Search

Human behavior computing has received a lot of attention in many business domains to derive daily routines, such as company's regular operations and cultural activities, especially towards to the development of smart industries in the fourth industrial revolution. Using the recent technology such as adaptive sensor devices, human movement and activity can be detected and traced. Discovering daily routines from lifelog can assist the growth of individual and organizations but yet needs a reliable approach to produce a representative behavior model. Some conformance checking approaches have been developed to verify the conformity of a real log with a generated model. However, the existing conformance checking approach relies on the business process property which is less reliable to the human behavior. Accordingly, limited approaches attempt to assess the conformity between the discovered model and self-elicited behavior (lifelog). This study presents norm approaches to assess the deviation between model space and lifelog. Two approaches, approximate and aggregate norm, are proposed to evaluate the discovered (routine) model according to the respective lifelog and a particular person. In this study, the model has been derived using the concept of time-lapse embedded in the sequential rules. The result of the experiment using the two-norm approaches shows that the routine models have 99% characteristics compared with the lifelog. [ABSTRACT FROM AUTHOR]