Recognizing social gestures with a wrist-worn smartband

Abstract

The ability to recognize social gestures opens the door for the development of enhanced pervasive computing applications that are responsive to users' social interactions. In this paper, we explore the feasibility of using a smartband for social gesture recognition. We apply logistic regression, a supervised machine learning technique, to accelerometer data collected in a study of 32 users performing 12 social gestures. Our experimental results show promise for recognizing social gestures with a smartband; our simple approach achieves an average accuracy of 86% for classification of social gestures.

HealthyOffice: Mood recognition at work using smartphones and wearable sensors

“…For instance, a smartwatch application has recently been proposed to automatically detect eating episodes and assist in monitoring an individual's diet [4]. Wrist-worn technology has further been used to detect selfharming activities [5], motion-based authentication [6] and recognizing social gestures [7]. Commercial smart wrist-bands are equipped with an increasing number of sensors including heart-rate monitors, skin temperature sensor and accelerometer; underpinning the motivation of this work to develop a mood recognition system on this basis.…”

Extraction of Information from Inertial Sensors to Aid Health Assessment

“…Knighten et al [71] used logistic regression to identify social gestures of humans using wrist-worn smart band. Masse et al [72] adopted logistic regression and inertial sensors to improve postural transition recognition mobility-impaired stroke patients.…”

Sitting is the new smoking: online complex human activity recognition with smartphones and wearables

“…Recently, smartwatches are also being used for the same purpose because they are also equipped with various sensors such as accelerometer and gyroscope. However, unlike smartphones, activity recognition using smartwatch sensors is relatively new [12,13,14,15,16]. Most of the research on human activity recognition using mobile phones and smartwatches is done offline in machine learning tools [17,18,19,20,21,22,12,13,14,15,16].…”

“…In some of these studies, the aim is to show that online recognizers can work on mobile phones considering the available resources, while in other studies, the aim is to develop an application where the activities of the users can be tracked, such as a mobile diary or a fitness tracker [4]. Unlike smartphones, most of the work using smartwatch sensors is still being done offline [12,13,14,15,16].…”

“…Activity recognition using smartwatch sensors is still relatively new, unlike smartphones. Most of the work using smartwatch sensors is still being done offline [12,13,14,15,16]. Recently, researchers have been moving towards online activity recognition in order to verify the offline results and to analyze the resource consumption of machine learning algorithms on mobile phones and other wearable devices such as smartwatches [7,53,67,57,58,59,60,61,147,148,149].…”