Peacock Spot Detection in Olive Leaves Using Self Supervised Learning in an Assembly Meta-Architecture

Spilocaea oleagina is a common and dangerous fungal disease in olive trees that significantly reduces olive production. The early and accurate detection of this disease is essential for implementing effective control measures. In this study, we propose the creation of a new meta-architecture for ide...

Full description

Saved in:
Bibliographic Details
Main Authors: Saul Huaquipaco, Oscar Vera, Victor Yana-Mamani, Wilson Mamani, Helarf Calsina, Flavio Puma, Eli Morales-Rojas, Norman Beltran, Jose Cruz
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10776944/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850242725524275200
author Saul Huaquipaco
Oscar Vera
Victor Yana-Mamani
Wilson Mamani
Helarf Calsina
Flavio Puma
Eli Morales-Rojas
Norman Beltran
Jose Cruz
author_facet Saul Huaquipaco
Oscar Vera
Victor Yana-Mamani
Wilson Mamani
Helarf Calsina
Flavio Puma
Eli Morales-Rojas
Norman Beltran
Jose Cruz
author_sort Saul Huaquipaco
collection DOAJ
description Spilocaea oleagina is a common and dangerous fungal disease in olive trees that significantly reduces olive production. The early and accurate detection of this disease is essential for implementing effective control measures. In this study, we propose the creation of a new meta-architecture for identifying peacock spots on olive leaves. This new meta-architecture integrates Xception and VGG16 as the basis for the methodology employed in this study. Furthermore, a machine learning approach was used to pretrain the model in an unsupervised manner, thereby improving its generalization capacity. Metrics such as Kappa (K), True Skill Statistic (TSS), Proportion of Expected Success (Pe), Threat Index (Ts), and the Heidke Skill Score (HSS) were used to validate the model results. Based on these indicators, we evaluated the robustness, accuracy, and ability of the model to identify peacock spots. The testing results showed that the suggested meta-architecture, named SSL-XceVNet, substantially outperformed the baseline XceVNet model (88.24%) in detecting peacock spots, with an accuracy of 95.22%. The validation measurement results (K, 73.57%; TSS, 72.66%; Pe, 55.06%; Ts, 90.71%; HSS, 90.44%) attested to the efficacy and resilience of the suggested model, underscoring its ability to generalize and produce accurate predictions under a variety of circumstances. In conclusion, the combination of Xception and VGG16 into a new meta-architecture added the strengths of both models, and self-supervised learning helped learn meaningful representations without the need for explicit labels.
format Article
id doaj-art-9502613e63d5415b9b4acd5e2beaac8f
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-9502613e63d5415b9b4acd5e2beaac8f2025-08-20T02:00:13ZengIEEEIEEE Access2169-35362024-01-011219282819283910.1109/ACCESS.2024.351145610776944Peacock Spot Detection in Olive Leaves Using Self Supervised Learning in an Assembly Meta-ArchitectureSaul Huaquipaco0https://orcid.org/0000-0003-2323-3061Oscar Vera1https://orcid.org/0000-0002-1996-8471Victor Yana-Mamani2https://orcid.org/0000-0003-0982-2353Wilson Mamani3https://orcid.org/0000-0002-5408-4284Helarf Calsina4https://orcid.org/0000-0002-8565-805XFlavio Puma5https://orcid.org/0009-0001-6451-8381Eli Morales-Rojas6https://orcid.org/0000-0002-8623-3192Norman Beltran7https://orcid.org/0000-0002-1597-2991Jose Cruz8https://orcid.org/0000-0002-5201-0265School of Ingeniería de Sistemas e Informática, Faculty of Engineering, Universidad Nacional de Moquegua, Moquegua, PeruSchool of Ingeniería de Sistemas e Informática, Faculty of Engineering, Universidad Nacional de Moquegua, Moquegua, PeruSchool of Ingeniería de Sistemas e Informática, Faculty of Engineering, Universidad Nacional de Moquegua, Moquegua, PeruUniversidad de Alicante, Alicante, SpainSchool of Ingeniería Mecatrónica, Faculty of Engineering, Universidad Nacional de Juliaca, Juliaca, PeruPostgraduate Unit of EPG-UNA-PUNO, Universidad Nacional del Altiplano de Puno, Puno, PeruFaculty of Ingeniería de Sistemas y Mecánica Eléctrica, Universidad Nacional Toribio Rodríguez de Mendoza de Amazonas, Chachapoyas, PeruSchool of Ingeniería Electrónica, Faculty of FIMEES, Universidad Nacional del Altiplano de Puno, Puno, PeruSchool of Ingeniería Electrónica, Faculty of FIMEES, Universidad Nacional del Altiplano de Puno, Puno, PeruSpilocaea oleagina is a common and dangerous fungal disease in olive trees that significantly reduces olive production. The early and accurate detection of this disease is essential for implementing effective control measures. In this study, we propose the creation of a new meta-architecture for identifying peacock spots on olive leaves. This new meta-architecture integrates Xception and VGG16 as the basis for the methodology employed in this study. Furthermore, a machine learning approach was used to pretrain the model in an unsupervised manner, thereby improving its generalization capacity. Metrics such as Kappa (K), True Skill Statistic (TSS), Proportion of Expected Success (Pe), Threat Index (Ts), and the Heidke Skill Score (HSS) were used to validate the model results. Based on these indicators, we evaluated the robustness, accuracy, and ability of the model to identify peacock spots. The testing results showed that the suggested meta-architecture, named SSL-XceVNet, substantially outperformed the baseline XceVNet model (88.24%) in detecting peacock spots, with an accuracy of 95.22%. The validation measurement results (K, 73.57%; TSS, 72.66%; Pe, 55.06%; Ts, 90.71%; HSS, 90.44%) attested to the efficacy and resilience of the suggested model, underscoring its ability to generalize and produce accurate predictions under a variety of circumstances. In conclusion, the combination of Xception and VGG16 into a new meta-architecture added the strengths of both models, and self-supervised learning helped learn meaningful representations without the need for explicit labels.https://ieeexplore.ieee.org/document/10776944/Spilocaea oleaginaself-supervised learningVGG16XceptionXceVNet
spellingShingle Saul Huaquipaco
Oscar Vera
Victor Yana-Mamani
Wilson Mamani
Helarf Calsina
Flavio Puma
Eli Morales-Rojas
Norman Beltran
Jose Cruz
Peacock Spot Detection in Olive Leaves Using Self Supervised Learning in an Assembly Meta-Architecture
IEEE Access
Spilocaea oleagina
self-supervised learning
VGG16
Xception
XceVNet
title Peacock Spot Detection in Olive Leaves Using Self Supervised Learning in an Assembly Meta-Architecture
title_full Peacock Spot Detection in Olive Leaves Using Self Supervised Learning in an Assembly Meta-Architecture
title_fullStr Peacock Spot Detection in Olive Leaves Using Self Supervised Learning in an Assembly Meta-Architecture
title_full_unstemmed Peacock Spot Detection in Olive Leaves Using Self Supervised Learning in an Assembly Meta-Architecture
title_short Peacock Spot Detection in Olive Leaves Using Self Supervised Learning in an Assembly Meta-Architecture
title_sort peacock spot detection in olive leaves using self supervised learning in an assembly meta architecture
topic Spilocaea oleagina
self-supervised learning
VGG16
Xception
XceVNet
url https://ieeexplore.ieee.org/document/10776944/
work_keys_str_mv AT saulhuaquipaco peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture
AT oscarvera peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture
AT victoryanamamani peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture
AT wilsonmamani peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture
AT helarfcalsina peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture
AT flaviopuma peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture
AT elimoralesrojas peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture
AT normanbeltran peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture
AT josecruz peacockspotdetectioninoliveleavesusingselfsupervisedlearninginanassemblymetaarchitecture