A Blockchain based Drug Supply Management and Recommendation System using Enhanced Learning Scheme
K. Niranjana, P. Sankarshana, L. Priyadharshini, SLS Raajavinayaga Subaash, S. Jawahar, V Prabhakaran · 2024
Over the course of the past ten years, pharmaceutical businesses have been encountering challenges in tracing their goods throughout the supply chain process. This has made it possible for counterfeiters to introduce their counterfeit medications into the market. One of the most significant challenges that the pharmaceutical business faces all around the world is the problem of counterfeit pharmaceuticals. In recent times, the technology of blockchain has generated a significant amount of attention in the field of recommendation system study among academic individuals. For the purpose of developing a recommendation system that is both thorough and trustworthy, these records also commonly include encryption. Quite commonly, encryption keys are contained inside these documents. Furthermore, in order to provide an accurate recommender system, it is essential to have recommendation systems that are concerned with appropriate assessment measures. There have been several attempts made to address these difficulties using a variety of methodologies; yet, relatively few researchers have judged encryption to be successful, particularly in terms of protecting the data of subscribers. A number of academics, particularly those working in the field of recommendation systems, are developing a significant amount of interest in blockchain technology at the present time. In order to identify these shortcomings, the current study is to investigate the implementation of blockchain technology as a significant potential solution to improve the level of data safety in recommendation systems. A novel approach is presented in this work that is referred to as the Blockchain Powered Drug Recommendation Model (BPDRM). In order to evaluate the effectiveness of the suggested model, it is cross-validated with a traditional model that is known as Random Forest Classification (RFC). In addition to providing an overview of blockchain-based programmes that are now accessible within sectors, this research made a significant contribution to a more in-depth understanding of blockchain-based security measures for suggesting systems. The paper places an emphasis on and investigates crucial facts and information on the security procedures for recommendation networks that are dependent on blockchain technology. A greater rate of protected data is of interest to researchers, and they emphasize notable features that have been identified by an independent review process.