With the rapid development of agriculture in China, the area of crop diseases is expanding and showing a growing trend year by year. However, the traditional recognition methods are inefficient and inaccurate. In order to improve the quality of agricultural products and reduce the economic loss rate, it is necessary to effectively classify crops to achieve efficient production and minimize the loss, so as to achieve the desired effect. This paper mainly introduces the application of several new algorithms based on convolution neural network model, fuzzy comprehensive evaluator and artificial neuron feature extraction technology in agriculture. The experimental results show that this method can identify disease information better. The test results show that the crop disease model synthesis can achieve a high recognition rate of 0.96. Because the number of samples of some categories is small, the category characteristics are weak, and the recognition rate of the model for such samples is low, so it is necessary to increase the number and diversity of samples to improve the recognition ability of the model for crop diseases.

Asia Kavita. Crop Disease Identification Method Based on Convolution Neural Network. International Journal of Neural Network (2021), Vol. 2, Issue 4: 32-40. https://doi.org/10.38007/NN.2021.020405.

[1] Anastasia Iskhakova, Daniyar Volf, Roman V. Meshcheryakov:Method for Reducing the Feature Space Dimension in Speech Emotion Recognition Using Convolutional Neural Networks.  Autom.  Remote.  Control.  83(6): 857-868 (2021). https://doi.org/10.1134/S0005117922060042

[2] Mehdi Abdollahpour, Tohid Yousefi Rezaii, Ali Farzamnia, Ismail Saad:A Two-Stage Learning Convolutional Neural Network for Sleep Stage Classification Using a Filterbank and Single Feature.  IEEE Access 10: 60597-60609 (2021). https://doi.org/10.1109/ACCESS.2021.3180730

[3] Myasar Mundher Adnan, Mohd Shafry Mohd Rahim, Amjad Rehman Khan, Tanzila Saba, Suliman Mohamed Fati, Saeed Ali Bahaj:An Improved Automatic Image Annotation Approach Using Convolutional Neural Network-Slantlet Transform.  IEEE Access 10: 7520-7532 (2021). https://doi.org/10.1109/ACCESS.2021.3140861

[4] Sonam Aggarwal, Sheifali Gupta, Ramani Kannan, Rakesh Ahuja, Deepali Gupta, Sapna Juneja, Samir Brahim Belhaouari:A Convolutional Neural Network-Based Framework for Classification of Protein Localization Using Confocal Microscopy Images.  IEEE Access 10: 83591-83611 (2021). https://doi.org/10.1109/ACCESS.2021.3197189

[5] Michael Opoku Agyeman, Andres Felipe Guerrero, Quoc-Tuan Vien:Classification Techniques for Arrhythmia Patterns Using Convolutional Neural Networks and Internet of Things (IoT) Devices.  IEEE Access 10: 87387-87403 (2021). https://doi.org/10.1109/ACCESS.2021.3192390

[6] Adal A. Alashban, Al-Hanouf Al-Aljmi, Norah F. Alhussainan, Ridha Ouni:Single Convolutional Neural Network With Three Layers Model for Crowd Density Estimation.  IEEE Access 10: 63823-63833 (2021). https://doi.org/10.1109/ACCESS.2021.3180738

[7] Anaam Ansari, Tokunbo Ogunfunmi:Hardware Acceleration of a Generalized Fast 2-D Convolution Method for Deep Neural Networks.  IEEE Access 10: 16843-16858 (2021). https://doi.org/10.1109/ACCESS.2021.3149505

[8] Eoin Brophy, Bryan M. Hennelly, Maarten De Vos, Geraldine B. Boylan, Tomás Ward:Improved Electrode Motion Artefact Denoising in ECG Using Convolutional Neural Networks and a Custom Loss Function.  IEEE Access 10: 54891-54898 (2021). https://doi.org/10.1109/ACCESS.2021.3176971

[9] Asghar Ali Chandio, Md. Asikuzzaman, Mark R. Pickering, Mehjabeen Leghari:Cursive Text Recognition in Natural Scene Images Using Deep Convolutional Recurrent Neural Network.  IEEE Access 10: 10062-10078 (2021). https://doi.org/10.1109/ACCESS.2021.3144844

[10] Minho Choi, Sang-Jin Lee:Oscillometry-Based Blood Pressure Estimation Using Convolutional Neural Networks.  IEEE Access 10: 56813-56822 (2021). https://doi.org/10.1109/ACCESS.2021.3177539

[11] Suci Dwijayanti, Muhammad Iqbal, Bhakti Yudho Suprapto:Real-Time Implementation of Face Recognition and Emotion Recognition in a Humanoid Robot Using a Convolutional Neural Network.  IEEE Access 10: 89876-89886 (2021). https://doi.org/10.1109/ACCESS.2021.3200762

[12] Ali Pourramezan Fard, Joe Ferrantelli, Anne-Lise Dupuis, Mohammad H. Mahoor:Sagittal Cervical Spine Landmark Point Detection in X-Ray Using Deep Convolutional Neural Networks.  IEEE Access 10: 59413-59427 (2021). https://doi.org/10.1109/ACCESS.2021.3180028

[13] Ahmed Y. Hatata, Mohammed Abd-Elnaby, Bishoy E. Sedhom:Adaptive Protection Scheme for FREEDM Microgrid Based on Convolutional Neural Network and Gorilla Troops Optimization Technique.  IEEE Access 10: 55583-55601 (2021). https://doi.org/10.1109/ACCESS.2021.3177544

[14] Jamal F. Hwaidi, Thomas M. Chen:Classification of Motor Imagery EEG Signals Based on Deep Autoencoder and Convolutional Neural Network Approach.  IEEE Access 10: 48071-48081 (2021). https://doi.org/10.1109/ACCESS.2021.3171906

[15] Svetlana Illarionova, Dmitrii Shadrin, Vladimir Ignatiev, Sergey Shayakhmetov, Alexey Trekin, Ivan V. Oseledets:Estimation of the Canopy Height Model From Multispectral Satellite Imagery With Convolutional Neural Networks.  IEEE Access 10: 34116-34132 (2021). https://doi.org/10.1109/ACCESS.2021.3161568

[16] Andac Imak, Adalet Celebi, Kamran Siddique, Muammer Turkoglu, Abdulkadir Sengür, Iftekhar Salam:Dental Caries Detection Using Score-Based Multi-Input Deep Convolutional Neural Network.  IEEE Access 10: 18320-18329 (2021). https://doi.org/10.1109/ACCESS.2021.3150358

[17] Ahmed H. Janabi, Triantafyllos Kanakis, Mark Johnson:Convolutional Neural Network Based Algorithm for Early Warning Proactive System Security in Software Defined Networks.  IEEE Access 10: 14301-14310 (2021). https://doi.org/10.1109/ACCESS.2021.3148134

[18] Joonhyun Jeong, Incheon Cho, Eunseop Shin, Sung-Ho Bae:A New Pointwise Convolution in Deep Neural Networks Through Extremely Fast and Non Parametric Transforms.  IEEE Access 10: 88251-88262 (2021). https://doi.org/10.1109/ACCESS.2021.3197219