International Conference on Computer and Knowledge Engineering

Home / 14th International Conference on Computer and Knowledge Engineering

Paddy Plant Stress Identification Using Few-Shot Learning Framework

Authors :

Ervin Gubin Moung¹ Pavindrah Naidu a/l Narayanasamy Naiidu² Maisarah Mohd Sufian³ Valentino Liaw⁴ Ali Farzamnia⁵ Lorita Angeline⁶

1- Faculty of Computing and Informatics University Malaysia Sabah 2- Faculty of Computing and Informatics, Universiti Malaysisa Sabah 3- Faculty of Computing and Informatics Universiti Malaysia Sabah 4- Faculty of Computing and Informatics Universiti Malaysia Sabah 5- School of Computing and Engineering University of Huddersfield 6- Faculty of Engineering Universiti Malaysisa Sabah

Keywords :

few-shot learning,،stress identification،smart agriculture،paddy leaves،accuracy،Convolutional Neural Network

Abstract :

The efficient identification of stress in paddy plant leaves is paramount for optimizing agricultural resources and ensuring robust crop yields in smart agriculture practices. This research explores the potential of few-shot learning (FSL) to address the inherent challenges posed by limited training data in stress identification. Three distinct FSL approaches - Siamese network, Matching network, and Model-Agnostic Meta Learning (MAML) - are evaluated for their accuracy in stress detection. The study begins with an introduction to the critical role of stress detection in smart agriculture and the current challenges associated with limited training data. It then delves into the methodology, involving five stages: dataset description, data pre-processing, implementation of FSL techniques for stress detection, accuracy evaluation, and final reporting. Among the FSL models, the Matching Network stands out with an impressive accuracy of 86% for 6-way 1-shot learning. This surpasses the performance of a Convolutional Neural Network (CNN) tested with a larger shot size (270-shots), which achieved an accuracy of 81%. These comparative results underscore the potential of FSL techniques in achieving precise stress identification, even when working with limited data. The overarching objective of this research is to contribute valuable insights towards enhancing the efficiency of stress prediction in paddy leaves, thereby fostering healthier and more productive paddy crop production in the evolving landscape of smart agriculture. The findings presented here aim to inform the development of effective stress detection systems and advance the field of precision agriculture.