Simulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?

Relative to standard red/green/blue (RGB) imaging systems, hyperspectral imaging systems offer superior capabilities but tend to be expensive and complex, requiring either a mechanically complex push-broom line scanning method, a tunable filter, or a large set of light emitting diodes (LEDs) to coll...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: John Chauvin, Ray Duran, Kouhyar Tavakolian, Alireza Akhbardeh, Nicholas MacKinnon, Jianwei Qin, Diane E. Chan, Chansong Hwang, Insuck Baek, Moon S. Kim, Rachel B. Isaacs, Ayse Gamze Yilmaz, Jiahleen Roungchun, Rosalee S. Hellberg, Fartash Vasefi
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
T
Acceso en línea:https://doaj.org/article/fd18c1a6f0454c0ca3a24a360fcbaa59
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:fd18c1a6f0454c0ca3a24a360fcbaa59
record_format dspace
spelling oai:doaj.org-article:fd18c1a6f0454c0ca3a24a360fcbaa592021-11-25T16:33:49ZSimulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?10.3390/app1122106282076-3417https://doaj.org/article/fd18c1a6f0454c0ca3a24a360fcbaa592021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10628https://doaj.org/toc/2076-3417Relative to standard red/green/blue (RGB) imaging systems, hyperspectral imaging systems offer superior capabilities but tend to be expensive and complex, requiring either a mechanically complex push-broom line scanning method, a tunable filter, or a large set of light emitting diodes (LEDs) to collect images in multiple wavelengths. This paper proposes a new methodology to support the design of a hypothesized system that uses three imaging modes—fluorescence, visible/near-infrared (VNIR) reflectance, and shortwave infrared (SWIR) reflectance—to capture narrow-band spectral data at only three to seven narrow wavelengths. Simulated annealing is applied to identify the optimal wavelengths for sparse spectral measurement with a cost function based on the accuracy provided by a weighted k-nearest neighbors (WKNN) classifier, a common and relatively robust machine learning classifier. Two separate classification approaches are presented, the first using a multi-layer perceptron (MLP) artificial neural network trained on sparse data from the three individual spectra and the second using a fusion of the data from all three spectra. The results are compared with those from four alternative classifiers based on common machine learning algorithms. To validate the proposed methodology, reflectance and fluorescence spectra in these three spectroscopic modes were collected from fish fillets and used to classify the fillets by species. Accuracies determined from the two classification approaches are compared with benchmark values derived by training the classifiers with the full resolution spectral data. The results of the single-layer classification study show accuracies ranging from ~68% for SWIR reflectance to ~90% for fluorescence with just seven wavelengths. The results of the fusion classification study show accuracies of about 95% with seven wavelengths and more than 90% even with just three wavelengths. Reducing the number of required wavelengths facilitates the creation of rapid and cost-effective spectral imaging systems that can be used for widespread analysis in food monitoring/food fraud, agricultural, and biomedical applications.John ChauvinRay DuranKouhyar TavakolianAlireza AkhbardehNicholas MacKinnonJianwei QinDiane E. ChanChansong HwangInsuck BaekMoon S. KimRachel B. IsaacsAyse Gamze YilmazJiahleen RoungchunRosalee S. HellbergFartash VasefiMDPI AGarticleclassificationhyperspectral imagingfood fraudsimulated annealingmachine learningspectroscopyTechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10628, p 10628 (2021)
institution DOAJ
collection DOAJ
language EN
topic classification
hyperspectral imaging
food fraud
simulated annealing
machine learning
spectroscopy
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
spellingShingle classification
hyperspectral imaging
food fraud
simulated annealing
machine learning
spectroscopy
Technology
T
Engineering (General). Civil engineering (General)
TA1-2040
Biology (General)
QH301-705.5
Physics
QC1-999
Chemistry
QD1-999
John Chauvin
Ray Duran
Kouhyar Tavakolian
Alireza Akhbardeh
Nicholas MacKinnon
Jianwei Qin
Diane E. Chan
Chansong Hwang
Insuck Baek
Moon S. Kim
Rachel B. Isaacs
Ayse Gamze Yilmaz
Jiahleen Roungchun
Rosalee S. Hellberg
Fartash Vasefi
Simulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?
description Relative to standard red/green/blue (RGB) imaging systems, hyperspectral imaging systems offer superior capabilities but tend to be expensive and complex, requiring either a mechanically complex push-broom line scanning method, a tunable filter, or a large set of light emitting diodes (LEDs) to collect images in multiple wavelengths. This paper proposes a new methodology to support the design of a hypothesized system that uses three imaging modes—fluorescence, visible/near-infrared (VNIR) reflectance, and shortwave infrared (SWIR) reflectance—to capture narrow-band spectral data at only three to seven narrow wavelengths. Simulated annealing is applied to identify the optimal wavelengths for sparse spectral measurement with a cost function based on the accuracy provided by a weighted k-nearest neighbors (WKNN) classifier, a common and relatively robust machine learning classifier. Two separate classification approaches are presented, the first using a multi-layer perceptron (MLP) artificial neural network trained on sparse data from the three individual spectra and the second using a fusion of the data from all three spectra. The results are compared with those from four alternative classifiers based on common machine learning algorithms. To validate the proposed methodology, reflectance and fluorescence spectra in these three spectroscopic modes were collected from fish fillets and used to classify the fillets by species. Accuracies determined from the two classification approaches are compared with benchmark values derived by training the classifiers with the full resolution spectral data. The results of the single-layer classification study show accuracies ranging from ~68% for SWIR reflectance to ~90% for fluorescence with just seven wavelengths. The results of the fusion classification study show accuracies of about 95% with seven wavelengths and more than 90% even with just three wavelengths. Reducing the number of required wavelengths facilitates the creation of rapid and cost-effective spectral imaging systems that can be used for widespread analysis in food monitoring/food fraud, agricultural, and biomedical applications.
format article
author John Chauvin
Ray Duran
Kouhyar Tavakolian
Alireza Akhbardeh
Nicholas MacKinnon
Jianwei Qin
Diane E. Chan
Chansong Hwang
Insuck Baek
Moon S. Kim
Rachel B. Isaacs
Ayse Gamze Yilmaz
Jiahleen Roungchun
Rosalee S. Hellberg
Fartash Vasefi
author_facet John Chauvin
Ray Duran
Kouhyar Tavakolian
Alireza Akhbardeh
Nicholas MacKinnon
Jianwei Qin
Diane E. Chan
Chansong Hwang
Insuck Baek
Moon S. Kim
Rachel B. Isaacs
Ayse Gamze Yilmaz
Jiahleen Roungchun
Rosalee S. Hellberg
Fartash Vasefi
author_sort John Chauvin
title Simulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?
title_short Simulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?
title_full Simulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?
title_fullStr Simulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?
title_full_unstemmed Simulated Annealing-Based Hyperspectral Data Optimization for Fish Species Classification: Can the Number of Measured Wavelengths Be Reduced?
title_sort simulated annealing-based hyperspectral data optimization for fish species classification: can the number of measured wavelengths be reduced?
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/fd18c1a6f0454c0ca3a24a360fcbaa59
work_keys_str_mv AT johnchauvin simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT rayduran simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT kouhyartavakolian simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT alirezaakhbardeh simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT nicholasmackinnon simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT jianweiqin simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT dianeechan simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT chansonghwang simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT insuckbaek simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT moonskim simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT rachelbisaacs simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT aysegamzeyilmaz simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT jiahleenroungchun simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT rosaleeshellberg simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
AT fartashvasefi simulatedannealingbasedhyperspectraldataoptimizationforfishspeciesclassificationcanthenumberofmeasuredwavelengthsbereduced
_version_ 1718413177164660736