Search

In this study, a portable optical instrument was designed and developed for real-time nondestructive determination of fruit ripeness. A prototype of the instrument using inexpensive parts was developed and calibrated for apple ripeness detection based on moisture content, soluble solids content, pH, and firmness. An array of six optical point sources (light-emitting diodes (LEDs) that emit light at 520-, 670-, 920-, 970-, 1050-, and 1320-nm wavelengths) were selected using visible/near infrarred (Vis/NIR) spectral analysis on apple samples. The instrument was equipped with optical fibers, optical sensors, and an Arduino board for sending and receiving the waves and processing the received signals, as well as controlling the operation of the instrument. The decision tree method was utilized to create a classification model for training the instrument to classify ripe and unripe apples. Test results showed acceptable performance of the developed instrument for apple ripeness estimation and proved useful in classifying fruits into ripe and unripe groups based on their internal quality. [ABSTRACT FROM AUTHOR]

Abstract In this research, the feasibility of utilizing visible/near-infrared (Vis/NIR) spectroscopy as an optical non-destructive technique combined with both supervised and unsupervised pattern recognition methods was assessed for detection of Ectomyelois ceratoniae , carob moth, infestation in pomegranates during hidden activity of the larvae. To this end, some fruits were artificially contaminated to the carob moth larvae. Vis/NIR spectra of the blank samples and the contaminated pomegranates without and with external visual symptoms of larvae infestation were analyzed one and two weeks after contaminating the samples as three groups of "Healthy", "Unhealthy-A" and "Unhealthy-B", respectively. Principal component analysis (PCA) as unsupervised pattern recognition method was used to verify the possibility of clustering of the pomegranate samples into the three groups. Discriminant analysis (DA) based on PCA was also used as a powerful supervised pattern recognition method to classify the samples. The calibration models of linear, quadratic and Mahalanobis discriminant analyses were developed based on different spectral pre-processing techniques. The best PCA-DA model was obtained using Mahalanobis distance method and first derivative (D1) pre-processing. The total percentage of correctly classified samples with the best calibration model was 97.9%. The developed model could also predict unknown samples with total percentage of correctly classified samples of 90.6%. It was concluded that Vis/NIR spectroscopy combined with pattern recognition method of PCA-DA can be an appropriate and rapid technology for non-destructively screening the pomegranates for detection of carob moth infestation during hidden activity of the larvae. Graphical Abstract Unlabelled Image Highlights • Rapid detection of carob moth infestation during hidden activity of larvae in pomegranate is possible. • Vis/NIR spectroscopy can be used for health screening the pomegranates, non-destructively. • PCA-DA provides excellent classification results of healthy and unhealthy samples. [ABSTRACT FROM AUTHOR]

The feasibility of utilizing near-infrared (NIR) spectroscopy has been recently assessed for rapid and non-destructive detection of internal insect infestation in some fruits. Based on the findings, this technology can be used for on/in-line inspection of the fruits in terms of insect infestation if suitable instrument is selected for accurate spectral measurements and system development. The spectral range and optical measurement mode are two of the most important factors which can affect the accuracy of the spectral measurements and detection models. The aim of this study is meta-analysis of these factors' effects on the ability of NIR-based spectroscopy for non-destructive detection of hidden insect infestation in fruits. Eight studies (65 observations) were extracted based on the criteria of this study. Overall, utilizing NIR-based spectroscopy led to 13.98% error (95% CI = 10.69–17.27%) for non-destructive detection of hidden insect infestation in fruits. Spectral ranges of Vis/SWNIR (above 300 up to 1100 nm), NIR (above 780 up to 2500 nm), and Vis/NIR (above 300 up to 2500 nm) showed errors of 21.71% (95% CI = 16.56–26.86%), 13.30% (95% CI = 5.24–21.36%), and 13.65% (95% CI = 5.9–21.4%), respectively. It was noted that wavelengths above 1100 nm (NIR region) are more useful to detect insect infestation in fruit. Results also indicated that optical measurement modes of interactance, reflectance, and transmittance had errors of 6.66% (95% CI = 4.18–9.14%), 15.73% (95% CI = 10.99–20.47%), and 16.04% (95% CI = 7.26–24.82%), respectively. This meta-analysis suggests that utilizing interactance mode for spectra measurement in NIR-based spectroscopy can increase the accuracy of discrimination of insect infested fruits especially when the spectral range of the spectrometer is Vis/SWNIR. Moreover, it should be selected a spectrometer with the wavelength range of NIR or Vis/NIR when using reflectance or transmittance mode is necessary for developing an in/on-line system to detect insect infestation in fruits. [ABSTRACT FROM AUTHOR]

• A new approach for in-situ monitoring of apple nutrient contents was proposed. • Apple leaf spectra can replace costly and destructive analysis to predict NPK. • The RF model with Rfrog wavelength selection achieved the best results. • PLSR-based models are not recommended for nutrient estimation. • The approach can be used to develop a portable instrument to estimate NPK concentrations. Timely and rapid monitoring of apple trees nutrition status is vital for accurate management of nutrient fertilizers in order to improve the yield and quality, as well as to reduce the risk of environmental degradation. As a most frequently used method, tissue analysis used to assess the nutritional status of apple tree leaves is laborious, costly, time-consuming, environmentally unfriendly, and destructive. Ground-based sensors are able to efficiently provide information on nutritional status using leaf spectra reflectance. This research aims to establish a novel cost-effective and non-destructive approach for rapidly estimating the status of nitrogen (N), phosphorus (P), and potassium (K) in apple tree leaves based on Visible/Near-infrared (Vis/NIR) spectroscopy (500–1000 nm) coupled with machine learning. The Vis/NIR spectra of apple trees' leaves were acquired. Then, leaf chemical contents of NPK elements were considered as reference points. Different pre-processing techniques were used to pre-treat the spectra. Four different chemometrics analysis consist of support vector machine (SVM), Artificial neural network (ANN), Random Forest (RF) and partial least square (PLS) were applied to predict NPK contents in comparison to actual values. In order to simplify the models, the sensitive wavelengths were extracted using three wavelength selection approaches, variable importance in projection (VIP), partial least squares (PLS), and random frog (Rfrog). The extracted feature wavelengths from PLS, VIP, and Rfrog methods were widely distributed in the visible and near-infrared regions of the spectrum. The performance of the developed models was tested using Residual Prediction Deviation (RPD) and the Ratio of Performance to Interquartile Distance (RPIQ). The results demonstrated that among all models, the non-linear modeling methods were superior to the linear model. The best results for estimation of Nitrogen (N), Phosphorus (P), and Potassium (K) elements were achieved by the models of MSC + D 2 -Rfrog-RF (r p = 0.985, RMSEP = 0.029%, RPD = 8.77, RPIQ = 7.72), SNV + D 2 -Rfrog-RF (r p = 0.977, RMSEP = 0.0053%, RPD = 6.42, RPIQ = 5.09) and SNV + D 2 -Rfrog-RF (r p = 0.978, RMSEP = 0.018%, RPD = 8.16, RPIQ = 7.01), respectively. The findings of the current approach may provide an efficient approach to predict in-situ NPK contents of apple trees based on leaf spectral reflectance. [ABSTRACT FROM AUTHOR]