PMID- 31251256
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20190701
IS  - 1539-4522 (Electronic)
IS  - 1559-128X (Linking)
VI  - 58
IP  - 16
DP  - 2019 Jun 1
TI  - On-site visualized classification of transparent hazards and noxious substances 
      on a water surface by multispectral techniques.
PG  - 4458-4466
LID - 10.1364/AO.58.004458 [doi]
AB  - This paper investigated the use of spectra and multispectral images for on-site 
      visualized classification of transparent hazards and noxious substances (HNS), 
      such as benzene, xylene, and palm oil, floating on a water surface with the 
      potential use for rapid classification of multiple HNS during a leak accident. 
      Partial least-squares discrimination analysis (PLS-DA) and least-squares support 
      vector machine (LS-SVM) models achieved a classification accuracy of 100% for 
      spectral reflectance (325-900 nm) and multispectral image at nine wavelengths. 
      Wavelength division and selection were applied for spectra and spectral images, 
      respectively, to reduce the difficulty in data collection and to simplify the 
      redundant bands. This was followed by PLS-DA and LS-SVM modeling. The LS-SVM 
      model based on the least wavelengths (365, 410, 450, and 850 nm) of multispectral 
      images was suggested as the most effective method for on-site visualized 
      classification of transparent HNS on a water surface.
FAU - Huang, Haocai
AU  - Huang H
FAU - Liu, Shuchang
AU  - Liu S
FAU - Wang, Chao
AU  - Wang C
FAU - Xia, Kaibo
AU  - Xia K
FAU - Zhang, Dejun
AU  - Zhang D
FAU - Wang, Hangzhou
AU  - Wang H
FAU - Zhan, Shuyue
AU  - Zhan S
FAU - Huang, Hui
AU  - Huang H
FAU - He, Shuangyan
AU  - He S
FAU - Liu, Caicai
AU  - Liu C
FAU - Li, Xiaorun
AU  - Li X
LA  - eng
PT  - Journal Article
PL  - United States
TA  - Appl Opt
JT  - Applied optics
JID - 0247660
EDAT- 2019/06/30 06:00
MHDA- 2019/06/30 06:01
CRDT- 2019/06/29 06:00
PHST- 2019/06/29 06:00 [entrez]
PHST- 2019/06/30 06:00 [pubmed]
PHST- 2019/06/30 06:01 [medline]
AID - 413128 [pii]
AID - 10.1364/AO.58.004458 [doi]
PST - ppublish
SO  - Appl Opt. 2019 Jun 1;58(16):4458-4466. doi: 10.1364/AO.58.004458.