Deep Learning for Smartwatch Based Continuous Authentication

Deep Learning for Smartwatch Based Continuous Authentication

Continuous Implicit authentication is a solution for privacy-sensitive mobile and IoT technologies. Physiological signals are strong candidates for implicit continuous authentication. Smartwatches can record multi-modal signals including galvanic skin response, photoplethysmogram, accelerometer and heart rate variability. The datasets gathered from daily life contains artifacts. Shallow machine learning models fails to operate successfully. Deep Learning algorithms, CNN and LSTMs can be used to improve these systems. You will apply state-of-the-art deep learning algorithms, develop novel multi-modal fusion system and expand the smartwatch dataset by conducting experiments including human subjects.

Project Advisor: 

Cem Ersoy

Project Status: 

Project Year: 

  • Spring

Contact us

Department of Computer Engineering, Boğaziçi University,
34342 Bebek, Istanbul, Turkey

  • Phone: +90 212 359 45 23/24
  • Fax: +90 212 2872461

Connect with us

We're on Social Networks. Follow us & get in touch.