Enhancing Pharmaceutical Supply Chains with Densenet-121 and 1D CNN Integration

The efficient distribution of medicines is vital for effective healthcare delivery, yet it faces numerous challenges including unpredictability, instability, and a lack of accountability within supply chains. Healthcare system today encounters distinct difficulties including outsourcing complexity, transportation issue, bottlenecks due to unexpectedly high demand, growing consumer expectation, and intricate operational process. To address these challenges, there is a growing interest in leveraging computational approaches, especially machine learning (ML) and deep learning (DL) techniques, to enhance supply chain management. The proposed research employs a hybrid model that combines DenseNet-121, a deep convolutional neural network (DCNN) known for its efficient feature extraction capability, with a one-dimensional CNN (1D CNN) tailored for sequential data analysis. This combination leverages the strengths of both architectures to enhance the model's performance in classifying supply chain health medication datasets. The study utilizes the "Supply Chain Shipment Pricing Data" dataset from Kaggle, which provides comprehensive information on health commodity shipments and pricing. The evaluation of the model reveals that it attained an accuracy of 96.01%, a precision of 96.13%, a recall of 96.23%, and an f1-score of 96.17%. The high accuracy and balanced performance metrics underscore the model's potential to enhance predictive accuracy and operational efficiency in health medication distribution, addressing the challenges currently faced in supply chain management.