Geometric property estimation based on raman spetra measurement using machine learning

Michael K. Jo, Umberto Ravaioli

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There have been many efforts to identify the relation between the geometric structure of carbon-nanomaterials and the intensity profile of Raman spectra. As a result, researchers have reported intensity profiles changing with the geometric properties of carbon-nanomaterials, i.e. the length of carbon nanotubes and the thickness of graphene. Based on these measured data, we constructed an autonomous framework that can deduce the geometric property from a Raman spectra pattern using a machine learning algorithm. In this work, we focus on the Raman peak shift recognition using principal component analysis (PCA) to identify the number of graphene layers and this framework can accelerate processes in both measurement and geometric property analysis.

Original languageEnglish (US)
Title of host publication2018 IEEE 13th Nanotechnology Materials and Devices Conference, NMDC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538610169
DOIs
StatePublished - Jan 8 2019
Event13th IEEE Nanotechnology Materials and Devices Conference, NMDC 2018 - Portland, United States
Duration: Oct 14 2018Oct 17 2018

Publication series

Name2018 IEEE 13th Nanotechnology Materials and Devices Conference, NMDC 2018

Conference

Conference13th IEEE Nanotechnology Materials and Devices Conference, NMDC 2018
Country/TerritoryUnited States
CityPortland
Period10/14/1810/17/18

Keywords

  • Few-Layer Graphene
  • Machine Learning
  • Pattern Recognition
  • Principal Component Analysis
  • Raman Spectra

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials
  • Surfaces, Coatings and Films
  • Instrumentation

Fingerprint

Dive into the research topics of 'Geometric property estimation based on raman spetra measurement using machine learning'. Together they form a unique fingerprint.

Cite this