A Blockchain-Based Deep-Learning-Driven Architecture for Quality Routing in Wireless Sensor Networks

Over the past few years, great importance has been given to wireless sensor networks (WSNs) as they play a significant role in facilitating world with daily life services like healthcare, military, social products, etc. However, heterogeneous nature of WSNs makes them prone various attacks, which results low throughput, and high network delay energy consumption. In WSNs, routing is performed using different protocols low-energy adaptive clustering hierarchy (LEACH), gateway-based energy-aware multi-hop (HMGEAR), such protocols, some nodes may perform malicious activities. Therefore, four deep learning (DL) techniques real-time message content validation (RMCV) scheme based on blockchain are used proposed for detection (MNs). Moreover, analyse data WSN, DL models trained state-of-the-art dataset generated from LEACH, known WSN-DS 2016. The WSN contains three types nodes: nodes, cluster heads (CHs) base station (BS). CHs after aggregating received send it towards BS. Furthermore, overcome single point failure issue, decentralized deployed Additionally, MNs removed RMCV techniques. legitimate (LNs) registered proof-of-authority consensus protocol. protocol outperforms proof-of-work terms computational cost. Later, between LNs compared original LEACH HMGEAR protocols. show that accuracy GRU 97%, LSTM 96%, CNN 92% ANN 90%. Throughput, death first node computed DL, RMCV, HMGEAR, RMCV. Oyente formal security analysis designed smart contract. shows resilient against vulnerabilities.