Nondestructive detection of Pleurotus geesteranus strain degradation based on micro-hyperspectral imaging and machine learning
In the production of edible fungi, the use of degraded strains in cultivation incurs significant economic losses. Based on micro-hyperspectral imaging and machine learning, this study proposes an early, nondestructive method for detecting different degradation degrees of Pleurotus geesteranus strain...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-12-01
|
| Series: | Frontiers in Plant Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpls.2023.1260625/full |
| _version_ | 1797403351963402240 |
|---|---|
| author | Xuan Wei Shiyang Liu Chuangyuan Xie Wei Fang Chanjuan Deng Zhiqiang Wen Dapeng Ye Dengfei Jie |
| author_facet | Xuan Wei Shiyang Liu Chuangyuan Xie Wei Fang Chanjuan Deng Zhiqiang Wen Dapeng Ye Dengfei Jie |
| author_sort | Xuan Wei |
| collection | DOAJ |
| description | In the production of edible fungi, the use of degraded strains in cultivation incurs significant economic losses. Based on micro-hyperspectral imaging and machine learning, this study proposes an early, nondestructive method for detecting different degradation degrees of Pleurotus geesteranus strains. In this study, an undegraded strain and three different degradation-level strains were used. During the mycelium growth, 600 micro-hyperspectral images were obtained. Based on the average transmittance spectra of the region of interest (ROI) in the range of 400-1000 nm and images at feature bands, feature spectra and images were extracted using the successive projections algorithm (SPA) and the deep residual network (ResNet50), respectively. Different feature input combinations were utilized to establish support vector machine (SVM) classification models. Based on the results, the spectra-input-based model performed better than the image-input-based model, and feature extraction improved the classification results for both models. The feature-fusion-based SPA+ResNet50-SVM model was the best; the accuracy rate of the test set was up to 90.8%, which was better than the accuracy rates of SPA-SVM (83.3%) and ResNet50-SVM (80.8%). This study proposes a nondestructive method to detect the degradation of Pleurotus geesteranus strains, which could further inspire new methods for the phenotypic identification of edible fungi. |
| first_indexed | 2024-03-09T02:37:30Z |
| format | Article |
| id | doaj.art-7201bce42f9c41259b9811cf42512542 |
| institution | Directory Open Access Journal |
| issn | 1664-462X |
| language | English |
| last_indexed | 2024-03-09T02:37:30Z |
| publishDate | 2023-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Plant Science |
| spelling | doaj.art-7201bce42f9c41259b9811cf425125422023-12-06T08:27:52ZengFrontiers Media S.A.Frontiers in Plant Science1664-462X2023-12-011410.3389/fpls.2023.12606251260625Nondestructive detection of Pleurotus geesteranus strain degradation based on micro-hyperspectral imaging and machine learningXuan Wei0Shiyang Liu1Chuangyuan Xie2Wei Fang3Chanjuan Deng4Zhiqiang Wen5Dapeng Ye6Dengfei Jie7College of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian, ChinaCollege of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian, ChinaCollege of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian, ChinaCollege of Future Technology, Fujian Agriculture and Forestry University, Fuzhou, Fujian, ChinaCollege of Future Technology, Fujian Agriculture and Forestry University, Fuzhou, Fujian, ChinaCollege of Life Science, Fujian Agriculture and Forestry University, Fuzhou, Fujian, ChinaCollege of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian, ChinaCollege of Mechanical and Electrical Engineering, Fujian Agriculture and Forestry University, Fuzhou, Fujian, ChinaIn the production of edible fungi, the use of degraded strains in cultivation incurs significant economic losses. Based on micro-hyperspectral imaging and machine learning, this study proposes an early, nondestructive method for detecting different degradation degrees of Pleurotus geesteranus strains. In this study, an undegraded strain and three different degradation-level strains were used. During the mycelium growth, 600 micro-hyperspectral images were obtained. Based on the average transmittance spectra of the region of interest (ROI) in the range of 400-1000 nm and images at feature bands, feature spectra and images were extracted using the successive projections algorithm (SPA) and the deep residual network (ResNet50), respectively. Different feature input combinations were utilized to establish support vector machine (SVM) classification models. Based on the results, the spectra-input-based model performed better than the image-input-based model, and feature extraction improved the classification results for both models. The feature-fusion-based SPA+ResNet50-SVM model was the best; the accuracy rate of the test set was up to 90.8%, which was better than the accuracy rates of SPA-SVM (83.3%) and ResNet50-SVM (80.8%). This study proposes a nondestructive method to detect the degradation of Pleurotus geesteranus strains, which could further inspire new methods for the phenotypic identification of edible fungi.https://www.frontiersin.org/articles/10.3389/fpls.2023.1260625/fulledible fungimicro-hyperspectral imagingphenotypestrain degradationclassification |
| spellingShingle | Xuan Wei Shiyang Liu Chuangyuan Xie Wei Fang Chanjuan Deng Zhiqiang Wen Dapeng Ye Dengfei Jie Nondestructive detection of Pleurotus geesteranus strain degradation based on micro-hyperspectral imaging and machine learning Frontiers in Plant Science edible fungi micro-hyperspectral imaging phenotype strain degradation classification |
| title | Nondestructive detection of Pleurotus geesteranus strain degradation based on micro-hyperspectral imaging and machine learning |
| title_full | Nondestructive detection of Pleurotus geesteranus strain degradation based on micro-hyperspectral imaging and machine learning |
| title_fullStr | Nondestructive detection of Pleurotus geesteranus strain degradation based on micro-hyperspectral imaging and machine learning |
| title_full_unstemmed | Nondestructive detection of Pleurotus geesteranus strain degradation based on micro-hyperspectral imaging and machine learning |
| title_short | Nondestructive detection of Pleurotus geesteranus strain degradation based on micro-hyperspectral imaging and machine learning |
| title_sort | nondestructive detection of pleurotus geesteranus strain degradation based on micro hyperspectral imaging and machine learning |
| topic | edible fungi micro-hyperspectral imaging phenotype strain degradation classification |
| url | https://www.frontiersin.org/articles/10.3389/fpls.2023.1260625/full |
| work_keys_str_mv | AT xuanwei nondestructivedetectionofpleurotusgeesteranusstraindegradationbasedonmicrohyperspectralimagingandmachinelearning AT shiyangliu nondestructivedetectionofpleurotusgeesteranusstraindegradationbasedonmicrohyperspectralimagingandmachinelearning AT chuangyuanxie nondestructivedetectionofpleurotusgeesteranusstraindegradationbasedonmicrohyperspectralimagingandmachinelearning AT weifang nondestructivedetectionofpleurotusgeesteranusstraindegradationbasedonmicrohyperspectralimagingandmachinelearning AT chanjuandeng nondestructivedetectionofpleurotusgeesteranusstraindegradationbasedonmicrohyperspectralimagingandmachinelearning AT zhiqiangwen nondestructivedetectionofpleurotusgeesteranusstraindegradationbasedonmicrohyperspectralimagingandmachinelearning AT dapengye nondestructivedetectionofpleurotusgeesteranusstraindegradationbasedonmicrohyperspectralimagingandmachinelearning AT dengfeijie nondestructivedetectionofpleurotusgeesteranusstraindegradationbasedonmicrohyperspectralimagingandmachinelearning |