Deep learning models for automatic identification of plant-parasitic nematode

Shabrina, Nabila Husna; Lika, Ryukin Aranta; Indarti, Siwi

doi:10.1016/j.aiia.2022.12.002

Cited by 15 publications

(12 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several deep-learning models were employed to identify self-acquired Indonesian plant-parasitic nematode identification. This study obtained the highest accuracy of more than 90% [17][18][19].…”

Section: Introductionmentioning

confidence: 66%

“…The research workflow for identifying nematodes using hybrid convolution and attention models is depicted in Figure 1. The self-collected nematode dataset [17] was combined with the public dataset from the study [15]. The acquired dataset is then preprocessed using several techniques.…”

Section: Research Workflowmentioning

confidence: 99%

“…CoAtNet-0 was selected for this study because it demonstrated exceptional performance in image classification when compared to other models in the ImageNet benchmark [21]. This study incorporated the datasets from studies [15,17] and analyzed the performance of the CoAtNet-0 model with respect to both single and double-data augmentation. Five different image augmentation techniques, including noise addition, flipping (both horizontally and vertically), brightness change, blurring, and contrast adjustment, were selected.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Transfer Learning using Hybrid Convolution and Attention Model for Nematode Identification in Soil Ecology

Lika,

Shabrina,

Indarti

et al. 2023

RIA

View full text Add to dashboard Cite

Nematodes constitute a crucial component of soil ecosystems, contributing significantly to soil ecology. The ability to differentiate between non-parasitic and plant-parasitic species is a critical aspect of efficient crop management. However, manual identification methods are labor-intensive, time-consuming, and susceptible to errors. Recent developments in the realm of machine and deep learning have paved the way for their application in the field of nematode identification. This study implements a hybrid convolution and attention network, termed CoAtNet-0, which integrates a Convolutional Neural Network (CNN) and a transformer for the identification of nematode genera. The performance of this model is anticipated to be robust across various dataset sizes. The current investigation employed a combined dataset, comprising both a self-collected nematode dataset and a public dataset, to evaluate the performance of CoAtNet-0 under single and double data augmentation conditions. Furthermore, it explored the efficacy of the Adam, Stochastic Gradient Descent (SGD), and RMS optimizers to identify the most effective optimizer for the CoAtNet-0 model. Adam was selected due to its typically satisfactory performance, while SGD was chosen as it often delivers superior results in deep learning applications. RMSprop was utilized for performance comparison among adaptive optimizers devoid of momentum. Upon evaluation, it was determined that the highest performance was achieved by the CoAtNet-0 model using the SGD optimizer on the non-augmented dataset, delivering an accuracy of 97.22%. Thus, the selection of suitable data augmentation methods and an appropriate optimizer is instrumental in optimizing the performance of the CoAtNet-0 model for nematode identification.

show abstract

Section: Introductionmentioning

confidence: 66%

Section: Research Workflowmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning using Hybrid Convolution and Attention Model for Nematode Identification in Soil Ecology

Lika,

Shabrina,

Indarti

et al. 2023

RIA

View full text Add to dashboard Cite

show abstract

“…This approach, coupled with advances in machine learning also referred to as deep learning or artificial intelligence (AI), could open a new avenue for nematode ecological assessment in future ( Colin et al ., 2017 ; Bogale et al ., 2020 ). Indeed, the development of machine learning for the automated detection of a few morphological nematode traits and their immediate combination into a trait code could be even more easily calibrated than in case of genera ( Shabrina et al ., 2023 ) and species level ( Thevenoux et al ., 2021 ), allowing for the faster deployment of AI systems and the skipping of time-consuming steps in the usual identification process. Promising results have been documented in marine systems using the trait combination ( Semprucci et al ., 2022 ).…”

Section: Discussionmentioning

confidence: 99%

Simple, inexpensive, and rapid approach to detect changes in the structure of soil free-living nematodes

Semprucci,

Catani,

Grassi

et al. 2024

Helminthologia

View full text Add to dashboard Cite

Summary A general limitation of ecological investigations based on nematodes is related to the difficult and time-consuming taxonomic identification of species. Therefore, nematologists are investing many efforts to develop alternative approaches as proxies applicable in biomonitoring assessment. Recently, an alternative method that combines morpho-functional traits was proposed for detecting assemblage changes of marine nematodes. In view of the promising results, it was tested the same approach to document taxonomic structure changes of soil free-living and plant parasitic nematodes. Specifically, this attempt was carried out using three data sets that include studies from various European regions and different types of ecosystems: forests, grasslands and maize crops. Multivariate statistical analysis revealed that the simple combination of the four traits (i.e., buccal cavity cuticularization occurrence, amphideal fovea size and shape, morphology of the cuticle and pharynx) in a single code number perfectly mirrors the taxonomic structure trends of the nematode assemblage at genus level. Therefore, we predict that similar results can be also obtained by directly encoding nematode specimens with the selected traits and we point to new important advances if this procedure can be coupled with advanced machine learning.

show abstract

“…The next step will be to integrate these models into previously developed models that focused on the identification of specific nematode genera. The models presented in this paper delineate potential PPN in a heterologous sample, while other efforts have targeted specific nematode genera in “clean” homogenous samples ( Akintayo et al, 2018 ; Uhlemann et al, 2020 ; Qing et al, 2022 ; Shabrina et al, 2023 ).…”

Section: Discussionmentioning

confidence: 99%

Plant Parasitic Nematode Identification in Complex Samples with Deep Learning

Agarwal,

Curran,

et al. 2023

Journal of Nematology

View full text Add to dashboard Cite

Plant parasitic nematodes are significant contributors to yield loss worldwide, causing devastating losses to every crop species, in every climate. Mitigating these losses requires swift and informed management strategies, centered on identification and quantification of field populations. Current plant parasitic nematode identification methods rely heavily on manual analyses of microscope images by a highly trained nematologist. This mode is not only expensive and time consuming, but often excludes the possibility of widely sharing and disseminating results to inform regional trends and potential emergent issues. This work presents a new public dataset containing annotated images of plant parasitic nematodes from heterologous soil extractions. This dataset serves to propagate new automated methodologies or speedier plant parasitic nematode identification using multiple deep learning object detection models and offers a path towards widely shared tools, results, and meta-analyses.

show abstract

Deep learning models for automatic identification of plant-parasitic nematode

Cited by 15 publications

References 15 publications

Transfer Learning using Hybrid Convolution and Attention Model for Nematode Identification in Soil Ecology

Transfer Learning using Hybrid Convolution and Attention Model for Nematode Identification in Soil Ecology

Simple, inexpensive, and rapid approach to detect changes in the structure of soil free-living nematodes

Plant Parasitic Nematode Identification in Complex Samples with Deep Learning

Contact Info

Product

Resources

About