Science, Vol.60, pp.1856-1864 (2015). Influence of Holding Smart Phone for Acceleration-based Gait Authentication, Proc. of IEEE 2014 International Conference on Emerging Security Technologies (EST), pp.30-33 (2014). Analogy between Immune System and Sensor Replacement Using Mobile Robots on Wireless Sensor Networks, Procedia Computer Science, Vol.35, pp.1352-1359 (2014). Development of Android Application for Touch Screen-Based Authentication, International Workshop on Smart Info-Media Systems in Asia (SISA), pp.376-379 (2013). A Study of Accelerometer-based Authentication on Walking with Smart Phone, International Workshop on Smart Info-Media Systems in Asia (SISA), pp.372-375 (2013). Toward Introduction of Immunity-based Model to Continuous Behavior-based User Authentication on Smart Phone, Procedia Computer Science, Vol.22, pp.1319-1327 (2013). |