Multiclass classification of nutrients deficiency of apple using deep neural network

Kumar, Yogesh; Dubey, Ashwani Kumar; Arora, Rajeev Ratan; Rocha, Álvaro

doi:10.1007/s00521-020-05310-x

Cited by 23 publications

(8 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The class output uses a SoftMax (Sharma and Sharma 2017) activation function with four outputs, one for each possible classification of landslide size. SoftMax was also chosen based on its common usage for multiclass classification models (Banerjee et al 2020;Kumar et al 2020).…”

Section: A1 Activation Functionsmentioning

confidence: 99%

On the prediction of landslide occurrences and sizes via Hierarchical Neural Networks

Aguilera

Lombardo

Tanyaş

et al. 2022

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

For more than three decades, the part of the geoscientific community studying landslides through data-driven models has focused on estimating where landslides may occur across a given landscape. This concept is widely known as landslide susceptibility. And, it has seen a vast improvement from old bivariate statistical techniques to modern deep learning routines. Despite all these advancements, no spatially-explicit data-driven model is currently capable of also predicting how large landslides may be once they trigger in a specific study area. In this work, we exploit a model architecture that has already found a number of applications in landslide susceptibility. Specifically, we opt for the use of Neural Networks. But, instead of focusing exclusively on where landslides may occur, we extend this paradigm to also spatially predict classes of landslide sizes. As a result, we keep the traditional binary classification paradigm but we make use of it to complement the susceptibility estimates with a crucial information for landslide hazard assessment. We will refer to this model as Hierarchical Neural Network (HNN) throughout the manuscript. To test this analytical protocol, we use the Nepalese area where the Gorkha earthquake induced tens of thousands of landslides on the 25th of April 2015. The results we obtain are quite promising. The component of our HNN that estimates the susceptibility outperforms a binomial Generalized Linear Model (GLM) baseline we used as benchmark. We did this for a GLM represents the most common classifier in the landslide literature. Most importantly, our HNN also suitably performed across the entire procedure. As a result, the landslide-area-class prediction returned not just a single susceptibility map, as per tradition. But, it also produced several informative maps on the expected landslide size classes. Our vision is for administrations to consult these suite of model outputs and maps to better assess the risk to local communities and infrastructure. And, to promote the diffusion of our HNN, we are sharing the data and codes in a githubsec repository in the hope that we would stimulate others to replicate similar analyses.

show abstract

Section: A1 Activation Functionsmentioning

confidence: 99%

On the prediction of landslide occurrences and sizes via Hierarchical Neural Networks

Aguilera

Lombardo

Tanyaş

et al. 2022

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

show abstract

“…Al. [5] proposed an approach a deep learning model for the nutrient shortage of apple fruit. This model's ability to 'classify' and 'recognize' any form of deficit present in apple fruit is 94.24 percent accurate.…”

Section: ░ 2 Literature Reviewmentioning

confidence: 99%

Automatic Framework for Vegetable Classification using Transfer-Learning

Singh¹,

Singh

Goel³

et al. 2022

IJEER

View full text Add to dashboard Cite

Globally, fresh vegetables are a crucial part of our lives and they provide most of the vitamins, minerals, and proteins, in short, every nutrition that a growing body need. They vary in colors like; red, green, and yellow but as our ancestors say that green vegetables are a must for every age. To identify the fresh vegetable that makes our body healthy and notion positive the proposed automatic multi-class vegetable classifier is used. In this paper, a framework based on a deep learning approach has been proposed for multi-class vegetable classification from scratch. The accuracy of the proposed model is further increased using the transfer-learning concept (DenseNet201). The whole process is divided into four modules; data collection and pre-processing, data splitting, CNN model training, and testing, and performance improvement using a pre-trained DenseNet201 network. Data augmentation and data shuffling are used to free from lack of data availability during the training phase of the model. The proposed framework is more efficient and can predict the type of vegetables comparatively in less computational time (2 to 3 minutes) with an ‘Accuracy’ of 98.58%, ‘Sensitivity’ of 98.23%, and ‘Specificity’ of 94.25%.

show abstract

“…The class output uses a SoftMax (Sharma and Sharma, 2017) activation function with four outputs, one for each possible classification of landslide size. SoftMax was also chosen based on its common usage for multiclass classification models (Banerjee et al, 2020;Kumar et al, 2020).…”

Section: A1 Activation Functionsmentioning

confidence: 99%

On The Prediction of Landslide Occurrences and Sizesvia Hierarchical Neural Networks

Aguilera

Lombardo

Tanyaş

et al. 2022

Preprint

View full text Add to dashboard Cite

For more than three decades, the scientific community that studies landslides through data-driven models has focused on estimating where landslides occur across a given landscape. This concept is widely known as landslide susceptibility. And, it has seen a vast improvement from old bivariate statistical techniques to modern deep learning routines. Despite all these advancements, no spatially-explicit data-driven model is currently capable of also predicting how large landslides may be once they trigger in a specific study area. In this work, we exploit a model architecture that has already found a number of applications in landslide susceptibility. Specifically, we opt for the use of Neural Network (NN). But, instead of focusing exclusively on where landslides may occur, we extend this paradigm to also spatially predict classes of landslide sizes. As a result, we keep the traditional binary classification paradigm but we make use of it to complement the susceptibility estimates with a crucial information for landslide hazard assessment. We will refer to this model as Hierarchical Neural Network (HNN) throughout the manuscript. To test this analytical protocol, we use the Nepalese area where the Gorkha earthquake induced tens of thousands of landslides in 2014. The results we obtain are quite promising. The component of our HNN that estimates the susceptibility outperforms a binomial Generalized Linear Model (GLM) baseline we used as benchmark. We did this for a GLM represents the most common classifier in the landslide literature. Most importantly, our HNN also suitably performed across the entire procedure. As a result, the landslide-area-class prediction returned not just a single susceptibility map, as per tradition. But, it also produced several informative maps on the expected landslide size classes. Our vision is for administrations to consult these suite of model outputs and maps to better assess the risk to local communities and infrastructure. And, to promote the diffusion of our HNN, we are sharing the data and codes in the supplementary material in the hope that we would stimulate others to replicate similar analyses.

show abstract

Multiclass classification of nutrients deficiency of apple using deep neural network

Cited by 23 publications

References 13 publications

On the prediction of landslide occurrences and sizes via Hierarchical Neural Networks

On the prediction of landslide occurrences and sizes via Hierarchical Neural Networks

Automatic Framework for Vegetable Classification using Transfer-Learning

On The Prediction of Landslide Occurrences and Sizesvia Hierarchical Neural Networks

Contact Info

Product

Resources

About