Utilization of mobile phone sensors for complex human activity recognition

Abstract

Activity recognition is a significant part of pervasive computing as it can be employed in a wide range of fields which include eldercare and healthcare. While previous efforts have proven to be successful in identifying simple human activities, the means for identifying complex human activities remains an on-going effort. It has been established that more often than not, in an actual circumstance, human activities are conducted in an intricate mode. The objectives of this study are (a) to examine the utilization of solely the sensors of a mobile phone to distinguish complex human activities and (b) to enhance the complex activities recognition capacity of mobile phones through the application of multiple or other forms of sensors. This endeavour reassesses earlier studies on mobile phone utilization for complex activity recognition with the emphasis on schemes directed at smart home applications. An overall configuration for a human activity recognition (HAR) scheme, as well as an analysis of the latest investigations related to the use of mobile phones for complex activity recognition is also included in this paper. We conclude with a discussion on the results obtained and the forwarding of our proposals.