Determining similarity between business process models has recently gained interest in the business process management community. So far similarity was addressed separately either at semantic or structural aspect of process models. Also, most of the contributions that measure similarity of process models assume an ideal case when process models are enriched with semantics---a description of meaning of process model elements. However, in real life this results in a heavy human effort consuming pre-processing phase which is often not feasible. In this paper we propose an automated approach for querying a business process model repository for structurally and semantically relevant models. Similar to the search on the Internet, a user formulates a BPMN-Q query and as a result receives a list of process models ordered by relevance to the query. We provide a business process model search engine implementation for evaluation of the proposed approach.

In the last decade, technological advancements in the cyber-physical system have set the basis for real-time and context-aware services to ease human lives. The citizens, especially travelers, want to experience a safe, healthy, and timely journey to their destination. Smart and on-ground real-time traffic analysis helps authorities further improve decision-making to ensure safe and convenient traveling. In this paper, we proposed a transport-control model that exploits cyber-physical systems (CPS) and sensor-technology to continuously monitor and mine the big city data for smart decision-making. The system makes use of travel-time, traffic intensity, vehicle’s speed, and current road conditions to construct a weighted city graph representing the road network. Traditional graph algorithms with efficient implementation technologies are employed to respond to commuters’ and authorities’ needs in order to achieve a smart and optimum transportation system. To efficiently process the incoming big data streams, the proposed architecture uses the Apache GraphX tool with several parallel processing nodes, along with Spark and Hadoop that ultimately provide better performance against various state-of-the-art solutions. The system is thoroughly evaluated in terms of system throughput and processing time, revealing that the proposed system is efficient, robust, and scalable.