HYBRID NEURAL NETWORK BASED ON SFAM AND CNN FOR GRAPE LEAF DISEASE DIAGNOSIS
Keywords:
Plant disease diagnosis, simplify fuzzy adaptive resonance theory map, convolutional neural network, 2 level convolutional simplify fuzzy adaptive resonance theory mapAbstract
Agricultural industry plays an important role in Thailand as its production has an impact on the domestic economy and exportation. Well-timed control and management of various factors causing plant diseases are essential to help the quality control of products and reduce damage such as the outbreak of plant diseases. However, the stage identification of occurring diseases is complicated for selecting the appropriate chemicals for treatment or controlling their amount possibly affects soil and water quality in the surrounding environment. To reduce the mentioned problem, this paper presents the AI system which can accurately diagnose as well as consider the disease characteristics. Besides, this system can also be used to identify the disease type and the time that firstly found disease. The architecture model of Simplify Fuzzy Adaptive Resonance Theory Map (SFAM) is developed to learn and remember the 2-levels of the information in the process of recognizing occurring diseases and their stage on grape leaves. In this paper, the hybrid algorithm is used for diagnosing grape leaf diseases from real-life images in the actual surroundings by using the combination between the SFAM and the Convolutional Neural Network (CNN). This algorithm can be called 2-Levels Convolutional Simplify Fuzzy Adaptive Resonance Theory Map (2LCSFAM). The Grape leaf is tested for the diagnosis of 3 grape leaf diseases including Downey, Rust, and Scap. The test results showed the accuracy value equals 87.14 percent in average. Thus, the proposed system can efficiently identify the types of the diseases and stages of infection by using only the image from the Grape leaf.
References
Aitkenhead, M.J., Dalgetty, I.A., Mullins, C.E., McDonald, A.J.S., and Strachan, N.J.C. (2003). Weed and crop discrimination using image analysis and artificial intelligence methods. Computers and Electronics in Agriculture., 39:157-171.
Amandeep, Bhattacharjee, A., Das, P., Basu, D., Roy, S., Ghosh, S., Saha, S. ,Pain , S., and Dey, S. (2017). Smart farming using IOT. 8th IEEE annual information technology. Electronics and Mobile Communication Conference (IEMCON), p. 278-280.
Burks, T.F., Shearer, S.A., and Payne, F.A. (2000). Classification of week species using color texture features and discriminant analysis. American Society of Agricultural Engineers (ASAE), p. 441-448.
Cires, D.C., Meier, U., Masci, J., Gambardella, L.M., and Schmidhuber, J. (2011). Flexible, high performance convolutional neural networks for image classification. Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, p. 1,237-1,242.
Dong, G. and Xie, M. (2005). Color clustering and learning for image segmentation based on neural networks. IEEE Trans. Neural Net., p. 925-936.
Dwarkani, C.M., Ganesh, R.R., Jagannathan, S., and Priyatharshini, R. (2015). Smart farming system using sensors for agricultural task automation. IEEE Technolo. Inno. ICT Agricul. Rural Develop. (TIAR), p. 49-53.
Gong, Y., Wang, L., Guo, R., and Lazebnik, S. (2014). Multi-scale orderless pooling of deep convolutional activation features. European conference on computer vision., 13:392-407.
He, K., Zhang, X., Ren, S., and Sun, J. (2014). Spatial pyramid pooling in deep convolutional networks for visual recognition. European Conference on Computer Vision (ECCV), p. 346-361.
Huang, K.Y. (2007). Application of artificial neural network for detecting Phalaenopsis seedling diseases using color and texture features. Computers and Electronics in Agriculture., 57:3-11.
Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2013). ImageNet classification with deep convolutional neural networks. Adv. Neural Inform. Proc. Syst. (NIPS 2012), p. 1,097-1,105
Long, J., Shelhamer, E., and Darrell, T. (2015). Fully convolutional networks for semantic segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), p. 3,431-3,440.
Meunkaewjinda, A., Kumsawat, P., Attakitmongcol, K., and Srikaew, A. (2008). Grape leaf disease detection from color imagery using hybrid intelligent system. 5th International Conference on Electrical Engineering Electronics, Computer, Telecommunications and Information Technology, p. 513-516.
Orillo, J.W., Cruz, J.D., Agapito, L., and Satimbre P.J. (2014). Identification of Diseases in Rice Plant (Oryza Sativa) using Back Propagation Artificial Neural Network. International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management (HNICEM), p. 1-6
Ramya, R., Sandhya, C., and Shwetha, R. (2017). Smart farming systems Using sensors. IEEE Technological Innovations in ICT for Agriculture and Rural Development (TIAR), p. 218-222.
Simonyan, K., and Zisserman, A., (2015). Very Deep Convolutional Networks for Large-scale Image Recognition., International Conference on Learning Representations (ICLR), arXiv preprint arXiv:1409.1556.
Song, Y., Diao, Z., Wang ,Y., and Wang, H. (2012). Image Feature Extraction of Crop Disease. IEEE Symposium on Electrical & Electronics Engineering (EEESYM), p. 448-451.
