An Interactive Method for Detection of Process Activity Executions from IoT Data

The increasing number of IoT devices equipped with sensors and actuators pervading every domain everyday life allows for improved automated monitoring analysis processes executed in IoT-enabled environments. While sophisticated methods exist to detect specific types activities from low-level data, a general approach detecting activity executions that are part more complex business does not exist. Moreover, dedicated information systems orchestrate or monitor process available typical As consequence, the large corpus existing mining techniques check improve cannot be applied. In this work, we develop an interactive method guiding data goal higher-level executions. is derived following exploratory set smart factory. We propose steps, sensor-actuator-activity patterns, novel concept signatures applicable many domains. shows valuable early stages analyses build ground truth based on knowledge decisions analyst, which can used detection later stages.