Blockchain based Lebesgue interpolated Gaussian secured information sharing for pharma supply chain

Abstract

Supervising the product's integrity and procedures in a multi-participant supply chain environment is a noteworthy issue. In recent years blockchain technology (BT) has made an appearance as a paramount model, as it bestows secure tracking, benchmark, and trust formation between stakeholders in a cost-efficient solution. To control the foregoing concerns, data analytics is indispensable on blockchain-based secure data and hence elevates the significance of surfacing technology Machine Learning (ML). The reliability of data and its distribution are very pivotal in ML to enhance the accuracy of results. In this paper, a blockchain-based secured information sharing method called Lebesgue IntegrableConsensus and Interpolated Gaussian Learning-based (LIC-IGL) authentication to provide pharmaceutical data integrity and security is proposed. The LIC-IGL method is split into two sections. First, validation of block is performed by applying the Lebesgue Integrable Consensus model. The second step involves the authentication process carried out by employing the Adaptive Support Vector Machine Authentication model via smart contracts. Finally, upon successful authentication, distinct products are provided between and within the blocks, therefore, ensuring secured pharmaceutical product sharing. The effectiveness of the proposed and existing methods is compared with certain parameters such as latency, authentication accuracy, and false positive rate with respect to distinct numbers of products. The results acquired from the experiments exhibit a superior execution of the proposed method upon comparison with the state-of-the-art blockchain-based authentication methods and it shows enhanced simulated results with good authentication accuracy, minimizing the latency and false positive rate.