Rice-net: an efficient artificial fish swarm optimization applied deep convolutional neural network model for identifyin
- PDF / 3,078,967 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 54 Downloads / 228 Views
(0123456789().,-volV)(0123456789().,-volV)
ORIGINAL ARTICLE
Rice-net: an efficient artificial fish swarm optimization applied deep convolutional neural network model for identifying the Oryza sativa diseases N. V. Raja Reddy Goluguri1,2 • K. Suganya Devi1
•
P. Srinivasan3
Received: 17 April 2020 / Accepted: 10 September 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract This research aims to identify rice diseases, namely Leaf blast, Brown spot, Healthy and Hispa. The purpose of this research is to utilize deep convolutional neural network (DCNN) with support vector machine (SVM), DCNN with artificial neural network (ANN) and DCNN with long short-term memory (LSTM). To enhance the performance of LSTM further, the research includes particle swarm optimization, artificial fish swarm optimization (AFSO) and efficient artificial fish swarm optimization (EAFSO) to identify optimal weights. This research also compares the proposed technique results with a conventional feature extraction approaches like texture, discrete wavelet transforms and color histogram with SVM, ANN and LSTM. The results exhibit the superiority of proposed DCNN-LSTM (EAFSO) technique over other techniques. The proposed technique EAFSO associates DCNN-LSTM identifies the rice diseases with 97.5% accuracy, which is better than DCNN-SVM and DCNN-ANN. Keywords Artificial intelligence (AI) Rice diseases Deep convolution neural network (DCNN) Long short-term memory (LSTM) Efficient artificial fish swarm optimization (EAFSO)
1 Introduction Today the world is devouring a species of swamp grass Oryza sativa more commonly known as Rice. It has very potential nutrients needed for human appetite, which has led to partial consumption, which, in effect, has made farmers all over the world take Oryza sativa farming very positively with an increase of 2.5% per year. In particular,
& K. Suganya Devi [email protected] N. V. Raja Reddy Goluguri [email protected] P. Srinivasan [email protected] 1
Computer Science and Engineering, National Institute of Technology Silchar, Silchar, Assam 788010, India
2
Information Technology, MVGR College of Engineering, Vizianagaram, Andhra Pradesh 535005, India
3
Department of Physics, National Institute of Technology Silchar, Silchar, Assam 788010, India
rice accounts for 80% of the calories consumed by humans in Asia. While there are claims that rice was first grown on the banks of the Chinese Yangtze River Valley. Today we can see rice being cultivated very much in every country and according to the information distributed by the United Nations Food and Agriculture Organization [1], the cumulative soil under Oryza sativa cultivation is approximately 160 million hectares, among which India contributes for 43.39 million hectares of rice cultivation, which is one quarter of what is cultivated all over the world. Apart from the fact that India retains a quarter of what is cultivated worldwide solely for rice cultivation, the country is falling behind in terms of produc
Data Loading...
