PMID- 32297518
OWN - NLM
STAT- MEDLINE
DCOM- 20210709
LR  - 20210709
IS  - 1943-3530 (Electronic)
IS  - 0003-7028 (Linking)
VI  - 74
IP  - 9
DP  - 2020 Sep
TI  - Application of a Hybrid Fusion Classification Process for Identification of 
      Microplastics Based on Fourier Transform Infrared Spectroscopy.
PG  - 1167-1183
LID - 10.1177/0003702820923993 [doi]
AB  - Microplastic research is an emerging field. Consistent accurate identification of 
      microplastic polymer composition is vital for understanding the effect of 
      microplastic pollution in the environment. Fourier transform infrared (FT-IR) 
      spectroscopy is becoming commonplace for identifying microplastics. Conventional 
      spectral identification is based on library searching, a process that utilizes a 
      search algorithm against digital databases containing single spectra of pristine 
      reference plastics. Several conditions on environmental microplastic particles 
      such as weathering, additives, and residues cause spectral alterations relative 
      to pristine reference library spectra. Thus, library searching is vulnerable to 
      misidentification of microplastic samples. While a classification process 
      (classifier) based on a collection of spectra can alleviate misidentification 
      problems, optimization of each classifier (tuning parameter) is required. 
      Additionally, erratic results relative to the particular optimized tuning 
      parameter can occur when microplastic samples originate from new environmental or 
      biological conditions than those defining the class. Presented in this study is a 
      process that utilizes spectroscopic measurements in a hybrid fusion algorithm 
      that depending on the user preference, simultaneously combines high-level fusion 
      with low- and mid-level fusion based on an ensemble of non-optimized classifiers 
      to assign microplastic samples into specific plastic categories (classes). The 
      approach is demonstrated with 17 classifiers using FT-IR for binary 
      classification of polyethylene terephthalate (PET) and high-density polyethylene 
      (HDPE) microplastic samples from environmental sources. Other microplastic types 
      are evaluated for non-class PET and HDPE membership. Results show that high 
      accuracy, sensitivity, and specificity are obtained thereby reducing the risk of 
      misidentifying microplastics.
FAU - Chabuka, Beauty K
AU  - Chabuka BK
AD  - Department of Chemistry, 6640Idaho State University, Pocatello, USA.
FAU - Kalivas, John H
AU  - Kalivas JH
AUID- ORCID: 0000-0001-7056-976X
AD  - Department of Chemistry, 6640Idaho State University, Pocatello, USA.
LA  - eng
PT  - Journal Article
DEP - 20200601
PL  - United States
TA  - Appl Spectrosc
JT  - Applied spectroscopy
JID - 0372406
RN  - 0 (Environmental Pollutants)
RN  - 0 (Microplastics)
RN  - 0 (Polyethylene Terephthalates)
RN  - 9002-88-4 (Polyethylene)
SB  - IM
MH  - Environmental Monitoring/*methods
MH  - *Environmental Pollutants/analysis/classification
MH  - *Microplastics/analysis/classification
MH  - *Polyethylene/analysis/classification
MH  - *Polyethylene Terephthalates/analysis/classification
MH  - Spectroscopy, Fourier Transform Infrared
OTO - NOTNLM
OT  - FT-IR
OT  - Fourier transform infrared spectroscopy
OT  - Microplastic
OT  - classification
OT  - classification maintenance
OT  - data fusion
OT  - transfer learning
EDAT- 2020/04/17 06:00
MHDA- 2021/07/10 06:00
CRDT- 2020/04/17 06:00
PHST- 2020/04/17 06:00 [pubmed]
PHST- 2021/07/10 06:00 [medline]
PHST- 2020/04/17 06:00 [entrez]
AID - 10.1177/0003702820923993 [doi]
PST - ppublish
SO  - Appl Spectrosc. 2020 Sep;74(9):1167-1183. doi: 10.1177/0003702820923993. Epub 
      2020 Jun 1.