Implementing Machine Learning for the Identification and Classification of Compound and Mixtures in Portable Raman Instruments

• NCJ Number: 305218
• Journal: Chemical Physics Letters Volume: 787 Issue: 139283 Dated: January 2022
• Author(s): Travon Cooman; Tatiana Trejos; Aldo Romero; Luis E. Arroyo
• Date Published: January 2022
• Grant Number(s): 2019-DU-BX-0030
• Sponsoring Agency: National Institute of Justice (NIJ)
• Corporate Author: West Virginia University
• Publication Format: Article
• Publication Type: Research (Applied/Empirical)
• Language: English
• Country: United States of America

Annotation

This study explored machine learning algorithms to classify single compounds, binary, ternary, and quaternary mixtures by the compound name, and the compound’s class, using seized drugs and common diluents as a model.

Abstract

The accuracies were ≥ 93% for most pure, binary mixtures, and quaternary mixtures algorithms. Therefore, incorporating machine learning algorithms in portable instruments, can improve the detection of unknown substances with high accuracies. (Publisher abstract provided)