Fusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification

Abstract Plant disease identification and detection refer to the process of recognizing and diagnosing diseases that affect plants. This process is crucial for maintaining plant health, maximizing crop yields, and preventing the spread of diseases to neighbouring plants. Various techniques have been...

Full description

Saved in:
Bibliographic Details
Main Authors: Kirti Kirti, Navin Rajpal, Virendra P. Vishwakarma, Pramod Kumar Soni
Format: Article
Language:English
Published: Springer 2025-07-01
Series:Discover Computing
Subjects:
Online Access:https://doi.org/10.1007/s10791-025-09679-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849761459860406272
author Kirti Kirti
Navin Rajpal
Virendra P. Vishwakarma
Pramod Kumar Soni
author_facet Kirti Kirti
Navin Rajpal
Virendra P. Vishwakarma
Pramod Kumar Soni
author_sort Kirti Kirti
collection DOAJ
description Abstract Plant disease identification and detection refer to the process of recognizing and diagnosing diseases that affect plants. This process is crucial for maintaining plant health, maximizing crop yields, and preventing the spread of diseases to neighbouring plants. Various techniques have been designed for plant disease identification with outstanding results. Still, it exhibits a prolonged convergence rate, taking much time to execute because of long iterations, consuming a large chunk of resources, and suffering local minimum problems. All these issues have emerged from the expansion of hidden layers and their parameters. In this work, a novel hybrid approach is proposed using a ResNet-50 based deep neural network integrated with a Kernel Extreme Learning Machine (KELM) classifier for efficient and accurate plant disease classification. Unlike conventional deep learning methods that rely on iterative training and heavy resources, our approach uses a non-iterative, single-pass KELM classifier to significantly reduce computational complexity while maintaining high classification performance. The method extracts deep, discriminative features via ResNet-50 and feeds them into a lightweight KELM for final classification. The performance of the proposed method is matched with the individual performance of ResNet50 and KELM, along with other Deep Learning (DL) frameworks. Experiments are conducted on the PlantVillage database, which has images of 14 different types of plants with 38 classes. The results obtained provide a nominal error rate of 1.05% using a non-iterative approach, which signifies that the ResNet-KELM method surpasses the existing techniques in terms of accuracy and efficiency.
format Article
id doaj-art-49219a7b03c34579b14101139f8b3306
institution DOAJ
issn 2948-2992
language English
publishDate 2025-07-01
publisher Springer
record_format Article
series Discover Computing
spelling doaj-art-49219a7b03c34579b14101139f8b33062025-08-20T03:06:01ZengSpringerDiscover Computing2948-29922025-07-0128112710.1007/s10791-025-09679-yFusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classificationKirti Kirti0Navin Rajpal1Virendra P. Vishwakarma2Pramod Kumar Soni3University School of Information, Communication and Technology, Guru Gobind Singh Indraprastha UniversityUniversity School of Information, Communication and Technology, Guru Gobind Singh Indraprastha UniversityUniversity School of Information, Communication and Technology, Guru Gobind Singh Indraprastha UniversityDepartment of Computer Applications, Manipal University JaipurAbstract Plant disease identification and detection refer to the process of recognizing and diagnosing diseases that affect plants. This process is crucial for maintaining plant health, maximizing crop yields, and preventing the spread of diseases to neighbouring plants. Various techniques have been designed for plant disease identification with outstanding results. Still, it exhibits a prolonged convergence rate, taking much time to execute because of long iterations, consuming a large chunk of resources, and suffering local minimum problems. All these issues have emerged from the expansion of hidden layers and their parameters. In this work, a novel hybrid approach is proposed using a ResNet-50 based deep neural network integrated with a Kernel Extreme Learning Machine (KELM) classifier for efficient and accurate plant disease classification. Unlike conventional deep learning methods that rely on iterative training and heavy resources, our approach uses a non-iterative, single-pass KELM classifier to significantly reduce computational complexity while maintaining high classification performance. The method extracts deep, discriminative features via ResNet-50 and feeds them into a lightweight KELM for final classification. The performance of the proposed method is matched with the individual performance of ResNet50 and KELM, along with other Deep Learning (DL) frameworks. Experiments are conducted on the PlantVillage database, which has images of 14 different types of plants with 38 classes. The results obtained provide a nominal error rate of 1.05% using a non-iterative approach, which signifies that the ResNet-KELM method surpasses the existing techniques in terms of accuracy and efficiency.https://doi.org/10.1007/s10791-025-09679-yDeep neural networkResNetPlant disease identificationKELMNon-iterative algorithmResidual network
spellingShingle Kirti Kirti
Navin Rajpal
Virendra P. Vishwakarma
Pramod Kumar Soni
Fusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
Discover Computing
Deep neural network
ResNet
Plant disease identification
KELM
Non-iterative algorithm
Residual network
title Fusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
title_full Fusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
title_fullStr Fusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
title_full_unstemmed Fusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
title_short Fusion of non-iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
title_sort fusion of non iterative deep neural network feature extraction with kernel extreme learning machine for plant disease classification
topic Deep neural network
ResNet
Plant disease identification
KELM
Non-iterative algorithm
Residual network
url https://doi.org/10.1007/s10791-025-09679-y
work_keys_str_mv AT kirtikirti fusionofnoniterativedeepneuralnetworkfeatureextractionwithkernelextremelearningmachineforplantdiseaseclassification
AT navinrajpal fusionofnoniterativedeepneuralnetworkfeatureextractionwithkernelextremelearningmachineforplantdiseaseclassification
AT virendrapvishwakarma fusionofnoniterativedeepneuralnetworkfeatureextractionwithkernelextremelearningmachineforplantdiseaseclassification
AT pramodkumarsoni fusionofnoniterativedeepneuralnetworkfeatureextractionwithkernelextremelearningmachineforplantdiseaseclassification