Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

IR Frequency Region: Fingerprint Region

IR Frequency Region: Fingerprint Region

IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Evaluation of Six Cutting-edge Large Language Models in Answering a Set of Open-ended Questions in Dental Case Reports.

Journal of dentistry·2026

Same author

Extracellular polysaccharide-facilitated selenium nanoparticle assembly and metabolic reprogramming support efficient selenite biotransformation by ARTP-mutagenized Lactiplantibacillus plantarum Vse252.

Bioresource technology·2026

Same author

Emotion regulation abilities in social anxiety, binge drinking, and their co-occurrence among young adults: A scoping review.

Progress in neuro-psychopharmacology & biological psychiatry·2026

Same author

Hollow MnO<sub>2</sub> nanosystem for glioblastoma sono-immunotherapy based on blood-brain barrier crossing and oxygen supply strategy.

Journal of colloid and interface science·2026

Same author

Dietary intake, fatty acid in adipose tissue and cardio-metabolic health: cross-sectional study from the TwinsUK cohort.

Nutrition & diabetes·2026

Same author

Correction method for cloud temperature retrieval combining rotational Raman, vibrational Raman, and elastic scattering lidar channels.

Applied optics·2026

Same journal

Traffic-related air toxics and Parkinson's disease in California's Central Valley.

The Science of the total environment·2026

Same journal

Mercury biomagnification across food webs with varying non-native fish presence: Implications for native fish conservation in the Upper Colorado River Basin.

The Science of the total environment·2026

Same journal

Eleven-year study of N<sub>2</sub>O and CH<sub>4</sub> emissions from a grassland in Nasu, Japan: influence of synthetic fertilizer, farmyard manure, and grassland renovations.

The Science of the total environment·2026

Same journal

Understanding dynamics of agricultural runoff to Oslofjord: A causal loop modelling approach.

The Science of the total environment·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 24, 2025

Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis

Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis

Published on: December 16, 2016

FRDA: Fingerprint Region based Data Augmentation using explainable AI for FTIR based microplastics classification.

Xinyu Yan¹, Zhi Cao², Alan Murphy²

¹Software Research Institute, Technological University of the Shannon: Midlands, Ireland; Luoyang Institute of Science and Technology, China.

The Science of the Total Environment

|July 6, 2023

Summary

This summary is machine-generated.

Marine microplastic identification using machine learning is improved by a new data augmentation method. This technique addresses imbalanced datasets by focusing on key spectral regions, enhancing identification accuracy for aquatic pollution monitoring.

Keywords:

Data augmentation Data pre-processing Deep learning FTIR Machine learning Microplastic identification

More Related Videos

Separation and Identification of Conventional Microplastics from Farmland Soils

Separation and Identification of Conventional Microplastics from Farmland Soils

Published on: March 21, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Related Experiment Videos

Last Updated: Jul 24, 2025

Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis

Protocol for Microplastics Sampling on the Sea Surface and Sample Analysis

Published on: December 16, 2016

Separation and Identification of Conventional Microplastics from Farmland Soils

Separation and Identification of Conventional Microplastics from Farmland Soils

Published on: March 21, 2025

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

Area of Science:

Environmental Science
Analytical Chemistry
Data Science

Background:

Marine microplastic (MP) contamination poses significant risks to aquatic ecosystems and human health.
Machine learning (ML) models, particularly those using Attenuated Total Reflection Fourier Transform Infrared Spectroscopy (ATR-FTIR), are crucial for MP identification.
Imbalanced and insufficient sample data, especially for copolymers and mixtures, present a major challenge for training accurate ML models.

Purpose of the Study:

To address the challenge of imbalanced datasets in MP identification.
To improve the performance of ML models for MP identification through effective data augmentation.
To identify influential spectral regions for MP identification using Explainable Artificial Intelligence (XAI) and Gaussian Mixture Models (GMM).

Main Methods:

Utilized Explainable Artificial Intelligence (XAI) and Gaussian Mixture Models (GMM) to analyze ATR-FTIR spectra and identify key spectral regions for MP identification.
Developed a novel Fingerprint Region based Data Augmentation (FRDA) method to generate synthetic FTIR data based on identified spectral regions.
Supplemented existing MP datasets with newly generated data using the FRDA method.

Main Results:

The FRDA method effectively generated new FTIR data, augmenting imbalanced MP datasets.
Analysis using XAI and GMM revealed specific spectral regions crucial for differentiating MP types.
Evaluation demonstrated that FRDA significantly outperformed existing spectral data augmentation techniques in improving ML model performance.

Conclusions:

The proposed FRDA method is an effective approach for augmenting MP datasets, particularly in addressing sample imbalance and complexity.
Identifying and utilizing fingerprint spectral regions enhances the accuracy of ML-based MP identification.
This work provides a valuable tool for improving the analysis and monitoring of marine microplastic pollution.