Intelligent computing provides efficient, real-time, and secure data analysis services for the Internet of Things (IoT). As the number of IoT devices increases, IoT generates massive, diverse, and multisourcing datasets that can be used to improve IoT services further. Models trained by intelligent computing from a single system or sensor are often not global, and sending all data directly to the computing platform wastes network bandwidth and may cause network congestion and even privacy leakage. To ensure IoT applications’ quality of service and privacy, we propose a framework that integrates edge computing and blockchain to provide lightweight data fusion and secure data analysis for IoT. We propose a lightweight data fusion method that can reduce the amount of data at the node level and prevent network congestion and bandwidth waste. Furthermore, we propose a hierarchical fuzzy hashing method to check and locate anomalies of IoT machine learning models to ensure the validity of IoT intelligent computing and the security of sensitive data. Finally, we demonstrate the effectiveness of the method proposed in this paper through experiments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.