IMU Data Processing to Recognize Activities of Daily Living with Smart Headset

This thesis proposes a novel approach for the detection and recognition of humanmovements. Specically, Activities of Daily Living (ADL) such as standing up,sitting down and walking are tracked. In order to monitor human motion, a headsetprototype with a single Inertial Measurement Unit (IMU) with accelerometer, gyroscopeand magnetometer has been developed. Accurate estimation of orientationand velocity through computationally cheap IMU data processing allows a representativecharacterization of human behavior patterns in this case. Thanks to testsperformed among dierent subjects, results show that events are robustly detected89% of the cases and that activities are recognized with a success rate of 92%. Whatis more, adequate rejection of noisy movements has also been achieved 94% of thetime. Thus, an ecient and robust solution for human physical activity tracking ispresented