Apple Ripeness Estimation Using Artificial Neural Network

Hamza, Raja; Chtourou, Mohamed

doi:10.1109/hpcs.2018.00049

Cited by 20 publications

(6 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, apples at relatively high risk for losses in quality could be marketed first, reducing storage costs, and increasing pack-out among fruit lots. The current apple management toolkit is largely composed of physiological indices including starch clearing [ 6 ], fruit firmness [ 7 ], peel color [ 8 ], and acid and sugar content [ 9 ]. However, these methods are often insufficient to estimate risk for losses in quality; indeed these limitations certainly play a role in the diversion of billions of kilograms of apple fruit from the fresh fruit market [ 10 ].…”

Section: Introductionmentioning

confidence: 99%

Towards identification of postharvest fruit quality transcriptomic markers in Malus domestica

Hadish,

Hargarten,

Zhang

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Gene expression is highly impacted by the environment and can be reflective of past events that affected developmental processes. It is therefore expected that gene expression can serve as a signal of a current or future phenotypic traits. In this paper we identify sets of genes, which we call Prognostic Transcriptomic Biomarkers (PTBs), that can predict firmness in Malus domestica (apple) fruits. In apples, all individuals of a cultivar are clones, and differences in fruit quality are due to the environment. The apples transcriptome responds to these differences in environment, which makes PTBs an attractive predictor of future fruit quality. PTBs have the potential to enhance supply chain efficiency, reduce crop loss, and provide higher and more consistent quality for consumers. However, several questions must be addressed. In this paper we answer the question of which of two common modeling approaches, Random Forest or ElasticNet, outperforms the other. We answer if PTBs with few genes are efficient at predicting traits. This is important because we need few genes to perform qPCR, and we answer the question if qPCR is a cost-effective assay as input for PTBs modeled using high-throughput RNA-seq. To do this, we conducted a pilot study using fruit texture in the ‘Gala’ variety of apples across several postharvest storage regiments. Fruit texture in ‘Gala’ apples is highly controllable by post-harvest treatments and is therefore a good candidate to explore the use of PTBs. We find that the RandomForest model is more consistent than an ElasticNet model and is predictive of firmness (r2 = 0.78) with as few as 15 genes. We also show that qPCR is reasonably consistent with RNA-seq in a follow up experiment. Results are promising for PTBs, yet more work is needed to ensure that PTBs are robust across various environmental conditions and storage treatments.

show abstract

Section: Introductionmentioning

confidence: 99%

Towards identification of postharvest fruit quality transcriptomic markers in Malus domestica

Hadish,

Hargarten,

Zhang

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Además, basándose en los resultados estadísticos, en los que se determinan que para el presente problema de clasificación no existe diferencia significativa entre el tamaño de las imágenes, se recomienda que para trabajos afines se utilice un tamaño de imágenes de 505x505 p, con el cual se obtienen buenos resultados a un costo computacional inferior. Este hallazgo se alinea con los resultados encontrados en trabajos previos, salvo por lo indicado en los resultados expuestos por Hamza & Chtourou (2018).…”

Section: Discussionunclassified

“…Asimismo, Elhariri et al, (2014) realizaron una estimación de la madurez en pimentones sin especificar el uso de un escenario controlado, considerando cinco categorías con 175 imágenes en total (Elhariri et al, 2014). Por su parte, Hamza & Chtourou (2018) realizaron una estimación de la madurez en manzanas sin especificar el uso de un escenario controlado, haciendo uso de tres categorías, con 200 imágenes en total (Hamza & Chtourou, 2018).…”

Section: Revisión De Literaturaunclassified

“…De la revisión se puede destacar que en en cuanto a técnicas, las más comunes son técnicas de aprendizaje híbridas (Kipli et al, 2018;Mhaski et al, 2015;Polder et al, 2002;Rupanagudi et al, 2014;Simbolon et al, 2019). En segundo lugar, los autores suelen usar redes neuronales artificiales (Hamza & Chtourou, 2018;Mazen & Nashat, 2019;Saad & Hussain, 2006). En tercer lugar, máquinas de soporte vectorial SVM (Arenga et al, 2017;El-Bendary et al, 2015;Elhariri et al, 2014).…”

Section: Revisión De Literaturaunclassified

See 1 more Smart Citation

Determinación de la madurez de mazorcas de Cacao, haciendo uso de redes neuronales convolucionales en un sistema embebido

Heredia-Gómez

Rueda-Gómez

Sarmiento

et al. 2020

Rev. colomb. comput.

View full text Add to dashboard Cite

Una correcta cosecha Cacao implica determinar si la mazorca se encuentra en un adecuado estado de madurez. No obstante, este proceso suele darse de manera artesanal y basarse en atributos como el tamaño y color de la mazorca, características que difieren según la variedad cultivada, lo cual dificulta su estandarización. Con el fin de simplificar la cantidad de variables y presentar un método automatizado, el presente trabajo propone desarrollar una herramienta portable, de bajo costo, y hecha a medida, la cual hace uso de una red neuronal convolucional para indicar si una mazorca de cacao se encuentra en el momento oportuno para ser cosechada. Entre los principales resultados del presente trabajo se encuentran: 1) la construcción de tres conjuntos de datos etiquetados (1992 imágenes cada uno), y 2) un sistema embebido con una precisión de 34.83% mAP (mean Average Precision). Finalmente, se demuestra estadísticamente que el tamaño de las imágenes (4033x4033 p, 1009x1009 p y 505x505 p) no incide sobre la eficacia del entrenamiento.

show abstract

“…In [14], ANN classification approach has been investigated to estimate the ripeness of apple fruits based on colour. Several points have been dealt with in this study, namely the colour features vectors, the learning pedagogy and the structure of the ANN classifier.…”

Section: Related Workmentioning

confidence: 99%

Design of fuzzy inference system for apple ripeness estimation using gradient method

Hamza

Chtourou

2020

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Apple Ripeness Estimation Using Artificial Neural Network

Cited by 20 publications

References 15 publications

Towards identification of postharvest fruit quality transcriptomic markers in Malus domestica

Towards identification of postharvest fruit quality transcriptomic markers in Malus domestica

Determinación de la madurez de mazorcas de Cacao, haciendo uso de redes neuronales convolucionales en un sistema embebido

Design of fuzzy inference system for apple ripeness estimation using gradient method

Contact Info

Product

Resources

About