Human Activity Recognition based on smart home environment and their applications, challenges

Abstract

Progress in technology aspect, Internet of Things (IoT) takes an obvious quantity in the development of smart applications in numerous area such as smart farming, smart grid, smart cities, smart industry, smart hospital, and so on. IoT is the method of emerging IoT applications and connected products that can be monitored, measured remotely in a given environment via external data sources and sensors, other related IoT enabled devices. Detection of human activity is a set of techniques that can be used in wide range of applications, including medical health care and smart home. With an advance development and commercialization of IoT enabled devices and crucial demands, human activity measuring the efficient states or health of individual in smart home-based environment has been a highly dynamic and important topic in recent years since its related to human life. Meanwhile, the intrinsic of human activities characteristic is considered by a high degree of ambiguity, and complexity, it's a gives a great challenge to design and develop a strong activity recognition model. The objectives of this article aim to exploit the applications of human activity recognition systems applications, challenges, and surveys their state of the art in smart home environment. We classify such smart home applications into vision based, sensor-based (wearable devices, object-tagged, dense sensing). Within these types, the applications are categorized according to the methodology, datasets, features, limitations used for identifying human behaviors. Finally, the article concludes with an evaluation of the existing approaches which, let to frame research problems and questions for future direction which, when applied to real-world scenarios.