Multiclass classification of nutrients deficiency of apple using deep neural network
- PDF / 4,183,415 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 46 Downloads / 218 Views
(0123456789().,-volV)(0123456789().,-volV)
S.I. : WORLDCIST’20
Multiclass classification of nutrients deficiency of apple using deep neural network Yogesh Kumar1 • Ashwani Kumar Dubey1
•
Rajeev Ratan Arora2 • Alvaro Rocha3
Received: 17 July 2020 / Accepted: 19 August 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Agriculture industry is the foundation of Indian economy where quality fruit production plays an important role. Apple or pome fruits are always in demand because of rich nutrients in it. Hence, to analyze and recognize the nutrients deficiency in fruits, a deep neural-based model is being proposed. This model automatically classifies and recognizes the type of deficiency present in apple. In this paper, a database has been created for four major types of nutrients deficiency in apples and used for training and validation of the proposed deep convolutional network. The model is tuned with k-fold crossvalidation. The hyper-parameters such as epoch are set at 100 and batch size kept at 5. Finally, the model is tested with the testing data and achieved an average accuracy of 98.24% with k-fold cross-validation set to 15. The model accuracy depends on the hyper-parameters. The process of features optimization reduces the risk of overfitting of the model. Hence, careful selection of hyper-parameters is important for the convergence of cost function to the global minima that results in minimum misclassification. Keywords Apple nutrients deficiency Convolutional neural network Deep learning Image recognition Image classification
1 Introduction Apple is one of the most demanding fruit in the world. Nutrients deficiency in apple has a devastating effect on apple production and is a major threat to the security of the fruit industry. Thus, the detection of nutrients deficiency & Ashwani Kumar Dubey [email protected] Yogesh Kumar [email protected] Rajeev Ratan Arora [email protected] Alvaro Rocha [email protected] 1
Department of Electronics and Communication Engineering, Amity School of Engineering and Technology, Amity University Uttar Pradesh, Noida, India
2
Department of Electronics and Communication Engineering, MVN University, Palwal, Haryana, India
3
ISEG, University of Lisbon, Rua do Quelhas, N8 6, 1200-781 Lisbon, Portugal
plays an important role in ensuring the high-quality standard of apple. The traditional method involves lots of experts’ experience and knowledge [1]. To improve the accuracy and rapid analysis, an automated apple nutrients deficiency diagnosis based on deep neural networks is developed. Deep learning has a key role in a wide range of critical applications like the agriculture industry where it provides potential solutions and sets a pillar for our future cultivation. This field is quite vast and growing rapidly. The highly complex problem in the agriculture industry in real-world is not practically possible and manually is solved by applying specialized algorithms. The learning approach is supervised in which the model is traine
Data Loading...
