Situ-Oracle: A Learning-Based Situation Analysis Servicing Framework for BIoT Systems

The emergence of blockchain technologies and the rapid growth of the Internet of Things (IoT) have brought blockchain-premised IoT (BIoT) systems into the focus of recent studies. The decentralized nature of blockchain enables data traceability, transparency, and immutability as complementary security features to the existing IoT systems. It has been applied to prevent malicious control or data leakages in traditional cloud-based, vendor-specific IoT use case scenarios. Nevertheless, as we gradually step towards the situation-aware IoT era, the lack of means to incorporate situation awareness with BIoT systems has limited the full potential of such integration. In this work, we propose a framework, Situ-Oracle, as an attempt to provide situation analysis as a service to BIoT systems. The framework utilizes a Recurrent Neural Network (RNN) based learning model to perform sensory-based situation analysis. We used smart home as an example to demonstrate the feasibility of the integration in bringing situation awareness to smart-contract-enabled IoT systems. Following that, system-wide performance evaluations were conducted over a physically constructed BIoT system, the results show that the proposed system achieves better situation analysis accuracy and network performance compared to a baseline system. Overall, the paper presents a promising approach for improving situation analysis in BIoT systems, with potential applications in various domains such as smart homes, healthcare, and industrial automation.