Archimedes Optimization with Enhanced Deep Learning based Recommendation System for Drug Supply Chain Management

Recently,pharmaceutical corporations are confronting difficulties while tracking their products in the supply chain process, allowing counterfeiters to include their fake medicines into market. Counterfeit drugs were examined as a great challenge for pharmaceutical sector worldwide. Sentiment analysis can be used to analyse customer reviews of drugs to determine overall sentiment towards the drug. Positive reviews can indicate that a drug is effective and well-tolerated, while negative reviews may indicate potential side effects or lack of effectiveness. However, it’s important to note that sentiment analysis is a subfield of natural language processing which uses statistical and machine learning techniques to identify and extract subjective information from source materials. Therefore, this article introduces an Archimedes Optimization with Enhanced Deep Learning based Recommendation System (AOAEDL-RS) for Drug Supply Chain Management. The proposed AOAEDL-RS technique majorly examines the drug reviews for the recommendation of drugs. It follows a three stage process: preprocessing, classification, and parameter tuning. Firstly, the AOAEDL-RS technique performs preprocessing and word2vec embedding processes. Secondly, the context based BiLSTM-CNN (CBLSTM-CNN) model is applied for drug review classification and classification. Thirdly, the AOAEDL-RS technique uses AOA for the optimal hyperparameter tuning of CBLSTM-CNN method. The result analysis of the AOAEDL-RS technique is tested on drug reviews dataset and the outcomes show the improved outcomes of the AOAEDL-RS method.