BIDS Innovate for Health Fellow Akram Bayat and a team of researchers under the supervision of Marc Pomplun at the University of Massachusetts Boston, have recently released Human Gait Data, a large human gait database conducted in real-world conditions, and suitable to be used by researchers using deep learning algorithms for various analysis applications in health, biometrics, education, etc.
The goal of this study was to introduce a comprehensive gait database of 100 human subjects who walked between two endpoints during two different sessions (200 walking sessions) and their gait data were recorded using two smartphones, one that was attached to their right thigh and another one was carried by a phone holder on the left side of their waist. The metadata including age, gender, smoking, daily exercise time, height, and weight of each individual was also recorded.
Read more about the team's initial research in this preprint article, Human Gait Database for Normal Walk Collected by Smart Phone Accelerometer, by Amir Vajdi, Mohammad Reza Zaghian, Saman Farahmand, Elham Rastegar, Kian Maroofi, Shaohua Jia, Marc Pomplun, Nurit Haspel, and Akram Bayat (arXiv, February 18, 2020).
