Blockchain Assisted Archimedes Optimization with Machine Learning Driven Drug Supply Management for Pharmaceutical Sector

Drug supply chain management (DSCM) is a vital procedure for pharmaceutical industries as it makes sure that medicines are delivered securely and effectively to patients. Effectual DSCM comprises the coordination and management of many key actions like warehousing, drug manufacturing, transportation, and distribution. For improving DSCM, pharmaceutical companies leverage technologies such as Blockchain (BC), Internet of Things (IoT), and artificial intelligence (AI) for enhancing traceability, increasing inventory management, and increasing communication and collaboration between stakeholders. Therefore, this study presents a Blockchain Assisted Archimedes Optimization with Machine Learning Driven Drug Supply Management (BAOML-DSM) technique for Pharmaceutical Sector. The presented BAOML-DSM technique focuses on the recommendation of drugs in the pharmaceutical sector. To accomplish this, the BAOML-DSM technique exploits the Hyperledger fabric for DSC management that allows to achieving of tracking procedures in the smart pharmaceutical industry. At the initial stage, preprocessing and Glove based word embedding process takes place. In addition, the gradient boosting decision tree (GBDT) model is employed and is applied for drug recommendation. Moreover, the Archimedes Optimization Algorithm (AOA) is employed for the hyperparameter tuning process which helps in optimal parameter tuning of the GBDT model. The experimental result analysis of the presented BAOML-DSM algorithm takes place using a benchmark dataset. The comprehensive results of the BAOML-DSM technique ensured the improved performance of the BAOML-DSM technique in terms of several metrics.