FAKE DRUG DETECTION USING DEEP LEARNING

This research presents a deep learning-based approach to counterfeit drug detection, focusing on the use of QR code technology to verify the authenticity of pharmaceutical products. Counterfeit drugs pose significant threats to public health, causing adverse effects and even fatalities. Existing methods for detecting counterfeit drugs often rely on physical inspection and chemical analysis, which can be time-consuming and prone to human error. This study aims to develop a more efficient and reliable system using deep learning, specifically a Gated Recurrent Unit (GRU) architecture, to distinguish genuine drugs from counterfeit ones. A synthetic dataset was created to simulate various pharmaceutical products, including information such as drug names, manufacturers, batch numbers etc. The dataset was preprocessed to encode categorical variables and scale numerical features, ensuring compatibility with the GRU model. The model was trained and tested on this dataset, achieving an accuracy of 96%, demonstrating its effectiveness in identifying counterfeit drugs. The proposed system offers a significant improvement over traditional methods, providing a fast, accurate, and automated solution for drug verification. The research concludes that deep learning, specifically the GRU architecture, is a promising tool for counterfeit drug detection. Future work should focus on expanding the dataset with real-world data, and integrating the system with broader healthcare infrastructures to maximize its impact and utility.