Monitoring Patients' Lifestyle with a Smartphone and Other Devices Placed Freely on the Body

Monitoring patients’ lifestyle can result in an improved treatment, but it is often not critical enough to warrant dedicated sensors. However, many consumer devices, such as smartphones, contain inertial sensors, which can be used for such monitoring. We propose an approach to activity recognition and human energy-expenditure estimation for diabetes patients that uses a phone and an accelerometer-equipped heart-rate monitor. The approach detects which of the two devices is carried or worn, the orientation of the phone and its location on the body, and adapts the monitoring accordingly. By using this approach, the accuracy of the activity recognition was increased by up to 20 percentage points compared to disregarding the orientation and location of the phone, while the error of the energy-expenditure estimation was decreased.