A novel insect and pest identification model based on a weighted multipath convolutional neural network and generative adversarial network

Vinita Abhishek Gupta, Department of Computer Applications, Bhilai Institute of Technology, Durg, (C.G.), IndiaFollow
M.V. Padmavati, Department of Computer Science and Engineering, Bhilai Institute of Technology, Durg, (C.G.), India
Ravi R. Saxena, Department of Statistics and Computer Science, Indira Gandhi Krishi Vishwavidyalaya, Raipur, (C.G.), India
Raunak Kumar Tamrakar, Department of Applied Physics, Bhilai Institute of Technology, Durg, (C.G.), India

Abstract

Timely identification of insects and their management play a significant role in sustainable agriculture development. The proposed hybrid model integrates a weighted multipath convolutional neural network and generative adversarial network to identify insects efficiently. To address the shortcomings of single-path networks, this novel model takes input from numerous iterations of the same image to learn more specific features. To avoid redundancy produced due to multipath, weights have been assigned to each path. For Xie2 dataset, the model shows 3.75%, 2.74%, 1.54%, 1.76%, 1.76%, 2.74 %, and 2.14% performance improvement from AlexNet, ResNet50, ResNet101, GoogleNet, VGG-16, VGG-19, and simple CNN respectively. To the best of our knowledge, no researchers have used a multipath convolution neural network in insect identification.

Recommended Citation

Gupta, Vinita Abhishek; Padmavati, M.V.; Saxena, Ravi R.; and Tamrakar, Raunak Kumar (2023) "A novel insect and pest identification model based on a weighted multipath convolutional neural network and generative adversarial network," Karbala International Journal of Modern Science: Vol. 9 : Iss. 1 , Article 14.
Available at: https://doi.org/10.33640/2405-609X.3280