Potato Leaf Disease Detection and Classification With Weighted Ensembling of YOLOv8 Variants DOI

M. Muthulakshmi,

N Aishwarya,

Rakesh Kumar

и другие.

Journal of Phytopathology, Год журнала: 2024, Номер 172(6)

Опубликована: Ноя. 1, 2024

ABSTRACT The identification and control of potato leaf diseases pose considerable difficulties for worldwide agriculture, affecting both the quality yield crops. Addressing this issue, we investigate efficacy lightweight YOLOv8 variants, namely YOLOv8n, YOLOv8s YOLOv8m, automated detection classification different states. These conditions are categorised into three types: healthy, early blight disease late disease. Our findings show that YOLOv8n achieves a mean average precision (mAP) 94.2%, mAP 93.4%, YOLOv8m 94%. Building on these results, propose novel weighted ensembling technique based confidence score (WECS) to combine predictions variants. WECS efficiently leverages advantages each variant by assigning weights scores individual model predictions. forecasts then combined produce final ensemble prediction sample. Achieving 99.9% 89.6% recall, method attains global Average Precision 96.3%, showcasing its robustness in real‐world applications.

Язык: Английский

Emerging Developments in Real-Time Edge AIoT for Agricultural Image Classification DOI Creative Commons
Maurizio Pintus,

Felice Colucci,

Fabio Maggio

и другие.

IoT, Год журнала: 2025, Номер 6(1), С. 13 - 13

Опубликована: Фев. 10, 2025

Advances in deep learning (DL) models and next-generation edge devices enable real-time image classification, driving a transition from the traditional, purely cloud-centric IoT approach to edge-based AIoT, with cloud resources reserved for long-term data storage in-depth analysis. This innovation is transformative agriculture, enabling autonomous monitoring, localized decision making, early emergency detection, precise chemical application, thereby reducing costs minimizing environmental health impacts. The workflow of an AIoT system agricultural monitoring involves two main steps: optimal training tuning DL through extensive experiments on high-performance AI-specialized computers, followed by effective customization deployment advanced devices. review highlights key challenges practical applications, including: (i) limited availability data, particularly due seasonality, addressed public datasets synthetic generation; (ii) selection state-of-the-art computer vision algorithms that balance high accuracy compatibility resource-constrained devices; (iii) algorithm optimization integration hardware accelerators inference; (iv) recent advancements AI classification that, while not yet fully deployable, offer promising near-term improvements performance functionality.

Язык: Английский

Процитировано

1
Characterization of Fungal Species Isolated from Cankered Apple Barks Demonstrates the Alternaria alternata Causing Apple Canker Disease DOI Creative Commons
Zhiqiang Li, Hao Li,

Jiating Zhang

и другие.

Journal of Fungi, Год журнала: 2024, Номер 10(8), С. 536 - 536

Опубликована: Июль 31, 2024

Apple canker disease, also named as apple Valsa canker, is one of the most destructive diseases for apples (Malus domestica Borkh.). Cytospora/Valsa spp. are dominant causal agent this but many studies have revealed that fungi from some other genus can cause typical symptoms. In study, we performed fungal pathogen isolation cankered ‘Fuji’ barks. Six representative morphologically different (Strain 1–6) were further subjected to ITS sequencing and evolutionary analysis. Molecular identification results Strains 1–6 Cytospora mali, Fusarium cf. solani, Alternaria alternata, C. Diplodia seriata F. proliferatum, respectively. All these been reported be agents diseases. By inoculating plugs onto trunks trees, pathogenicity six accessed. Only inoculations two mali strains 1 Strain 4) A. alternata strain 3) resulted in symptoms trunks. It worth noting caused much more severe higher incidence than fungi. has identified a causing on fruits leaves. assessing its leaves, verified it fruit rot leaf spot To best our knowledge, first report disease by China. Our present study provide theoretical foundation prevention control disease.

Язык: Английский

Процитировано

4
Algorithms for Plant Monitoring Applications: A Comprehensive Review DOI Creative Commons
Giovanni Paolo Colucci, Paola Battilani, Marco Camardo Leggieri

и другие.

Algorithms, Год журнала: 2025, Номер 18(2), С. 84 - 84

Опубликована: Фев. 5, 2025

Many sciences exploit algorithms in a large variety of applications. In agronomy, amounts agricultural data are handled by adopting procedures for optimization, clustering, or automatic learning. this particular field, the number scientific papers has significantly increased recent years, triggered scientists using artificial intelligence, comprising deep learning and machine methods bots, to process crop, plant, leaf images. Moreover, many other examples can be found, with different applied plant diseases phenology. This paper reviews publications which have appeared past three analyzing used classifying agronomic aims crops applied. Starting from broad selection 6060 papers, we subsequently refined search, reducing 358 research articles 30 comprehensive reviews. By summarizing advantages applying analyses, propose guide farming practitioners, agronomists, researchers, policymakers regarding best practices, challenges, visions counteract effects climate change, promoting transition towards more sustainable, productive, cost-effective encouraging introduction smart technologies.

Язык: Английский

Процитировано

0
Transforming Pest Management with Artificial Intelligence Technologies: The Future of Crop Protection DOI

E. Vidya Madhuri,

J. S. Rupali,

S. P. Sharan

и другие.

Deleted Journal, Год журнала: 2025, Номер 77(2)

Опубликована: Фев. 19, 2025

Язык: Английский

Процитировано

0
Hyperparameter optimization of apple leaf dataset for the disease recognition based on the YOLOv8 DOI Creative Commons
Yong-Suk Lee, Maheshkumar Prakash Patil,

Jeong Gyu Kim

и другие.

Journal of Agriculture and Food Research, Год журнала: 2025, Номер unknown, С. 101840 - 101840

Опубликована: Март 1, 2025

Язык: Английский

Процитировано

0
Hyperspectral Imaging Combined with Deep Learning for the Early Detection of Strawberry Leaf Gray Mold Disease DOI Creative Commons

Yunmeng Ou,

Jingyi Yan,

Zhiyan Liang

и другие.

Agronomy, Год журнала: 2024, Номер 14(11), С. 2694 - 2694

Опубликована: Ноя. 15, 2024

The presence of gray mold can seriously affect the yield and quality strawberries. Due to their susceptibility rapid spread this disease, it is important develop early, accurate, rapid, non-destructive disease identification strategies. In study, early detection strawberry leaf diseases was performed using hyperspectral imaging combining multi-dimensional features like spectral fingerprints vegetation indices. Firstly, images healthy affected leaves (24 h) were acquired a system. Then, reflectance (616) index (40) extracted. Next, CARS algorithm used extract fingerprint (17). Pearson correlation analysis combined with SPA method select five significant Finally, we deep learning methods (LSTMs, CNNs, BPFs, KNNs) build models for strawberries based on individual fusion characteristics. results showed that accuracy recognition model fused ranged from 88.9% 96.6%. CNN best, Overall, feature-based reduce dimensionality classification data effectively improve predicting precision algorithm.

Язык: Английский

Процитировано

2
Potato Leaf Disease Detection and Classification With Weighted Ensembling of YOLOv8 Variants DOI

M. Muthulakshmi,

N Aishwarya,

Rakesh Kumar

и другие.

Journal of Phytopathology, Год журнала: 2024, Номер 172(6)

Опубликована: Ноя. 1, 2024

ABSTRACT The identification and control of potato leaf diseases pose considerable difficulties for worldwide agriculture, affecting both the quality yield crops. Addressing this issue, we investigate efficacy lightweight YOLOv8 variants, namely YOLOv8n, YOLOv8s YOLOv8m, automated detection classification different states. These conditions are categorised into three types: healthy, early blight disease late disease. Our findings show that YOLOv8n achieves a mean average precision (mAP) 94.2%, mAP 93.4%, YOLOv8m 94%. Building on these results, propose novel weighted ensembling technique based confidence score (WECS) to combine predictions variants. WECS efficiently leverages advantages each variant by assigning weights scores individual model predictions. forecasts then combined produce final ensemble prediction sample. Achieving 99.9% 89.6% recall, method attains global Average Precision 96.3%, showcasing its robustness in real‐world applications.

Язык: Английский

Процитировано

0