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.