Detection of Mild Moldy-Core Disease in Apples by Fusing Acoustic-Vibration Signals and Visible-Near-Infrared Transmission Spectroscopy
In response to the issue of low detection accuracy for mild moldy-core disease in apples using single methods, this study proposed an approach based on the fusion of near-infrared transmission spectroscopy and acoustic-vibration technology to enhance the discriminability of mild moldy-core disease i...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
China Food Publishing Company
2024-12-01
|
| Series: | Shipin Kexue |
| Subjects: | |
| Online Access: | https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-23-029.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832539796273102848 |
|---|---|
| author | GU Jiahui, LAI Lisi, WANG Kai, ZHANG Hui |
| author_facet | GU Jiahui, LAI Lisi, WANG Kai, ZHANG Hui |
| author_sort | GU Jiahui, LAI Lisi, WANG Kai, ZHANG Hui |
| collection | DOAJ |
| description | In response to the issue of low detection accuracy for mild moldy-core disease in apples using single methods, this study proposed an approach based on the fusion of near-infrared transmission spectroscopy and acoustic-vibration technology to enhance the discriminability of mild moldy-core disease in apples. For the near-infrared spectral signals, the impacts of different preprocessing and feature extraction methods on modeling outcomes were analyzed to select the spectral feature bands. For the acoustic-vibration signals, 7 time-domain features were optimized by using the YSV engineering test and signal analysis software as well as calculating Pearson correlation coefficients. The spectral feature bands and time-domain features were then concatenated to form a fused feature vector. Convolutional neural networks (CNN), long short-term memory (LSTM), and CNN-LSTM were employed to construct discrimination models based on single and fused features, separately. The performance analysis of the models revealed that the CNN-LSTM combination model, which integrated 15 near-infrared transmission spectral bands and 7 time-domain features, exhibited the best performance in discriminating mild moldy-core disease, with accuracy, recall, specificity, and F1 scores of 98.31%, 97.06%, 97.06%, and 97.90% on the test set, respectively. These findings demonstrate that the proposed method can effectively improve the discrimination accuracy of mild moldy-core disease in apples. |
| format | Article |
| id | doaj-art-0756875fe252483ca2381345564b069d |
| institution | Kabale University |
| issn | 1002-6630 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | China Food Publishing Company |
| record_format | Article |
| series | Shipin Kexue |
| spelling | doaj-art-0756875fe252483ca2381345564b069d2025-02-05T09:07:53ZengChina Food Publishing CompanyShipin Kexue1002-66302024-12-01452325926710.7506/spkx1002-6630-20240510-066Detection of Mild Moldy-Core Disease in Apples by Fusing Acoustic-Vibration Signals and Visible-Near-Infrared Transmission SpectroscopyGU Jiahui, LAI Lisi, WANG Kai, ZHANG Hui0(College of Intelligent Manufacturing Modern Industry, Xinjiang University, ürümqi 830017, China)In response to the issue of low detection accuracy for mild moldy-core disease in apples using single methods, this study proposed an approach based on the fusion of near-infrared transmission spectroscopy and acoustic-vibration technology to enhance the discriminability of mild moldy-core disease in apples. For the near-infrared spectral signals, the impacts of different preprocessing and feature extraction methods on modeling outcomes were analyzed to select the spectral feature bands. For the acoustic-vibration signals, 7 time-domain features were optimized by using the YSV engineering test and signal analysis software as well as calculating Pearson correlation coefficients. The spectral feature bands and time-domain features were then concatenated to form a fused feature vector. Convolutional neural networks (CNN), long short-term memory (LSTM), and CNN-LSTM were employed to construct discrimination models based on single and fused features, separately. The performance analysis of the models revealed that the CNN-LSTM combination model, which integrated 15 near-infrared transmission spectral bands and 7 time-domain features, exhibited the best performance in discriminating mild moldy-core disease, with accuracy, recall, specificity, and F1 scores of 98.31%, 97.06%, 97.06%, and 97.90% on the test set, respectively. These findings demonstrate that the proposed method can effectively improve the discrimination accuracy of mild moldy-core disease in apples.https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-23-029.pdfvisible-near-infrared transmission spectroscopy; acoustic-vibration signals; apple moldy-core disease; feature fusion; convolutional neural networks-long short-term memory |
| spellingShingle | GU Jiahui, LAI Lisi, WANG Kai, ZHANG Hui Detection of Mild Moldy-Core Disease in Apples by Fusing Acoustic-Vibration Signals and Visible-Near-Infrared Transmission Spectroscopy Shipin Kexue visible-near-infrared transmission spectroscopy; acoustic-vibration signals; apple moldy-core disease; feature fusion; convolutional neural networks-long short-term memory |
| title | Detection of Mild Moldy-Core Disease in Apples by Fusing Acoustic-Vibration Signals and Visible-Near-Infrared Transmission Spectroscopy |
| title_full | Detection of Mild Moldy-Core Disease in Apples by Fusing Acoustic-Vibration Signals and Visible-Near-Infrared Transmission Spectroscopy |
| title_fullStr | Detection of Mild Moldy-Core Disease in Apples by Fusing Acoustic-Vibration Signals and Visible-Near-Infrared Transmission Spectroscopy |
| title_full_unstemmed | Detection of Mild Moldy-Core Disease in Apples by Fusing Acoustic-Vibration Signals and Visible-Near-Infrared Transmission Spectroscopy |
| title_short | Detection of Mild Moldy-Core Disease in Apples by Fusing Acoustic-Vibration Signals and Visible-Near-Infrared Transmission Spectroscopy |
| title_sort | detection of mild moldy core disease in apples by fusing acoustic vibration signals and visible near infrared transmission spectroscopy |
| topic | visible-near-infrared transmission spectroscopy; acoustic-vibration signals; apple moldy-core disease; feature fusion; convolutional neural networks-long short-term memory |
| url | https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-23-029.pdf |
| work_keys_str_mv | AT gujiahuilailisiwangkaizhanghui detectionofmildmoldycorediseaseinapplesbyfusingacousticvibrationsignalsandvisiblenearinfraredtransmissionspectroscopy |