Catalogo Articoli (Spogli Riviste)

OPAC HELP

Titolo:
Artificial intelligence methods for selection of an optimized sensor arrayfor identification of volatile organic compounds
Autore:
Polikar, R; Shinar, R; Udpa, L; Porter, MD;
Indirizzi:
Rowan Univ, Dept Elect & Comp Engn, Glassboro, NJ 08028 USA Rowan Univ Glassboro NJ USA 08028 ct & Comp Engn, Glassboro, NJ 08028 USA Iowa State Univ Sci & Technol, Ames Lab, US DOE, Microanalyt Instrument Ctr, Ames, IA 50011 USA Iowa State Univ Sci & Technol Ames IA USA 50011 t Ctr, Ames, IA 50011 USA Iowa State Univ Sci & Technol, Dept Chem, Microanalyt Instrument Ctr, Ames, IA 50011 USA Iowa State Univ Sci & Technol Ames IA USA 50011 t Ctr, Ames, IA 50011 USA Iowa State Univ Sci & Technol, Dept Elect & Comp Engn, Ames, IA 50011 USA Iowa State Univ Sci & Technol Ames IA USA 50011 Engn, Ames, IA 50011 USA
Titolo Testata:
SENSORS AND ACTUATORS B-CHEMICAL
fascicolo: 3, volume: 80, anno: 2001,
pagine: 243 - 254
SICI:
0925-4005(200112)80:3<243:AIMFSO>2.0.ZU;2-D
Fonte:
ISI
Lingua:
ENG
Soggetto:
ACOUSTIC-WAVE SENSORS; PATTERN-RECOGNITION; VAPOR RECOGNITION; CLUSTER-ANALYSIS; MIXTURES; CLASSIFICATION; RESPONSES; DESIGN;
Keywords:
optimum coating selection; decision tree; wrapper search; neural network classification;
Tipo documento:
Article
Natura:
Periodico
Settore Disciplinare:
Physical, Chemical & Earth Sciences
Engineering, Computing & Technology
Citazioni:
46
Recensione:
Indirizzi per estratti:
Indirizzo: Polikar, R Rowan Univ, Dept Elect & Comp Engn, 136 Rowan Hall, Glassboro, NJ 08028 USA Rowan Univ 136 Rowan Hall Glassboro NJ USA 08028 , NJ 08028 USA
Citazione:
R. Polikar et al., "Artificial intelligence methods for selection of an optimized sensor arrayfor identification of volatile organic compounds", SENS ACTU-B, 80(3), 2001, pp. 243-254

Abstract

We have investigated two artificial intelligence (Al)-based approaches forthe optimum selection of a sensor array for the identification of volatileorganic compounds (VOCs). The array consists of quartz crystal microbalances (QCMs), each coated with a different polymeric material. The first approach uses a decision tree classification algorithm to determine the minimum number of features that are required to classify the training data correctly. The second approach employs the hill-climb search algorithm to search the feature space for the optimal minimum feature set that maximizes the performance of a neural network classifier. We also examined the value of simple statistical procedures that could be integrated into the search algorithmin order to reduce computation time. The strengths and limitations of eachapproach are discussed. (C) 2001 Elsevier Science B.V. All rights reserved.

ASDD Area Sistemi Dipartimentali e Documentali, Università di Bologna, Catalogo delle riviste ed altri periodici
Documento generato il 31/03/20 alle ore 15:36:47