Deep Learning Techniques for a Comparative Study of Crop Disease Detection DOI
Sumukha Prasad, Lokendra Kumar,

Sai Nirupam Mallem

и другие.

Lecture notes in networks and systems, Год журнала: 2024, Номер unknown, С. 407 - 423

Опубликована: Окт. 26, 2024

Язык: Английский

GeoAgriGuard: AI-Driven Pest and Disease Management with Remote Sensing for Global Food Security DOI

K Sharada,

Shailee Lohmor Choudhary,

T. Harikrishna

и другие.

Remote Sensing in Earth Systems Sciences, Год журнала: 2025, Номер unknown

Опубликована: Янв. 20, 2025

Язык: Английский

Процитировано

1

Application of a Hybrid Model for Data Analysis in Hydroponic Systems DOI Creative Commons

Kuanysh Bakirov,

Jamalbek Tussupov, Tussupov Akhmet

и другие.

Technologies, Год журнала: 2025, Номер 13(5), С. 166 - 166

Опубликована: Апрель 22, 2025

This study presents a hybrid data analysis approach to optimize the growing conditions for beetroot and tarragon microgreens cultivated in hydroponic systems. Maintaining precise microclimate control is essential, as even minor deviations can significantly affect yield product quality, but traditional monitoring methods fail adapt promptly changing conditions. To overcome this limitation, an automated system integrating machine learning XGBoost 3.0.0, principal component (PCA), fuzzy logic was developed. The model continuously identifies environmental parameters recommends corrective actions stabilize growth Experimental evaluation demonstrated superior predictive performance by using XGBoost, achieving accuracy F1-score of 97.88%, ROC-AUC 99.99%, computational efficiency (training completed 2.3 s), outperforming RandomForest GradientBoosting algorithms. Real-time collection facilitated through IoT sensors transmitting readings via Wi-Fi every 5 s local server, accumulating approximately 17,280 records per day. highlighted air humidity, solution temperature critical influencing factors. research confirms developed system’s effectiveness intelligent monitoring, with future work aimed at IIoT technologies scalable management across diverse crops.

Язык: Английский

Процитировано

0

Analyzing Disease and Pest Dynamics in Steppe Crop Using Structured Data DOI Creative Commons
Jamalbek Tussupov, Gulzira Abdikerimova, Aisulu Ismailova

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 71323 - 71330

Опубликована: Янв. 1, 2024

In this study, an analysis of the spectral brightness coefficients (SBC) agricultural crops in steppe regions Kazakhstan was carried out using remote field and space measurements during growing season. The possibility assessing structural changes plants near-infrared data explored. An electronic database corrected SBC for studied has been created. results obtained confirm that dynamics values reflect morphophysiological their Analysis seasonal pests diseases makes it possible to diagnose species composition physiological state plants. Spectrophotometric information from satellite various can be used build simulation models provide scientifically based forecasts spatial distribution vegetation cover. study highlights potential subtle differences different types ecological status. Sentinel prospects its use ground-based spectrometric calibration, as well predicting yields.

Язык: Английский

Процитировано

2

Soil classification, crop prediction, and disease detection using ML and DL–“agro insights” DOI

Tamilarasi Kathirvel Mururgan,

Penta Revanth

Journal of Plant Diseases and Protection, Год журнала: 2024, Номер unknown

Опубликована: Сен. 6, 2024

Язык: Английский

Процитировано

2

Design of an Iterative Method for Crop Disease Analysis Incorporating Graph Attention with Spatial-Temporal Learning and Deep Q-Networks DOI Open Access

Rupali Meshram,

A. S. Alvi

International journal of intelligent engineering and systems, Год журнала: 2024, Номер 17(3), С. 706 - 719

Опубликована: Май 3, 2024

Existing approaches often fail to capture the complex spatial-temporal interactions among crop conditions, environmental factors, and disease progression, leading suboptimal diagnosis treatment strategies.This work introduces innovative methodologies integrating advanced machine learning techniques overcome these limitations.Specifically, we propose a novel Graph Attention Mechanism with Spatial-Temporal Convolutional Networks (ST-GCN) model analyze diseases.This uniquely combines graph attention mechanisms spatialtemporal modeling, enabling precise identification tracking of progression over time space.This allows for high-accuracy predictions presence, severity, spatial distribution, achieving 90% accuracy an Intersection Union (IoU) score at least 0.8.Furthermore, introduce Deep Q-Network Attention-Based Feature Selection (DQN-AFS) model, which innovatively applies deep Q-networks integrated optimize feature selection in images.This approach significantly enhances model's ability discern between varying types severity levels diseases, ensuring 85% or higher classification 80% rate different use case scenarios.Lastly, Swarm Intelligence-Based Multiple Agent Reinforcement Learning (SI-MARL) framework adaptive recommendation.This demonstrates superior efficacy resource utilization efficiency compared conventional methods.

Язык: Английский

Процитировано

1

Бидай өнімділігіне әсер етуші факторларды машиналық оқытумен анықтаудың моделі DOI

Ләззат Тәжібай,

Gulden Murzabekova, G.Zh. Stybaev

и другие.

L.N. Gumilev atyndaġy Euraziâ u̇lttyķ universitetìnìņ habaršysy., Год журнала: 2024, Номер 147(2), С. 17 - 31

Опубликована: Июнь 30, 2024

Экономикалық өсуді ынталандыру үшін өсімдік шаруашылығы Қазақстан экономикасының негізі болып табылады. Өнімділікті болжау ауылшаруашылық жоспарлау мен басқарудың маңызды аспектісі болғандықтан, болжаудың заманауи әдістері модельдері рөл атқарады. Дақылдардың өнімділігі дақылдарды өсіру аймағының климаттық жағдайларына байланысты. Ауа-райының бидай өнімділігіне әсерін интеллектуалды әдістерді, соның ішінде машиналық оқыту әдістерін қолдана отырып модельдеу жоғары тиімділікке ие. Метеодеректер (ML) әдістеріне негізделген модельдер өнімділікті кезінде уақытты едәуір қысқартуға және ауа-райының өнімділікке анықтауға мүмкіндік береді. Бұл мақалада қолда бар деректер негізінде дақылдардың өнімділігін алгоритмдері қолданылды. Қарастырылып отырған алгоритмдерге салыстырмалы талдау жүргізілді. Сызықтық алгоритм, шешімдер ағаштары бустинг алгоритмдерінің ML Өнімділік Ақмола облысы Ақкөл ауданының метеодеректеріне сүйене болжанған.

Процитировано

0

Deep Learning Techniques for a Comparative Study of Crop Disease Detection DOI
Sumukha Prasad, Lokendra Kumar,

Sai Nirupam Mallem

и другие.

Lecture notes in networks and systems, Год журнала: 2024, Номер unknown, С. 407 - 423

Опубликована: Окт. 26, 2024

Язык: Английский

Процитировано

0