Low-cost spectrogram based counterfeit medicine detection

TL;DR

This paper introduces a low-cost spectrometer-based device utilizing machine learning models like SVM and CNN to detect contaminated medicines and food, offering an accessible solution for developing communities.

Contribution

The paper presents a novel, affordable spectrometer device combined with machine learning for rapid detection of contaminated substances, addressing cost and complexity issues of traditional methods.

Findings

High accuracy in identifying contaminated substances

Effective use of machine learning models on spectrum data

Low-cost device suitable for developing communities

Abstract

Contaminated substances such as counterfeit medication and food contami-nated with pesticide residue is a pandemic of utmost urgency. Spectroscopy and chromatography methods are often used but are expensive and complex and as such a need exists for a device that can be easily operated in developing commu-nities. We present a hacked visible spectrometer based contaminated substance detector using machine learning. The Support Vector Machine (SVM), Logistic Regression, linear Regression and Convolutional Neural Network (CNN) models have been implemented and are trained on the acquired spectrum data. Our results show that a lowcost method of identifying contaminated substances is achievable with very high accuracy.