Alarm notification of body sensors utilising activity recognition and smart device application: Dealing with diversity in the wild

Smart device and body sensors have become innovative and converged with health informatics. To reduce the battery power consumption and bandwidth usage in wireless body area networks, it is proposed to infer sensed data in sensor nodes, which can raise an alarm when the user is in an urgent situation by analysing the sensed data against the user's activity status utilising accelerometer sensors. However when the activity changes frequently, there may be an increase in false alarms which increases sensing and transferring of data resulting in higher resource consumption. To reduce and mitigate the problem, we propose to verify the alarm using a smart device or smartwatch application so that a user can respond to whether the alarm is true or false, and thus provide feedback to the system to improve activity recognition. This paper presents a user-feedback system for use in activity recognition to mitigate and improve possible false alarm situations, which will consequently result in helping sensors to reduce the frequency of transactions and transmissions in wireless body area networks.