Machine/deep learning techniques for disease and nutrient deficiency disorder diagnosis in rice crops: A systematic review

Biosystems Engineering, Journal Year: 2024, Volume and Issue: 244, P. 77 - 92

Published: June 7, 2024

Language: Английский

---

Monitoring system for peanut leaf disease based on a lightweight deep learning model

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 222, P. 109055 - 109055

Published: May 22, 2024

Language: Английский

---

Machine Learning Application in Horticulture and Prospects for Predicting Fresh Produce Losses and Waste: A Review

Plants, Journal Year: 2024, Volume and Issue: 13(9), P. 1200 - 1200

Published: April 25, 2024

The current review examines the state of knowledge and research on machine learning (ML) applications in horticultural production potential for predicting fresh produce losses waste. Recently, ML has been increasingly applied horticulture efficient accurate operations. Given health benefits need food nutrition security, postharvest management are important. This aims to assess application preharvest reducing waste by their magnitude, which is crucial practices policymaking loss reduction. starts assessing horticulture. It then presents handling processing, lastly, prospects its quantification. findings revealed that several algorithms perform satisfactorily classification prediction tasks. Based that, there a further investigate suitability more models or combination with higher prediction. Overall, suggested possible future directions related

Language: Английский

---

Advancements in rice disease detection through convolutional neural networks: A comprehensive review

Heliyon, Journal Year: 2024, Volume and Issue: 10(12), P. e33328 - e33328

Published: June 1, 2024

This review paper addresses the critical need for advanced rice disease detection methods by integrating artificial intelligence, specifically convolutional neural networks (CNNs). Rice, being a staple food large part of global population, is susceptible to various diseases that threaten security and agricultural sustainability. research significant as it leverages technological advancements tackle these challenges effectively. Drawing upon diverse datasets collected across regions including India, Bangladesh, Türkiye, China, Pakistan, this offers comprehensive analysis efforts in using CNNs. While some are universally prevalent, many vary significantly growing region due differences climate, soil conditions, practices. The primary objective explore application AI, particularly CNNs, precise early identification diseases. literature includes detailed examination data sources, datasets, preprocessing strategies, shedding light on geographic distribution collection profiles contributing researchers. Additionally, synthesizes information algorithms models employed detection, highlighting their effectiveness addressing complexities. thoroughly evaluates hyperparameter optimization techniques impact model performance, emphasizing importance fine-tuning optimal results. Performance metrics such accuracy, precision, recall, F1 score rigorously analyzed assess effectiveness. Furthermore, discussion section critically examines associated with current methodologies, identifies opportunities improvement, outlines future directions at intersection machine learning detection. review, analyzing total 121 papers, underscores significance ongoing interdisciplinary meet evolving technology needs enhance security.

Language: Английский

---

A systematic review of deep learning applications for rice disease diagnosis: current trends and future directions

Frontiers in Computer Science, Journal Year: 2024, Volume and Issue: 6

Published: Sept. 11, 2024

Background The occurrence of diseases in rice leaves presents a substantial challenge to farmers on global scale, hence jeopardizing the food security an expanding population. timely identification and prevention these are utmost importance order mitigate their impact. Methods present study conducts comprehensive evaluation contemporary literature pertaining diseases, covering period from 2008 2023. process selecting pertinent studies followed guidelines outlined by Kitchenham, which ultimately led inclusion 69 for purpose review. It is worth mentioning that significant portion research endeavours have been directed towards studying such as brown spot, blast, bacterial blight. primary performance parameter emerged was accuracy. Researchers strongly advocated combination hybrid deep learning machine methodologies improve rates recognition leaf diseases. Results collection scholarly investigations focused detection characterization affecting leaves, with specific emphasis prominence accuracy measure highlights precision diagnosis Furthermore, efficacy employing combine techniques exemplified enhancing capacities leaves. Conclusion This systematic review provides insight into conducted scholars field disease during previous decade. text underscores significance calls implementation augment identification, presenting possible resolutions obstacles presented agricultural hazards.

Language: Английский

---

Rice Leaf Disease Classification—A Comparative Approach Using Convolutional Neural Network (CNN), Cascading Autoencoder with Attention Residual U-Net (CAAR-U-Net), and MobileNet-V2 Architectures

Technologies, Journal Year: 2024, Volume and Issue: 12(11), P. 214 - 214

Published: Oct. 29, 2024

Classifying rice leaf diseases in agricultural technology helps to maintain crop health and ensure a good yield. In this work, deep learning algorithms were, therefore, employed for the identification classification of from images crops field. The initial algorithmic phase involved image pre-processing images, using bilateral filter improve quality. effectiveness step was measured by metrics like Structural Similarity Index (SSIM) Peak Signal-to-Noise Ratio (PSNR). Following this, work advanced neural network architectures classification, including Cascading Autoencoder with Attention Residual U-Net (CAAR-U-Net), MobileNetV2, Convolutional Neural Network (CNN). proposed CNN model stood out, since it demonstrated exceptional performance identifying diseases, test Accuracy 98% high Precision, Recall, F1 scores. This result highlights that is particularly well suited disease classification. robustness validated through k-fold cross-validation, confirming its generalizability minimizing risk overfitting. study not only focused on classifying but also has potential benefit farmers community greatly. advantages custom models efficient accurate paving way technology-driven advancements farming practices.

Language: Английский

---

Intelligent vineyard blade density measurement method incorporating a lightweight vision transformer

Egyptian Informatics Journal, Journal Year: 2024, Volume and Issue: 26, P. 100456 - 100456

Published: March 21, 2024

Under the new demand model of Agriculture 4.0, automated spraying is a very complex task in precision agriculture, which needs to be combined with computerized vision perception system distinguish plant leaf density and execute operation real-time accordingly. Aiming at accurate determination grape density, an image method based on lightweight Vision Transformer (ViT) architecture proposed, designs fusion data augmentation containing dual spatial extension weather method, where former adopts pixel for original processing, latter realizes from empirical point view adapted agricultural environment, fuses two order expand sample capacity image, then enhances model's generalization ability robustness. The ViT has self-attention that can automatically efficiently extract high-frequency local feature representations use two-branch structure mix low-frequency information form grapevine-leaf features region interest. semantic analysis extraction layer parsed using t-SNE histogram methods, improves transparency multidimensional frequency domain distribution space. experimental results show effectively improve recognition accuracy, accuracy comparing included methods improved by 0.55 % 3.46 %, respectively. recognizing all four types densities exceeded 94 MCC reached 90.39 %. In addition, proposed least 0.34 FLOPs only 0.6 G compared popular MobileViT. this work high speed provide practical technical support protection robots profitability growers reduction pesticide residues.

Language: Английский

---

A hybrid approach for rice crop disease detection in agricultural IoT system

Discover Sustainability, Journal Year: 2024, Volume and Issue: 5(1)

Published: May 23, 2024

Abstract Agriculture is an essential sector that plays a necessary role in the economic improvement of country. Prediction plant diseases at earliest stage may result better yield and sustainable for growing population. The conventional method necessitates highly skilled inspectors to identify phenotypic expression different diseases. Alternatively, biochemical technologies offer more precise means obtaining crop disease information by analyzing susceptible rice. However, these methods are time-consuming, expensive, reliant on laboratories, require professionals, rendering them unaffordable most farmers. paper aims propose solution prevent infection benefit A novel detection model deploying deep convolutional generative adversarial network (DC-GAN) with multidimensional feature compensation Residual Neural Network (MDFC-ResNet) named as DC-GAN-MDFC–ResNet, which fine grained identification system detects from three aspects, bacterial leaf blight, streak panicle blight. Initially input data undergone preprocessing using several processes like improvement, normalization, Singular value decomposition (SVD) reduce negative influence set has training model. When compared traditional convolution models, suggested DC-GAN-MDFC–ResNet architecture exhibits terms highest classification accuracy, Segmentation free methodology stability. experiments done this work Plant Village dataset show proposed technique offering improved recognition rate 95.99% accuracy generating higher quality samples other well-known learning models.

Language: Английский

---

Enhancing Rice Leaf Disease Classification: A Customized Convolutional Neural Network Approach

Sustainability, Journal Year: 2023, Volume and Issue: 15(20), P. 15039 - 15039

Published: Oct. 19, 2023

In modern agriculture, correctly identifying rice leaf diseases is crucial for maintaining crop health and promoting sustainable food production. This study presents a detailed methodology to enhance the accuracy of disease classification. We achieve this by employing Convolutional Neural Network (CNN) model specifically designed images. The proposed method achieved an 0.914 during final epoch, demonstrating highly competitive performance compared other models, with low loss minimal overfitting. A comparison was conducted Transfer Learning Inception-v3 EfficientNet-B2 showed superior performance. With increasing demand precision models like one show great potential in accurately detecting managing diseases, ultimately leading improved yields ecological sustainability.

Language: Английский

---

TRiP: a transfer learning based rice disease phenotype recognition platform using SENet and microservices

Frontiers in Plant Science, Journal Year: 2024, Volume and Issue: 14

Published: Jan. 24, 2024

Classification of rice disease is one significant research topics in phenotyping. Recognition diseases such as Bacterialblight , Blast Brownspot Leaf smut and Tungro are a critical field However, accurately identifying these challenging issue due to their high phenotypic similarity. To address this challenge, we propose phenotype identification framework which utilizing the transfer learning SENet with attention mechanism on cloud platform. The pre-trained parameters transferred network for optimization. capture distinctive features diseases, applied feature extracting. Experiment test comparative analysis conducted real datasets. experimental results show that accuracy our method reaches 0.9573. Furthermore, implemented recognition platform based microservices architecture deployed it cloud, can provide task service easy usage.

Language: Английский

---