Identification the activities of daily living based on decision tree

The basic concept of smart environment is to be aware of the context information related to environmental and human behavioral changes, and to provide appropriate services accordingly. To obtain the context information, people often use video cameras, microphones, and other devices. These devices can obtain complex environmental data but they also need powerful equipment for handling the data. In addition, monitoring equipment will generate privacy issues. Users will generate sense of exclusion. In these devices, users generally dislike the graphic and audio monitoring equipment. We mainly collect user activity information through the most simple data quality of sensor. Due to amount of activity of human is difficult to make computers understand by natural language. On the other hand, activity vulnerable to external factors produce different variations. In order to effectively address these issues, we propose an activity to identify architecture based on fuzzy logic. This method using fuzzy logic deal with sensor data and using fuzzy decision trees identification of a user´s activities. According to the results of preliminary experiments, the system can identify 85.49% the daily activities.