eprintid: 10010 rev_number: 6 eprint_status: archive userid: 2 dir: disk0/00/01/00/10 datestamp: 2023-12-07 23:30:33 lastmod: 2023-12-07 23:30:33 status_changed: 2023-12-07 23:30:33 type: article metadata_visibility: show creators_name: Dogra, Roopali creators_name: Rani, Shalli creators_name: Singh, Aman creators_name: Albahar, Marwan Ali creators_name: Pascual Barrera, Alina Eugenia creators_name: Alkhayyat, Ahmed creators_id: creators_id: creators_id: aman.singh@uneatlantico.es creators_id: creators_id: alina.pascual@unini.edu.mx creators_id: title: Deep learning model for detection of brown spot rice leaf disease with smart agriculture ispublished: pub subjects: uneat_eng divisions: uneatlantico_produccion_cientifica divisions: unincol_produccion_cientifica divisions: uninimx_produccion_cientifica divisions: uninipr_produccion_cientifica full_text_status: none abstract: Given that it provides nourishment for more than half of humanity, rice is regarded as one of the most significant plants in the world in agriculture. The quantity and quality of the product may be impacted by diseases that can damage rice plants which can occasionally cause crop losses ranging from 30 to 60%. This manuscript proposed a Convolutional Neural Network (CNN) and Visual Geometry Group (VGG)19 i.e. CNN-VGG19 model with a transfer learning-based method for the precise identification and classification of rice leaf diseases. This scheme employs a transfer learning technique based on the VGG19 which can identify the brown spot class. The accuracy is 93.0% in the deployment of the dataset of rice leaf disease. The other parameters are sensitivity, specificity, precision and F1-score with 89.9%, 94.7%, 92.4% and 90.5% respectively. The developed technique obtained better results as compared to the existing baseline models. date: 2023-07 publication: Computers and Electrical Engineering volume: 109 pagerange: 108659 id_number: doi:10.1016/j.compeleceng.2023.108659 refereed: TRUE issn: 00457906 official_url: http://doi.org/10.1016/j.compeleceng.2023.108659 access: close language: en citation: Artículo Materias > Ingeniería Universidad Europea del Atlántico > Investigación > Producción Científica Fundación Universitaria Internacional de Colombia > Investigación > Producción Científica Universidad Internacional Iberoamericana México > Investigación > Producción Científica Universidad Internacional Iberoamericana Puerto Rico > Investigación > Producción Científica Cerrado Inglés Given that it provides nourishment for more than half of humanity, rice is regarded as one of the most significant plants in the world in agriculture. The quantity and quality of the product may be impacted by diseases that can damage rice plants which can occasionally cause crop losses ranging from 30 to 60%. This manuscript proposed a Convolutional Neural Network (CNN) and Visual Geometry Group (VGG)19 i.e. CNN-VGG19 model with a transfer learning-based method for the precise identification and classification of rice leaf diseases. This scheme employs a transfer learning technique based on the VGG19 which can identify the brown spot class. The accuracy is 93.0% in the deployment of the dataset of rice leaf disease. The other parameters are sensitivity, specificity, precision and F1-score with 89.9%, 94.7%, 92.4% and 90.5% respectively. The developed technique obtained better results as compared to the existing baseline models. metadata Dogra, Roopali; Rani, Shalli; Singh, Aman; Albahar, Marwan Ali; Pascual Barrera, Alina Eugenia y Alkhayyat, Ahmed mail SIN ESPECIFICAR, SIN ESPECIFICAR, aman.singh@uneatlantico.es, SIN ESPECIFICAR, alina.pascual@unini.edu.mx, SIN ESPECIFICAR (2023) Deep learning model for detection of brown spot rice leaf disease with smart agriculture. Computers and Electrical Engineering, 109. p. 108659. ISSN 00457906