Machine learning for pattern and waveform recognitions in terahertz image data

Dmitry S Bulgarevich,Miezel Talara,Makoto Watanabe,Masahiko Tani

doi:10.1038/s41598-020-80761-9

Dmitry S Bulgarevich, Miezel Talara + Show 2 more

Open Access

https://doi.org/10.1038/s41598-020-80761-9

Copy DOI

Abstract

Several machine learning (ML) techniques were tested for the feasibility of performing automated pattern and waveform recognitions of terahertz time-domain spectroscopy datasets. Out of all the ML techniques under test, it was observed that random forest statistical algorithm works well with the THz datasets in both the frequency and time domains. With such ML algorithm, a classifier can be created with less than 1% out-of-bag error for segmentation of rusted and non-rusted sample regions of the image datasets in frequency domain. The degree of linear correlation between the rusted area percentage and the image spatial resolution with terahertz frequency can be used as an additional cross-validation criteria for the evaluation of classifier quality. However, for different rust staging measured datasets, a standardized procedure of image pre-processing is necessary to create/apply a single classifier and its usage is only limited to 1 ± 0.2 THz. Moreover, random forest is practically the best choice among the several popular ML techniques under test for waveform recognition of time-domain data in terms of classification accuracy and timing. Our results demonstrate the usefulness of random forest and several other machine learning algorithms for terahertz hyperspectral pattern recognition.

Highlights

Several machine learning (ML) techniques were tested for the feasibility of performing automated pattern and waveform recognitions of terahertz time-domain spectroscopy datasets
K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Random Forest (RF) were compared in terms of total classification accuracy and recognition ability for the diagnosis of traumatic brain injury and results showed that RF was the best algorithm among the three algorithms under study[21]
We demonstrate the feasibility of pattern recognition in THz-TDS images of rusted steel with RF machine learning a lgorithm[32,33]

Summary

Introduction

Several machine learning (ML) techniques were tested for the feasibility of performing automated pattern and waveform recognitions of terahertz time-domain spectroscopy datasets. There is still very limited literature on the application of ML techniques in nondestructive testing (NDT) using pattern or waveform recognition in THz-TDS datasets. We demonstrate the feasibility of pattern recognition in THz-TDS images of rusted steel with RF machine learning a lgorithm[32,33].

Results

Conclusion