Objectives: Recognising human activity is very useful for an investigator about a patient's behaviour and can aid in prescribing activity in future recommendations. The use of body worn accelerometers has been demonstrated to be an accurate measure of human activity, however research looking at the use of multiple body worn accelerometers in a free living environment to recognise a wide range of activities is not evident. This study aimed to successfully recognise activity and subcategory activity types through the use of multiple body worn accelerometers in a free living environment. Method: Ten participants (Age = 23.1 ± 1.7 years, height =171.0 ± 4.7 cm, mass = 78.2 ± 12.5 Kg) wore nine body-worn accelerometers for a day of free living. Activity type was identified through the use of a wearable camera, and sub category activities were quantified through a combination of freeliving and controlled testing. A variety of machine learning techniques consisting of pre-processing algorithms, feature and classifier selections were tested, accuracy and computing time were reported. Results: A fine k-nearest neighbour classifier with mean and standard deviation features of unfiltered data reported a recognition accuracy of 97.6%. Controlled and free-living testing provided highly accurate recognition for sub-category activities (>95.0%). Decision tree classifiers and maximum features demonstrated to have the lowest computing time. Conclusions: Results show recognition of activity and subcategory activity types is possible in a free living environment through the use of multiple body worn accelerometers. This method can aid in prescribing recommendations for activity and sedentary periods for healthy living.

Wearable devices are a popular training tool to measure biomechanical performance indicators during running, including vertical oscillation (VO). VO is a contributing factor in running economy and injury risk, therefore VO feedback can have a positive impact on running performance. The validity and reliability of the VO measurements from wearable devices is crucial for them to be an effective training tool. The aims of this study were to test the validity and reliability of VO measurements from wearable devices against video analysis of a single trunk marker. Four wearable devices were compared: the INCUS NOVA, Garmin Heart Rate Monitor-Pro (HRM), Garmin Running Dynamics Pod (RDP), and Stryd Running Power Meter Footpod (Footpod). Fifteen participants completed treadmill running at five different self-selected speeds for one minute at each speed. Each speed interval was completed twice. VO was recorded simultaneously by video and the wearables devices. There was significant effect of measurement method on VO (p < 0.001), with the NOVA and Footpod underestimating VO compared to video analysis, while the HRM and RDP overestimated. Although there were significant differences in the average VO values, all devices were significantly correlated with the video analysis (R > = 0.51, p < 0.001). Significant agreement between repeated VO measurements for all devices, revealed the devices to be reliable (ICC > = 0.948, p < 0.001). There was also significant agreement for VO measurements between each device and the video analysis (ICC > = 0.731, p < = 0.001), therefore validating the devices for VO measurement during running. These results demonstrate that wearable devices are valid and reliable tools to detect changes in VO during running. However, VO measurements varied significantly between the different wearables tested and this should be considered when comparing VO values between devices.

No abstract

No abstract