Unified Classification of Bacterial Colonies on Different Agar Media Based on Hyperspectral Imaging and Machine Learning
A universal method by considering different types of culture media can enable convenient classification of bacterial species. The study combined hyperspectral technology and versatile chemometric algorithms to achieve the rapid and non-destructive classification of three kinds of bacterial colonies...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-04-01
|
Series: | Molecules |
Subjects: | |
Online Access: | https://www.mdpi.com/1420-3049/25/8/1797 |
id |
doaj-3f5bcf7f3e1c4b519b8dc53b8f1bf31c |
---|---|
record_format |
Article |
spelling |
doaj-3f5bcf7f3e1c4b519b8dc53b8f1bf31c2020-11-25T02:28:54ZengMDPI AGMolecules1420-30492020-04-01251797179710.3390/molecules25081797Unified Classification of Bacterial Colonies on Different Agar Media Based on Hyperspectral Imaging and Machine LearningPeng Gu0Yao-Ze Feng1Le Zhu2Li-Qin Kong3Xiu-ling Zhang4Sheng Zhang5Shao-Wen Li6Gui-Feng Jia7Department of Mechatronics Engineering, College of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaDepartment of Mechatronics Engineering, College of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaDepartment of Mechatronics Engineering, College of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaDepartment of Mechatronics Engineering, College of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaDepartment of Preventive Veterinary Medicine, College of Veterinary Medicine, Huazhong Agricultural University, Wuhan 430070, ChinaDepartment of Mechatronics Engineering, College of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaDepartment of Preventive Veterinary Medicine, College of Veterinary Medicine, Huazhong Agricultural University, Wuhan 430070, ChinaDepartment of Mechatronics Engineering, College of Engineering, Huazhong Agricultural University, Wuhan 430070, ChinaA universal method by considering different types of culture media can enable convenient classification of bacterial species. The study combined hyperspectral technology and versatile chemometric algorithms to achieve the rapid and non-destructive classification of three kinds of bacterial colonies (<i>Escherichia coli</i>, <i>Staphylococcus aureus</i> and <i>Salmonella</i>) cultured on three kinds of agar media (Luria–Bertani agar (LA), plate count agar (PA) and tryptone soy agar (TSA)). Based on the extracted spectral data, partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were employed to established classification models. The parameters of SVM models were optimized by comparing genetic algorithm (GA), particle swarm optimization (PSO) and grasshopper optimization algorithm (GOA). The best classification model was GOA-SVM, where the overall correct classification rates (OCCRs) for calibration and prediction of the full-wavelength GOA-SVM model were 99.45% and 98.82%, respectively, and the Kappa coefficient for prediction was 0.98. For further investigation, the CARS, SPA and GA wavelength selection methods were used to establish GOA-SVM simplified model, where CARS-GOA-SVM was optimal in model accuracy and stability with the corresponding OCCRs for calibration and prediction and the Kappa coefficients of 99.45%, 98.73% and 0.98, respectively. The above results demonstrated that it was feasible to classify bacterial colonies on different agar media and the unified model provided a continent and accurate way for bacterial classification.https://www.mdpi.com/1420-3049/25/8/1797bacterial pathogensVisible-Near-infrared hyperspectral imaginggrasshopper optimization algorithmsupport vector machinevariable selectionoptimization |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Peng Gu Yao-Ze Feng Le Zhu Li-Qin Kong Xiu-ling Zhang Sheng Zhang Shao-Wen Li Gui-Feng Jia |
spellingShingle |
Peng Gu Yao-Ze Feng Le Zhu Li-Qin Kong Xiu-ling Zhang Sheng Zhang Shao-Wen Li Gui-Feng Jia Unified Classification of Bacterial Colonies on Different Agar Media Based on Hyperspectral Imaging and Machine Learning Molecules bacterial pathogens Visible-Near-infrared hyperspectral imaging grasshopper optimization algorithm support vector machine variable selection optimization |
author_facet |
Peng Gu Yao-Ze Feng Le Zhu Li-Qin Kong Xiu-ling Zhang Sheng Zhang Shao-Wen Li Gui-Feng Jia |
author_sort |
Peng Gu |
title |
Unified Classification of Bacterial Colonies on Different Agar Media Based on Hyperspectral Imaging and Machine Learning |
title_short |
Unified Classification of Bacterial Colonies on Different Agar Media Based on Hyperspectral Imaging and Machine Learning |
title_full |
Unified Classification of Bacterial Colonies on Different Agar Media Based on Hyperspectral Imaging and Machine Learning |
title_fullStr |
Unified Classification of Bacterial Colonies on Different Agar Media Based on Hyperspectral Imaging and Machine Learning |
title_full_unstemmed |
Unified Classification of Bacterial Colonies on Different Agar Media Based on Hyperspectral Imaging and Machine Learning |
title_sort |
unified classification of bacterial colonies on different agar media based on hyperspectral imaging and machine learning |
publisher |
MDPI AG |
series |
Molecules |
issn |
1420-3049 |
publishDate |
2020-04-01 |
description |
A universal method by considering different types of culture media can enable convenient classification of bacterial species. The study combined hyperspectral technology and versatile chemometric algorithms to achieve the rapid and non-destructive classification of three kinds of bacterial colonies (<i>Escherichia coli</i>, <i>Staphylococcus aureus</i> and <i>Salmonella</i>) cultured on three kinds of agar media (Luria–Bertani agar (LA), plate count agar (PA) and tryptone soy agar (TSA)). Based on the extracted spectral data, partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were employed to established classification models. The parameters of SVM models were optimized by comparing genetic algorithm (GA), particle swarm optimization (PSO) and grasshopper optimization algorithm (GOA). The best classification model was GOA-SVM, where the overall correct classification rates (OCCRs) for calibration and prediction of the full-wavelength GOA-SVM model were 99.45% and 98.82%, respectively, and the Kappa coefficient for prediction was 0.98. For further investigation, the CARS, SPA and GA wavelength selection methods were used to establish GOA-SVM simplified model, where CARS-GOA-SVM was optimal in model accuracy and stability with the corresponding OCCRs for calibration and prediction and the Kappa coefficients of 99.45%, 98.73% and 0.98, respectively. The above results demonstrated that it was feasible to classify bacterial colonies on different agar media and the unified model provided a continent and accurate way for bacterial classification. |
topic |
bacterial pathogens Visible-Near-infrared hyperspectral imaging grasshopper optimization algorithm support vector machine variable selection optimization |
url |
https://www.mdpi.com/1420-3049/25/8/1797 |
work_keys_str_mv |
AT penggu unifiedclassificationofbacterialcoloniesondifferentagarmediabasedonhyperspectralimagingandmachinelearning AT yaozefeng unifiedclassificationofbacterialcoloniesondifferentagarmediabasedonhyperspectralimagingandmachinelearning AT lezhu unifiedclassificationofbacterialcoloniesondifferentagarmediabasedonhyperspectralimagingandmachinelearning AT liqinkong unifiedclassificationofbacterialcoloniesondifferentagarmediabasedonhyperspectralimagingandmachinelearning AT xiulingzhang unifiedclassificationofbacterialcoloniesondifferentagarmediabasedonhyperspectralimagingandmachinelearning AT shengzhang unifiedclassificationofbacterialcoloniesondifferentagarmediabasedonhyperspectralimagingandmachinelearning AT shaowenli unifiedclassificationofbacterialcoloniesondifferentagarmediabasedonhyperspectralimagingandmachinelearning AT guifengjia unifiedclassificationofbacterialcoloniesondifferentagarmediabasedonhyperspectralimagingandmachinelearning |
_version_ |
1724835816552792064 |