Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral Images
Nitrogen is an essential macronutrient for the growth and development of tomatoes. However, excess nitrogen fertilization can affect the quality of tomato fruit, making it unattractive to consumers. Consequently, the aim of this study is to develop a method for the early detection of excessive nitro...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/12/2706 |
| _version_ | 1797595095391797248 |
|---|---|
| author | Brahim Benmouna Raziyeh Pourdarbani Sajad Sabzi Ruben Fernandez-Beltran Ginés García-Mateos José Miguel Molina-Martínez |
| author_facet | Brahim Benmouna Raziyeh Pourdarbani Sajad Sabzi Ruben Fernandez-Beltran Ginés García-Mateos José Miguel Molina-Martínez |
| author_sort | Brahim Benmouna |
| collection | DOAJ |
| description | Nitrogen is an essential macronutrient for the growth and development of tomatoes. However, excess nitrogen fertilization can affect the quality of tomato fruit, making it unattractive to consumers. Consequently, the aim of this study is to develop a method for the early detection of excessive nitrogen fertilizer use in Royal tomato by visible and near-infrared spectroscopy. Spectral reflectance values of tomato leaves were captured at wavelengths between 400 and 1100 nm, collected from several treatments after application of normal nitrogen and on the first, second, and third days after application of excess nitrogen. A new method based on convolutional neural networks (CNN) with an attention mechanism was proposed to perform the estimation of nitrogen overdose in tomato leaves. To verify the effectiveness of this method, the proposed attention mechanism-based CNN classifier was compared with an alternative CNN having the same architecture without integrating the attention mechanism, and with other CNN models, AlexNet and VGGNet. Experimental results showed that the CNN with an attention mechanism outperformed the alternative CNN, achieving a correct classification rate (CCR) of 97.33% for the treatment, compared with a CCR of 94.94% for the CNN alone. These findings will help in the development of a new tool for rapid and accurate detection of nitrogen fertilizer overuse in large areas. |
| first_indexed | 2024-03-11T02:32:36Z |
| format | Article |
| id | doaj.art-54076482d819448795e4ce878e23518b |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T02:32:36Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-54076482d819448795e4ce878e23518b2023-11-18T10:09:28ZengMDPI AGElectronics2079-92922023-06-011212270610.3390/electronics12122706Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral ImagesBrahim Benmouna0Raziyeh Pourdarbani1Sajad Sabzi2Ruben Fernandez-Beltran3Ginés García-Mateos4José Miguel Molina-Martínez5Computer Science and Systems Department, University of Murcia, 30100 Murcia, SpainDepartment of Biosystems Engineering, College of Agriculture, University of Mohaghegh Ardabili, Ardabil 56199-11367, IranComputer Engineering Department, Sharif University of Technology, Tehran 11155-1639, IranComputer Science and Systems Department, University of Murcia, 30100 Murcia, SpainComputer Science and Systems Department, University of Murcia, 30100 Murcia, SpainFood Engineering and Agricultural Equipment Department, Technical University of Cartagena, 30203 Cartagena, SpainNitrogen is an essential macronutrient for the growth and development of tomatoes. However, excess nitrogen fertilization can affect the quality of tomato fruit, making it unattractive to consumers. Consequently, the aim of this study is to develop a method for the early detection of excessive nitrogen fertilizer use in Royal tomato by visible and near-infrared spectroscopy. Spectral reflectance values of tomato leaves were captured at wavelengths between 400 and 1100 nm, collected from several treatments after application of normal nitrogen and on the first, second, and third days after application of excess nitrogen. A new method based on convolutional neural networks (CNN) with an attention mechanism was proposed to perform the estimation of nitrogen overdose in tomato leaves. To verify the effectiveness of this method, the proposed attention mechanism-based CNN classifier was compared with an alternative CNN having the same architecture without integrating the attention mechanism, and with other CNN models, AlexNet and VGGNet. Experimental results showed that the CNN with an attention mechanism outperformed the alternative CNN, achieving a correct classification rate (CCR) of 97.33% for the treatment, compared with a CCR of 94.94% for the CNN alone. These findings will help in the development of a new tool for rapid and accurate detection of nitrogen fertilizer overuse in large areas.https://www.mdpi.com/2079-9292/12/12/2706hyperspectral imagingnitrogen treatment predictionRoyal tomatocrop yield improvementattention mechanism |
| spellingShingle | Brahim Benmouna Raziyeh Pourdarbani Sajad Sabzi Ruben Fernandez-Beltran Ginés García-Mateos José Miguel Molina-Martínez Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral Images Electronics hyperspectral imaging nitrogen treatment prediction Royal tomato crop yield improvement attention mechanism |
| title | Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral Images |
| title_full | Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral Images |
| title_fullStr | Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral Images |
| title_full_unstemmed | Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral Images |
| title_short | Attention Mechanisms in Convolutional Neural Networks for Nitrogen Treatment Detection in Tomato Leaves Using Hyperspectral Images |
| title_sort | attention mechanisms in convolutional neural networks for nitrogen treatment detection in tomato leaves using hyperspectral images |
| topic | hyperspectral imaging nitrogen treatment prediction Royal tomato crop yield improvement attention mechanism |
| url | https://www.mdpi.com/2079-9292/12/12/2706 |
| work_keys_str_mv | AT brahimbenmouna attentionmechanismsinconvolutionalneuralnetworksfornitrogentreatmentdetectionintomatoleavesusinghyperspectralimages AT raziyehpourdarbani attentionmechanismsinconvolutionalneuralnetworksfornitrogentreatmentdetectionintomatoleavesusinghyperspectralimages AT sajadsabzi attentionmechanismsinconvolutionalneuralnetworksfornitrogentreatmentdetectionintomatoleavesusinghyperspectralimages AT rubenfernandezbeltran attentionmechanismsinconvolutionalneuralnetworksfornitrogentreatmentdetectionintomatoleavesusinghyperspectralimages AT ginesgarciamateos attentionmechanismsinconvolutionalneuralnetworksfornitrogentreatmentdetectionintomatoleavesusinghyperspectralimages AT josemiguelmolinamartinez attentionmechanismsinconvolutionalneuralnetworksfornitrogentreatmentdetectionintomatoleavesusinghyperspectralimages |