We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
The Identification and Classification of Microplastics by FTIR Using Gaussian Mixture and Naive Bayes
Summary
Researchers developed a machine learning approach using Gaussian Mixture models and Naive Bayes classification to automate the identification and classification of microplastics from FTIR spectral data, addressing the challenge of variable-length spectral outputs. The method successfully standardized data preprocessing to equal-length inputs and achieved high classification accuracy, offering a tool to support and accelerate manual polymer identification.
Microplastics has become more widely discussed recently. Detecting microplastics can be done using Fourier Transform Infrared Spectroscopy (FTIR). The results provide an absorption band that must be translated into a polymer. However, these results have different sizes of data, varied data, and take a long time to translate if done manually. This can be solved using Gaussian Mixture and Naïve Bayes by modifying the preprocessing to create same-sized data. The results are preprocessing which succeed in equalizing the length of the data, having good performance in the means value which is likely the same as the reference and having high accuracy, also being able to be used as supporting data when manual matching is done.
Sign in to start a discussion.
More Papers Like This
Machine Learning Microplastic Characterisation Surpasses Human Performance and Uncovers Labelling Errors in Public FTIR Data
Researchers developed a machine learning system for automated FTIR-based microplastic characterization that surpassed human expert performance in classification accuracy and identified labeling errors in publicly available FTIR datasets. The system offers a faster, more consistent alternative to manual spectral analysis and highlights quality issues in existing reference databases used for microplastic identification.
An ensemble machine learning method for microplastics identification with FTIR spectrum
Researchers developed an ensemble machine learning method to automatically identify microplastics using Fourier transform infrared (FTIR) spectroscopy data. The approach combines multiple classification algorithms to improve accuracy over individual methods for detecting and categorizing microplastic particles. The study suggests this automated approach could help standardize and accelerate microplastic monitoring in marine environments.
A Comparative Study of Machine Learning and Deep Learning Models for Microplastic Classification using FTIR Spectra
Researchers compared machine learning and deep learning models for classifying microplastics using FTIR spectra, evaluating multiple algorithmic approaches against standardised spectral datasets. The study assessed classification accuracy and computational efficiency, identifying which model architectures best discriminate between polymer types in environmental microplastic samples.
FTIR-Based Microplastic Classification: A Comprehensive Study on Normalization and ML Techniques
Researchers tested machine learning and deep learning techniques for classifying six common types of microplastics using infrared spectroscopy data. They found that using broader spectral ranges and certain normalization techniques significantly improved classification accuracy. The study demonstrates that automated identification of microplastic types is feasible and could speed up environmental monitoring efforts.
Robust Automatic Identification of Microplastics in Environmental Samples Using FTIR Microscopy
Researchers developed a robust automated method for identifying microplastics in environmental samples using FTIR microscopy combined with machine learning-based spectral matching, improving the consistency and efficiency of microplastic identification compared to manual evaluation.