Artificial Intelligence Techniques for IoT-Based Smart Pharmacies for Optimizing Stock Management with Siamese Heterogeneous Convolutional Neural Networks: Trends and Challenges

Abstract

The increasing demand for efficient pharmaceutical supply chain management has led to the adoption of Artificial Intelligence (AI) and Internet of Things (IoT) technologies in smart pharmacy systems. Traditional pharmacy inventory management often suffers from issues such as drug shortages, overstocking, and medication wastage due to limited forecasting capabilities and manual monitoring processes. AI-driven systems integrated with IoT sensors enable real-time monitoring of pharmaceutical inventory and predictive demand analysis, allowing pharmacies to maintain optimal stock levels. Recent advances in deep learning, particularly Siamese Heterogeneous Convolutional Neural Networks (SH-CNN), provide powerful tools for analyzing heterogeneous pharmacy data and identifying patterns in drug consumption trends. This review examines recent developments in recent years in AI-based IoT smart pharmacy systems for optimizing stock management. The study highlights key technologies, research trends, and challenges associated with implementing intelligent pharmacy systems. The findings suggest that integrating AI, IoT, and deep learning architectures can significantly improve inventory accuracy, reduce medication waste, and enhance pharmacy supply chain efficiency, while challenges related to data security, system integration, and scalability remain important areas for future research.