Predicting Fruit’s Sweetness Using Artificial Intelligence—Case Study: Orange

Al-Sammarraie, Mustafa Ahmed Jalal; Gierz, Łukasz; Przybył, Krzysztof; Koszela, Krzysztof; Szychta, Marek; Brzykcy, Jakub; Baranowska, Hanna Maria

doi:10.3390/app12168233

Cited by 20 publications

(11 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the possibility of using deep learning methods to discover patterns in such large and complex biological datasets is promising. To date, image-based analysis has been used to study plant stress and phenotyping [19-21] and assess the quality of fruits, grains, and vegetables [22-25].…”

Section: Discussionmentioning

confidence: 99%

Fruit-In-Sight:a deep learning-based framework for secondary metabolite class prediction using fruit and leaf images

Krishnan,

Kumar,

Panda

2024

Preprint

View full text Add to dashboard Cite

Fruits produce a wide variety of secondary metabolites of great economic value. Analytical measurement of secondary metabolites is tedious, time-consuming and expensive. Additionally, metabolite concentration varies greatly from tree to tree, making it difficult to choose trees for fruit collection. The current study tested whether deep learning-based models can be developed using fruit and leaf images alone to predict a metabolite's concentration class (high or low). We collected fruits and leaves (n = 1045) from neem trees grown in the wild across 0.6 million sq km, imaged those, measured concentration of five metabolites (azadirachtin, deacetyl-salannin, salannin, nimbin and nimbolide) using high-performance liquid chromatography and used those to train deep learning models for metabolite class prediction. The best model out of the seven tested (YOLOv5, GoogLeNet, InceptionNet, EfficientNet_B0, Resnext_50, Resnet18, and SqueezeNet) provided a validation F1 score of 0.93 and a test F1 score of 0.88. The sensitivity and specificity of the fruit model alone in the test set were 83.52 ± 6.19 and 82.35 ± 5.96 and 79.40 ± 8.50 and 85.64 ± 6.21, for the low and the high class, respectively. The sensitivity was further boosted to 92.67 ± 5.25 for the low class and 88.11 ± 9.17 for the high class and the specificity to 100% for both classes, using a multi-analyte framework. We incorporated the model in an Android mobile App Fruit-In-Sight that uses fruit and leaf images to decide whether to ″pick″ or ″not pick″ the fruits from a specific tree based on the metabolite concentration class. Our study provides evidence that images of fruits and leaves alone can predict the concentration class of a secondary metabolite without using extensive analytical laboratory procedures and equipment and makes the process of choosing the right tree for fruit collection easy and free of equipment and additional cost.

show abstract

Section: Discussionmentioning

confidence: 99%

Fruit-In-Sight:a deep learning-based framework for secondary metabolite class prediction using fruit and leaf images

Krishnan,

Kumar,

Panda

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…However, the possibility of using deep learning methods to discover patterns in such large and complex biological datasets is promising. Till date, image-based analysis have been used to study plant stress, phenotyping (Pound et al 2017a; Pound et al 2017b; Ghosal et al 2018), and assess quality of fruits, grains, and vegetables (Al-Sammarraie et al 2022; Boniecki et al 2015; Zaborowicz et al 2017; Koszela et al 2015).…”

Section: Discussionmentioning

confidence: 99%

“…However, the study included only a limited number of fruits ( n = 13). Al-Sammarraie and co-workers (Al-Sammarraie et al 2022) compared various methods and found that the logistical regression analysis provided the highest accuracy (97%) to predict sweetness in oranges. In the study by Al-Sammarraie and co-workers, multiple methods provided an accuracy between 82-97%.…”

Section: Discussionmentioning

confidence: 99%

“…Kinnow fruits are preferred over oranges as they are juicier, inexpensive and locally grown in certain parts of south Asia. Image analysis was previously used to identify and assess the quality of fruits, grains, and vegetables (Al-Sammarraie et al 2022; Boniecki et al 2015; Zaborowicz et al 2017; Koszela et al 2015). In the second case, we used fruits from neem ( Azadirachta indica ) tree.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Single and multi-analyte deep learning-based analysis framework for class prediction in biological images

Krishnan

Kumar

et al. 2022

Preprint

View full text Add to dashboard Cite

Measurement of biological analytes, characterizing flavor in fruits, is a cumbersome, expensive and time-consuming process. Fruits with higher concentration of analytes have greater commercial or nutritional values. Here, we tested a deep learning-based framework with fruit images to predict the class (sweet or sour and high or low) of analytes using images from two types of trees in a single and multi-analyte mode. We used fruit images from kinnow (n = 3451), an edible hybrid mandarin and neem (n = 1045), a tree with agrochemical and pharmaceutical properties. We measured sweetness in kinnows and five secondary metabolites in neem fruits (azadirachtin or A, deacetyl-salannin or D, salannin or S, nimbin or N and nimbolide or E) using a refractometer and high-performance liquid chromatography, respectively. We trained the models for 300 epochs, before and after evolution of hyper-parameters, using 300 generations with 50 epochs/generation, estimated the best models and evaluated their performance on 10 percent of independent images. The validation F1score and test accuracies were 0.79 and 0.77 and 82.55 percent and 60.8 percent respectively for kinnow and neem A analyte. A multi-analyte model enhanced the prediction of the neem model to high class when the D N S combined class predictions were high low high and to low class when D N combined class predictions were low:high respectively. The test accuracy increased further to nearly 70 percent with a 10-fold cross-validation error of 0.257 across ten randomly split train validation test sets proving the potential of a multi-analyte model to enhance the prediction accuracy, especially when the numbers of images are limiting.

show abstract

“…The data are mapped to a high-dimensional space in which the discrete superplane can be found in situations when linear separability cannot be achieved. Using a method known as kernel function, the allocation is performed [27,28,29]. In training, 80% of the data was used, and in testing, 20%.…”

Section: Methodsmentioning

confidence: 99%

Determine, Predict and Map Soil pH Level by Fiber Optic Sensor

Al-Sammarraie,

Al-Aani,

Al-Mashhadany

2023

IOP Conf. Ser.: Earth Environ. Sci.

Self Cite

View full text Add to dashboard Cite

Soil pH is one of the main factors to consider before undertaking any agricultural operation. Methods for measuring soil pH vary, but all traditional methods require time, effort, and expertise. This study aimed to determine, predict, and map the spatial distribution of soil pH based on data taken from 50 sites using the Kriging geostatistical tool in ArcGIS as a first step. In the second step, the Support Vector Machines (SVM) machine learning algorithm was used to predict the soil pH based on the CIE-L*a*b values taken from the optical fiber sensor. The standard deviation of the soil pH values was 0.42, which indicates a more reliable measurement and the data distribution is normal. The Kriging method gave a prediction accuracy of 65% while the SVM algorithm gave an accuracy of 80%. The root mean square error (RMSE) was 0.36, 0.16 and the mean absolute error (MAE) was 0.37, 0.13, respectively, for the two methods. These two methods allow the prediction of soil pH and thus the assessment of soils, allowing for easier and more efficient management decisions and sustaining productivity.

show abstract

Predicting Fruit’s Sweetness Using Artificial Intelligence—Case Study: Orange

Cited by 20 publications

References 48 publications

Fruit-In-Sight:a deep learning-based framework for secondary metabolite class prediction using fruit and leaf images

Fruit-In-Sight:a deep learning-based framework for secondary metabolite class prediction using fruit and leaf images

Single and multi-analyte deep learning-based analysis framework for class prediction in biological images

Determine, Predict and Map Soil pH Level by Fiber Optic Sensor

Contact Info

Product

Resources

About