i-RM: An intelligent risk management framework for context-aware ubiquitous cold chain logistics

• We suggest an intelligent risk management framework for ubiquitous cold chain logistics.
• The framework supports context-aware real-time risk management based on ontologies.
• Rules for the risk management are defined and dynamically linked for handling risks at run time.
• A prototype system was implemented to illustrate the framework for ubiquitous cold chain logistics.

Owing to the increasing interest in food quality in terms of freshness, a special type of logistics, called ubiquitous cold chain logistics (UCCL), has become an essential part of the distribution of environmentally sensitive items. UCCL aims to guarantee that delivery items are held under proper environmental conditions. By incorporating ubiquitous technologies such as radio frequency identification (RFID) tags and various types of sensors, monitoring and tracking environmental conditions for delivery items in UCCL have been easily achievable without latency. Nevertheless, addressing the complex nature of risk management rules caused by a large number of possible risk cases in UCCL has not yet been fully developed. Therefore, in this research, we suggest an intelligent risk management framework for UCCL, namely i-RM, which is designed to accommodate various types of risk situations by introducing the notion of context-aware real-time risk management. More specifically, i-RM takes a divide-and-combine approach where rules for risk management functions, context identification, risk detection, and response action judgment are defined in semantic ontologies. While rules for the risk management functions are defined independently of the others, they are dynamically linked for handling risks during run time. Moreover, i-RM is fully responsible for all of the risk management tasks required in UCCL, from information acquisition to responses in real time, by adopting event-based processing techniques. The effectiveness of the risk management ability of i-RM is demonstrated based on a real-world UCCL scenario.