BILSTM HYBRID NETWORK TO ENHANCE CROP PEST CLASSIFICATION

Author (s) : M.Velmurugan, N.Karthigavani, R.Maruthamuthu, J.Sowmya

---

Abstract :
The agricultural sectors that produce rice, millet, maize, legumes, sugarcane, garbanzo, and onions suffer significant financial losses as a result of insect infestations. In order to reduce the amount of money lost to the bug, it is crucial to identify its species as soon as feasible. However, due to a lack of knowledge and experience, farmers find it challenging to distinguish between the various varieties of agricultural insects. Convolutional neural networks, or CNNs for short, are frequently used in conjunction with other computer-based methodologies to solve this problem. Because of their ability to automatically learn characteristics that depend on the information from the data themselves, CNNs are helpful for the identification of many photos.Keywords:Automation work flows, Air quality, PIC controller, urbanization. Within the scope of this study, we proposed a hybrid BiLSTM network as a potential solution to this problem. A pretrained model and a layer of bidirectional long short- term memories (BiLSTM) that takes temporal information into consideration are included in the architecture that has been recommended.

Keywords : Long Short-Term Memory, Convolutional Neural Network, Deep Learning.Keywords-component.

Conference Date : 30/08/2019

Pages : 212

Paper ID : 19203