“…At the present, caution should be exercised before utilising them in commercial applications due the lingering issues that require resolution by further research. It cannot be said that CNNs outperform traditional techniques such as PLS regression in all cases, but rather that they outperform PLS in certain scenarios, depending on the 76 instrument and the attribute. It is crucial to consider the context of the application, available resources, and expertise to achieve the "best result" for the application.…”
Section: Discussionmentioning
confidence: 94%
“…Although the results are not directly comparable, as Yang et al 76 used up to 20% of the fourth season dataset to train the model, it can be inferred that the Yang et al 76 CNN architecture is much less successful for the mango dry matter application. Yang et al 76 could have easily produced a directly comparable result by keeping the fourth season as the independent test set, as per the previous publications.Figure 4.1D-CNN architecture proposed by Yang et al 76 …”
Section: Cnn-nir In Fruit Quality Evaluationmentioning
confidence: 96%
“…The first application of CNN for NIR attribute estimation of intact fruit occurred in 2021, with an explosion of effort in that 10 papers have been published in 2021 and 2022 (Table 3). Of the publications identified, six involved application to mango DM, [76][77][78][79][80][81] two to pear attributes, 76,82 two to orange attributes 83,84 and one to pomelo attributes 85 (Table 3). 3).…”
Section: Regressionmentioning
confidence: 99%
“…As the largest publicly available fruit data set, it has been utilised in several studies exploring the use of global modelling techniques. [76][77][78][79][80][81]87,89,94 In these works data of the first three seasons is used for training, and the fourth season for independent validation. Table 5 presents a direct comparison of the reported RSMEP on the same independent test.…”
Section: Technique Comparison Involving Publicly Available Datamentioning
confidence: 99%
“…Yang et al 76 experimented with a CNN architecture with three convolutional layers as opposed to the Cui and Fearn 28 architecture implemented by Mishra and Passos 77 which employs only one convolutional layer (Figures 2 and 4). Although the results are not directly comparable, as Yang et al 76 used up to 20% of the fourth season dataset to train the model, it can be inferred that the Yang et al 76 CNN architecture is much less successful for the mango dry matter application. Yang et al 76 could have easily produced a directly comparable result by keeping the fourth season as the independent test set, as per the previous publications.Figure 4.1D-CNN architecture proposed by Yang et al 76 …”
Section: Cnn-nir In Fruit Quality Evaluationmentioning
The Part 1 prequel to this review evaluated the evolution of modelling techniques used in evaluation of fruit quality over the past three decades and noted a progression towards the use of artificial neural networks (ANNs) and convolutional neural networks (CNNs). In this review, Part 2, the use of CNNs for NIR fruit quality evaluation is explored, given the success of CNNs in various other fields, such as image, video, speech, and audio processing, and the availability of large (open source) datasets of fruit spectra and reference quality attribute, which is required for the training of CNN models. The review provides an overview of deep learning and the CNN architectures and techniques used in NIR spectroscopy for regression modelling, with advantages and disadvantages identified. Studies using CNN for NIR based fruit quality evaluation are then critically examined. Eight publications have presented on models using the same open-source mango dry matter calibration and test set, enabling inter-method comparisons. CNN models have been demonstrated to be accurate, precise and robust. Techniques of transfer learning for CNN models offer an alternative solution to model updating and calibration transfer methods applied in traditional chemometrics. The review has highlighted crucial areas that require resolution and exploration in this application through future research, including, (i) data requirements for training a CNN (ii) optimal spectral pre-processing for CNN (iii) CNN architecture and hyper-parameter selection and tuning for fruit quality evaluation (iv) CNN model interpretability and explainability. Future studies must conduct clearer comparison to partial least squares (PLS) regression and shallow ANNs to better assess the prospective benefit of using CNN, a more complex model. The potential for visualisation of spectra relevance to the CNN model using techniques such as GradCam, currently employed in visualising 2D-CNN models, remains to be explored.
“…At the present, caution should be exercised before utilising them in commercial applications due the lingering issues that require resolution by further research. It cannot be said that CNNs outperform traditional techniques such as PLS regression in all cases, but rather that they outperform PLS in certain scenarios, depending on the 76 instrument and the attribute. It is crucial to consider the context of the application, available resources, and expertise to achieve the "best result" for the application.…”
Section: Discussionmentioning
confidence: 94%
“…Although the results are not directly comparable, as Yang et al 76 used up to 20% of the fourth season dataset to train the model, it can be inferred that the Yang et al 76 CNN architecture is much less successful for the mango dry matter application. Yang et al 76 could have easily produced a directly comparable result by keeping the fourth season as the independent test set, as per the previous publications.Figure 4.1D-CNN architecture proposed by Yang et al 76 …”
Section: Cnn-nir In Fruit Quality Evaluationmentioning
confidence: 96%
“…The first application of CNN for NIR attribute estimation of intact fruit occurred in 2021, with an explosion of effort in that 10 papers have been published in 2021 and 2022 (Table 3). Of the publications identified, six involved application to mango DM, [76][77][78][79][80][81] two to pear attributes, 76,82 two to orange attributes 83,84 and one to pomelo attributes 85 (Table 3). 3).…”
Section: Regressionmentioning
confidence: 99%
“…As the largest publicly available fruit data set, it has been utilised in several studies exploring the use of global modelling techniques. [76][77][78][79][80][81]87,89,94 In these works data of the first three seasons is used for training, and the fourth season for independent validation. Table 5 presents a direct comparison of the reported RSMEP on the same independent test.…”
Section: Technique Comparison Involving Publicly Available Datamentioning
confidence: 99%
“…Yang et al 76 experimented with a CNN architecture with three convolutional layers as opposed to the Cui and Fearn 28 architecture implemented by Mishra and Passos 77 which employs only one convolutional layer (Figures 2 and 4). Although the results are not directly comparable, as Yang et al 76 used up to 20% of the fourth season dataset to train the model, it can be inferred that the Yang et al 76 CNN architecture is much less successful for the mango dry matter application. Yang et al 76 could have easily produced a directly comparable result by keeping the fourth season as the independent test set, as per the previous publications.Figure 4.1D-CNN architecture proposed by Yang et al 76 …”
Section: Cnn-nir In Fruit Quality Evaluationmentioning
The Part 1 prequel to this review evaluated the evolution of modelling techniques used in evaluation of fruit quality over the past three decades and noted a progression towards the use of artificial neural networks (ANNs) and convolutional neural networks (CNNs). In this review, Part 2, the use of CNNs for NIR fruit quality evaluation is explored, given the success of CNNs in various other fields, such as image, video, speech, and audio processing, and the availability of large (open source) datasets of fruit spectra and reference quality attribute, which is required for the training of CNN models. The review provides an overview of deep learning and the CNN architectures and techniques used in NIR spectroscopy for regression modelling, with advantages and disadvantages identified. Studies using CNN for NIR based fruit quality evaluation are then critically examined. Eight publications have presented on models using the same open-source mango dry matter calibration and test set, enabling inter-method comparisons. CNN models have been demonstrated to be accurate, precise and robust. Techniques of transfer learning for CNN models offer an alternative solution to model updating and calibration transfer methods applied in traditional chemometrics. The review has highlighted crucial areas that require resolution and exploration in this application through future research, including, (i) data requirements for training a CNN (ii) optimal spectral pre-processing for CNN (iii) CNN architecture and hyper-parameter selection and tuning for fruit quality evaluation (iv) CNN model interpretability and explainability. Future studies must conduct clearer comparison to partial least squares (PLS) regression and shallow ANNs to better assess the prospective benefit of using CNN, a more complex model. The potential for visualisation of spectra relevance to the CNN model using techniques such as GradCam, currently employed in visualising 2D-CNN models, remains to be explored.
The renowned Alphonso mango, celebrated in India for its exquisite taste, saffron hue, pleasing texture, and prolonged shelf life, holds significant global commercial appeal. Unfortunately, the widespread issue of spongy tissue (ST) disorder in Alphonso mangoes results in a soft, corky texture, affecting up to 30% of mangoes in a single batch. This challenge leads to the outright rejection of affected mangoes during export due to delayed disorder identification. The current evaluation method involves destructive cutting, causing substantial fruit loss, and lacks assurance for the overall batch quality. This study addresses these challenges by focusing on the utilization of visible near‐infrared spectroscopy as a non‐invasive method to assess the internal quality of mangoes. Additionally, it introduces innovative classification models for automated binary categorization (Healthy vs. ST affected). Through preprocessing and principal component analysis of spectral reflectance data for feature extraction and wavelength optimization, successful wavelength ranges of 650–970 nm were identified, effectively distinguishing between healthy and damaged mangoes. Various machine learning models used notably, linear discriminant analysis, support vector machine, and logistic regression exhibited strong discriminative capabilities with higher accuracy reaching 99%. This non‐destructive approach addresses critical challenges in the mango export industry, offering early detection of internal disorders and minimizing postharvest losses.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
