WEKO3
アイテム
Prediction of a single Gaussian shape of spectral line measured with low-dispersion spectrometer by using machine learning
https://repo.qst.go.jp/records/82838
https://repo.qst.go.jp/records/828380f32871f-8926-4869-9a6d-90776adb8cf4
Item type | 学術雑誌論文 / Journal Article(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2021-05-18 | |||||
タイトル | ||||||
タイトル | Prediction of a single Gaussian shape of spectral line measured with low-dispersion spectrometer by using machine learning | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
資源タイプ | journal article | |||||
アクセス権 | ||||||
アクセス権 | metadata only access | |||||
アクセス権URI | http://purl.org/coar/access_right/c_14cb | |||||
著者 |
Fumiyoshi, Kin
× Fumiyoshi, Kin× Tomohide, Nakano× Naoyuki, Oyama× Akihiro, Terakado× Takuma, Wakatsuki× Emi, Narita× Fumiyoshi, Kin× Tomohide, Nakano× Naoyuki, Oyama× Akihiro, Terakado× Takuma, Wakatsuki× Emi, Narita |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | We have developed a denoising autoencoder based neural network (NN) method to determine a spectral line intensity with an uncertainty lower than the uncertainty determined by fitting the spectral line. The NN method processes the measured raw spectral line shape, providing a single Gaussian shape based on the training dataset, which consists of synthetically prepared Doppler shift and broadening free spectral lines in the present work. It is found that the uncertainty reduction level significantly depends on the training dataset. Limitations originating from the training dataset are also discussed. | |||||
書誌情報 |
Review of Scientific Instruments 巻 92, 号 5, p. 053505, 発行日 2021-05 |
|||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 0034-6748 | |||||
DOI | ||||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1063/5.0039781 | |||||
関連サイト | ||||||
識別子タイプ | URI | |||||
関連識別子 | https://aip.scitation.org/doi/10.1063/5.0039781?af=R&feed=most-recent |