Location-Aware Context Detection Based-On Behavior Sensors

Sensor-based physical activity detection has become increasingly popular in recent years due to the development of internet-of-things and smart sensing technologies, and a large number of studies have been done in this area. Accurately identifying human activity in the wild and the surrounding environments, however, is still a scientific challenge that has to be solved. This study introduces a novel Location Aware Context Detection (LACD) strategy that uses physical activity detection to infer user situations in the wild and explicitly learns human activity patterns in a variety of behavioral contexts. This component links 225 sensor features, and 51 context-labeled distinct behavioral situations, including phone locations, to everyday life activities eg. sleeping, cooking, shopping, cleaning, singing, talking, cleaning, etc. A number of machine learning classifiers are employed to assess the suggested method using a public domain dataset, namely ExtraSensory. The Random Forest classifier proves the effectiveness of the suggested strategy by achieving an identification rate of 88.4%.