A Novel Deep Neural Network-Based Prediction Model for Identifying Diseases in Tomato Leaves DOI
T. Ananth Kumar,

S. Oviya,

Sunday Adeola Ajagbe

и другие.

2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), Год журнала: 2023, Номер unknown, С. 1 - 6

Опубликована: Ноя. 16, 2023

Ensuring global food security is essential for the various stakeholders involved. Accurate identification and categorization of plant diseases are imperative. The emergence novel solutions in image can be attributed to advancements deep learning-based techniques. However, integration these technologies low-end devices requires processing systems that efficient, precise, cost-effective. This study presents a concise practical approach utilizing transfer learning detect anomalies tomato leaves. utilization illumination correction enhance leaf images represents an effective preprocessing technique improving categorization. methodology employed our involves hybrid model consisting pre-trained MobileNetV2 architecture classifier network gather data generate accurate predictions. Runtime augmentation assumes responsibility conventional methods prevent breaches facilitate management.

Язык: Английский

Isolation and Identification of Cucumber Root Rot-Associated Fungi and Assessment of Their Pathogenicity DOI Open Access

Ibrahim Ali Ibrahim,

Hurria H. Al-Juboory

IOP Conference Series Earth and Environmental Science, Год журнала: 2024, Номер 1371(3), С. 032024 - 032024

Опубликована: Июль 1, 2024

Abstract This study was conducted at the Laboratories of Crop Protection Directorate / Ministry Agriculture – Iraq for isolating causative agents cucumber root rot disease from various sites in Baghdad, Salah al-Din, Sulaymaniyah, and Basra provinces Iraq, testing their pathogenicity on seeds laboratory Results isolation diagnosis revealed presence several plant-associated fungi that varied appearance across different regions The fungus Rhizoctonia solani most prevalent, as it appeared majority isolated samples, totaling fifteen isolates, while isolates Fusarium spp Macrophomina phaseolina reached 5 2 respectively results assessment 22 fungal indicated all tested significantly reduced germination rate Germination rates treatments ranged 0-43.3% compared to 100% control Isolates R7 R15 R. , 1F F5 . spp, M1 M2 M. exhibited significant superiority over other which completely inhibiting germination, isolate R1, R2, R3, R4, R5, R6 43.3, 36.6, 20, 10, 30, 6.6%,

Язык: Английский

Процитировано

0
Green Guardians: Endophytic microbes in protecting vegetable crops against pathogens DOI Creative Commons

Sagarika Medari,

Krishnan Kalpana,

Muthusamy Ramakrishnan

и другие.

Plant Protection Science, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 29, 2024

Sagarika Medari, Krishnan Kalpana, Muthuswamy Ramakrishnan, Aravindaram Kandan, Subbiah Ramasamy, Karuppiah Eraivan Arutkani Aiyanathan, Sankarasubramanian Harish, Andithevar Beaulah, Rangaswamy Anandham, Narayanan Manikandaboopathi, Marimuthu Ayyandurai

Процитировано

0
A Novel Deep Neural Network-Based Prediction Model for Identifying Diseases in Tomato Leaves DOI
T. Ananth Kumar,

S. Oviya,

Sunday Adeola Ajagbe

и другие.

2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), Год журнала: 2023, Номер unknown, С. 1 - 6

Опубликована: Ноя. 16, 2023

Ensuring global food security is essential for the various stakeholders involved. Accurate identification and categorization of plant diseases are imperative. The emergence novel solutions in image can be attributed to advancements deep learning-based techniques. However, integration these technologies low-end devices requires processing systems that efficient, precise, cost-effective. This study presents a concise practical approach utilizing transfer learning detect anomalies tomato leaves. utilization illumination correction enhance leaf images represents an effective preprocessing technique improving categorization. methodology employed our involves hybrid model consisting pre-trained MobileNetV2 architecture classifier network gather data generate accurate predictions. Runtime augmentation assumes responsibility conventional methods prevent breaches facilitate management.

Язык: Английский

Процитировано

0