Comparison of Autoencoder with NMF for Odor Component Exploration Using Mass Spectrometry

カテゴリ: 研究会(論文単位)

論文No: CHS18002

グループ名: 【E】センサ・マイクロマシン部門 ケミカルセンサ研究会

発行日: 2018/07/12

タイトル(英語): Comparison of Autoencoder with NMF for Odor Component Exploration Using Mass Spectrometry

著者名: Prasetyawan Dani(Tokyo Institute of Technology),Nakamoto Takamichi(Tokyo Institute of Technology)

著者名(英語): Dani Prasetyawan(Tokyo Institute of Technology),Takamichi Nakamoto(Tokyo Institute of Technology)

キーワード: NMF|Autoencoder|Odor Appriximation|Odor Component|Odor Reproduction|NMF|Autoencoder|Odor Appriximation|Odor Component|Odor Reproduction

要約(日本語): Non-negative Matrix Factorization (NMF) and Autencoder are used briefly on many fields to explore dimensionality reduction and classification. We describe performance of autoencoder and NMF with respective results in pursuing fewer as possible odor components to perform odor reproduction. Least-squares method was performed to approximate odor components.

要約(英語): Non-negative Matrix Factorization (NMF) and Autencoder are used briefly on many fields to explore dimensionality reduction and classification. We describe performance of autoencoder and NMF with respective results in pursuing fewer as possible odor components to perform odor reproduction. Least-squares method was performed to approximate odor components.

原稿種別: 英語

PDFファイルサイズ: 1,637 Kバイト