[19p-E215-1~17] 4.5 Terahertz Photonics

▲ [19p-E215-12] Machine Learning Classifiers for Terahertz Waveform Recognition

〇Dmitry S Bulgarevich¹, Masahiro Kusano¹, Takashi Furuya², Jessica Afalla², Valynn Mag-usara², Masahiko Tani², Makoto Watanabe¹ (1.National Institute for Materials Science, 2.FIR Center of University of Fukui)

Keywords:THz application, machine learning

Several machine learning (ML) classifiers were tested to automate the analysis of time-domain terahertz spectroscopy (THz-TDS) imaging, which is inherently the hyperspectral technique with often large datasets having the sliced image data in frequency and time domains. Among the tested ML classifiers for THz waveform recognitions, the random forest one was the best choice in terms of overall accuracy, speed, robustness, and user-friendliness. Combining these and our previously reported results in frequency domain, such ML techniques could have a great potential for THz-TDS analytical and non-destructive testing (NDT) applications.