Recognition based on wearable inertial sensors

Bachelor Thesis, Master Thesis

Smart environments require to recognize users and their activities in an effective and unobtrusive manner. In spite of the important advances in this area, most approaches are evaluated in very small datasets that hardly represent scenarios that can be considered fully realistic.

Goal

Devise and implement a machine learning approach to continuously identify users in indoor environments based on inertial sensors in a smart watch. The approach is expected to be empirically evaluated in a large dataset that corresponds as much as possible to realistic scenarios. The project includes the development of an app to collect inertial sensors data effectively and efficiently on a smart watch (specifically, apple Watch).

Requirements

  • Programming experience required
    • Python would be relevant
    • hands-on experience programming for iOS would also be relevant
  • Some hands-on experience in machine learning
  • Eagerness to learn and work hard