Unstructured play 1 is considered important for the social, physical and cognitive development of children. Traditional observational research examining play behaviour at playtime (recess) has been hampered by challenges in obtaining reliable data and in processing sufficient quantities of that data to permit credible inferences to be drawn. The emergence of wearable wireless sensor technology makes it possible to study individual differences in childhood social behaviour based on collective movement patterns during playtime. In this work, we introduce a new method to enable simultaneous collection of GNSS/IMU data from a group of children interacting on a playground. We present a detailed description of system development and implementation before going on to explore methods of characterising social groups based on collective movement recording and analysis. A case study was carried out for a class of 7-8 year old children in their school playground during 10 episodes of unstructured play. A further 10 play episodes were monitored in the same space following the introduction of large, loose play materials. This study design allowed us to observe the effect of an environmental intervention on social movement patterns. Sociometric analysis was conducted for comparison and validation. This successful case study demonstrates that sensor based movement data can be used to explore children's social behaviour during naturalistic play.

Unstructured play is considered important for the social, physical and cognitive development of children. Traditional observational research examining play behaviour at playtime (recess) has been hampered by challenges in obtaining reliable data and in processing sufficient quantities of that data to permit credible inferences to be drawn. The emergence of wearable wireless sensor technology makes it possible to study individual differences in childhood social behaviour based on collective movement patterns during playtime. In this work, we introduce a new method to enable simultaneous collection of GNSS/IMU data from a group of children interacting on a playground. We present a detailed description of system development and implementation before going on to explore methods of characterising social groups based on collective movement recording and analysis. A case study was carried out for a class of 7-8 year old children in their school playground during 10 episodes of unstructured play. A further 10 play episodes were monitored in the same space following the introduction of large, loose play materials. This experimental design allowed us to study the effect of an environmental intervention on social movement patterns. Sociometric analysis was conducted for comparison and validation. This successful case study demonstrates that sensor based movement data can be used to explore children’s social behaviour during naturalistic play.

As part of the Accessible Routes from Crowdsourced Cloud Services project (ARCCS) we conducted a series of experiments using the ARCCS sensor to identify push style of wheelchair users. The aim of ARCCS is to make use of a set of well-calibrated sensors to establish a processing chain that then provides ground truth of known accuracy about location, the nature of the environment, and physiological effort. In this paper we focus on two classification problems 1) The push style employed by people as they push themselves and 2) Whether the person is being pushed by an attendant or pushing themselves (independent of push style). Solving the first enables us to develop a level of granularity to pushing classification which transcends rehabilitation and accessibility. The first problem was solved using a wrist-mounted ARCCS sensor, and the second using a wheel-mounted ARCCS sensor. Push styles were classified between semi-circular and arc styles in both indoor and outdoor environments with a high-decrees of precision and recall (>95%). The ARCCS sensor also proved capable of discerning attendant from self-propulsion with near perfect accuracy and recall, without the need for a body-worn sensor.

No abstract

These days smart phones have changed the concept of mobile platform. Due to rapid growth in affordability, increased sensory and computational power has opened the ways for some interesting applications like activity recognition, gaming, navigation/tracking, augmented reality etc. In all these applications orientation of mobile phone is very important, once we know the correct orientation of the device, it becomes easy to develop such applications. Orientation can be determined by sensor fusion of accelerometer and magnetometer but it provides good accuracy as long as device is stationary or not moving linearly and also it suffers from surrounding magnetic interference. Orientation estimation systems often use gyroscope to increase reliability and accuracy. Although gyroscopes provide a quick response to change in angles and do not have problems like interference, they suffer from bias and integration errors which introduce drift in signal. In this paper an efficient and less complicated approach is utilized which minimizes the drift and noise in output orientation. In most of smart phone navigation applications these days, it is assumed that mobile is at fixed position like holding in hand facing forward, in trouser/jacket pocket or attached to waist. But if we assume that mobile position is changing arbitrary then situation becomes complicated. The goal of this work is to find accurately the direction of movement of a pedestrian while holding mobile in any position. In this work an accelerometer based approach is presented for pedestrian direction of movement estimation.

Essentially, our lives are made of social interactions. These can be recorded through personal gadgets as well as sensors adequately attached to people for research purposes. In particular, such sensors may record real time location of people. This location data can then be used to infer interactions, which may be translated into behavioural patterns. In this paper, we focus on the automatic discovery of exceptional social behaviour from spatio-temporal data. For that, we propose a method for Exceptional Behaviour Discovery (EBD). The proposed method combines Subgroup Discovery and Network Science techniques for finding social behaviour that deviates from the norm. In particular, it transforms movement and demographic data into attributed social interaction networks, and returns descriptive subgroups. We applied the proposed method on two real datasets containing location data from children playing in the school playground. Our results indicate that this is a valid approach which is able to obtain meaningful knowledge from the data.

1 This paper reports an exploratory case-study introducing a new method to quantify 2 children's social interactions during unstructured outdoor play. Movements of 18 3 children were tracked using wearable sensors over 20 sessions of outdoor play at 4 school. Sessions were divided between two play conditions: Baseline; the usual play 5 environment and Intervention; in which a playground intervention was implemented. 6 Sensor data were used to build a network representing the social interactions that took 7 place each day. Questionnaire-based measures of social and communication skills were 8 completed by teachers, and peer nomination was used as a child-based measure of 9 social skills.

No abstract