부산대학교 도서관

The modernization of transportation has drastically adopted automated vehicles on the roads due to their prevailing benefits of eradicating human error and preventing road accidents. Nevertheless, the intelligent systems of autonomous vehicles can be prone to various faults that can bring concern to road authorities. Therefore, we have proposed a blockchain-based engine fault detection scheme in autonomous vehicles using machine learning (ML). The employed Interplanetary File System (IPFS) protocol with the blockchain ensures cost-efficient engine fault detection for autonomous vehicles. Further, the decentralized and transparent nature of the blockchain guarantees secure data transactions for the proposed scheme. Moreover, we have implemented a random forest (RF) model to predict engine fault detection in autonomous vehicles with improved accuracy compared to the other ML models. Finally, the performance evaluation of the proposed scheme is analyzed by considering various metrics, such as accuracy, precision, recall, F1 score, and log-loss.