Please login first
Deep Learning enabled Pest Detection System Using Sound Analytics in Internet of Agricultural Things
1 , * 2
1  Professor at Symbiosis Institute of Computer Studies and Research (SICSR), Symbiosis International (Deemed University), Pune, India.
2  Ph.D Scholar at School of Computing Science and Engineering, Galgotias University, Greater Noida, U.P, India & Assistant Professor, Dept. of CSE at Bangabandhu Sheikh Mujibur Rahman Science and Technology University, Gopalganj, Bangladesh
Academic Editor: Francisco Falcone

Abstract:

Around the globe, agriculture has grown to a point where it is now a financially feasible way to produce more sophisticated cultivation methods. Throughout the long tradition of agriculture, this represents a pivotal moment. The widespread adoption of data and the latest technological advances of the contemporary period allowed this paradigm change. However, pests remain to blame for significant harm done to crops, which has a detrimental impact on finances, the natural world, and society. This highlights the necessity of using automated techniques to apprehend pests before they cause widespread harm. Agriculture-related issues are currently the predominant subject for research that utilizes ML. The overarching aim of this investigation is the development of an economically feasible method for pest detection in vast fields of crops that IoT enables through the utilizes pest audio sound analytics. The recommended approach incorporates numerous acoustic preparation methods from audio sound analytics. The Chebyshev filter, the Welch method, non-overlap-add method, FFT, DFT, STFT, LPC algorithm, acoustic sensors, and PID sensors were among them. 800 pest sounds were examined for features and statistical measurements before being incorporated into Multilayer Perceptron (MLP) for training, testing, and validation. The experiment's outcomes demonstrated that the proposed MLP model triumphed over the currently available DenseNet, Faster RCNN, VGG-16, ResNet-50, YOLOv5, FE-Net, DCNN, MS-ALN, and SAFFPEST approaches alongside an accuracy of 99.78%, 99.91% sensitivity, 99.64% specificity, 99.59% recall, 99.82% F1 score, and 99.85% precision. The significance of the findings rests in their potential to proactively identify pests in large agriculture fields. As a result, the cultivation of crops will improve, leading to increased economic prosperity for agricultural producers, the country, and the entire globe.

Keywords: Internet of Agricultural Things; Deep Learning; Multilayer Perceptron; Pest Detection; Sound Analytics
Comments on this paper
AANJANKUMAR S
Much needed research on agriculture

Malathy Sathyamoorthy
Good content on pest detection and deep learning.



 
 
Top