Abstract
Human activity recognition algorithms based on information obtained from wearable sensors are successfully applied in detecting many basic activities. Identified activities with time-stationary features are characterised inside a predefined temporal window by using different machine learning algorithms on extracted features from the measured data. Better accuracy, precision and recall levels could be achieved by combining the information from different sensors. However, detecting short and sporadic human movements, gestures and actions is still a challenging task. In this paper, a novel algorithm to detect human basic movements from wearable measured data is proposed and evaluated. The proposed algorithm is designed to minimise computational requirements while achieving acceptable accuracy levels based on characterising some particular points in the temporal series obtained from a single sensor. The underlying idea is that this algorithm would be implemented in the sensor device in order to pre-process the sensed data stream before sending the information to a central point combining the information from different sensors to improve accuracy levels. Intra- and inter-person validation is used for two particular cases: single step detection and fall detection and classification using a single tri-axial accelerometer. Relevant results for the above cases and pertinent conclusions are also presented.
Highlights
Human Activity Recognition (HAR) systems are already integrated into many of our daily routine activities [1]
In order to assess the inter-person validity, a different set of users and hardware devices is used for training and validation
A novel algorithm is presented to detect atomic human movements based on the stochastic properties of local maxima and minima of the sensed time series from a tri-axial accelerometer
Summary
Human Activity Recognition (HAR) systems are already integrated into many of our daily routine activities [1] Applications, such as Google Fit [2] or Apple Health [3], are able to detect some activities, such as walking and running, that are linked to health and fitness parameters. HAR-related applications are available either using the sensors embedded in smart phones or using wearable devices. Applications such as Lumo [4] are developed to provide a gentle vibration when a person slouches to remind them to sit or stand straight and correct their posture [5]. Using wearable sensors provides a non-intrusive, always available companion compared to vision-based systems [6]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have