Idioma:

Mobile application using DCDM and cloud-based automatic plant disease detection

Kumar, Parasuraman ; Raghavendran, Srinivasan ; Silambarasan, Karunagaran ; Kannan, Kaliaperumal Senthamarai ; Krishnan, Nallaperumal

Environmental monitoring and assessment, 2023-01, Vol.195 (1), p.44-44, Article 44 [Periódico revisado por pares]

Cham: Springer International Publishing

Texto completo disponível

Citações Citado por

Enviar para

Título:
Mobile application using DCDM and cloud-based automatic plant disease detection
Autor: Kumar, Parasuraman ; Raghavendran, Srinivasan ; Silambarasan, Karunagaran ; Kannan, Kaliaperumal Senthamarai ; Krishnan, Nallaperumal
Assuntos: Agribusiness ; Agricultural economics ; Agricultural production ; Agriculture ; Applications programs ; Atmospheric Protection/Air Quality Control/Air Pollution ; Cloud computing ; Crop production ; Data centers ; Data conversion ; Data storage ; Deep learning ; Disease control ; Disease detection ; Disease recognition ; Disease transmission ; Earth and Environmental Science ; Ecology ; Economic development ; Economic growth ; Ecotoxicology ; Electronic devices ; Employment ; Environment ; Environmental factors ; Environmental Management ; Environmental monitoring ; Environmental science ; Farms ; Growth rate ; Image classification ; Information centres ; Information management ; Internet ; Internet access ; Leaves ; Machine learning ; Medical imaging ; Mobile computing ; Modules ; Monitoring/Environmental Analysis ; Plant diseases ; Plant monitoring ; Plants ; Telemedicine ; Water management ; Water supply
É parte de: Environmental monitoring and assessment, 2023-01, Vol.195 (1), p.44-44, Article 44
Notas: ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Descrição: Farming has a plethora of difficult responsibilities, and plant monitoring is one of them. There is also an urgent need to increase the number of alternative techniques for detecting plant diseases, which is now lacking. The agriculture and agricultural support sectors in India provide employment for the great majority of the country’s people. In India, the agricultural production of the country is directly connected to the country’s economic growth rate. In order to sustain healthy plant development, a variety of processes must be followed, including consideration of environmental factors and water supply management for the optimal production of crops. It is inefficient and uncertain in its outcomes to use the traditional method of watering a lawn. The devastation of more than 18% of the world’s agricultural produce is caused by disease attacks on an annual basis. Because it is difficult to execute these activities manually, identifying plant diseases is essential to decreasing losses in the agricultural product business. In addition to diagnosing a wide range of plant ailments, our method also includes the identification of infections as a prophylactic step. Below is a detailed description of a farm-based module that includes numerous cloud data centers and data conversion devices for accurately monitoring and managing farm information and environmental elements. This procedure involves imaging the plant’s visually obvious signs in order to identify disease. It is recommended that the therapy be used in conjunction with an application to minimize any harm. Increased productivity as a result of the suggested approach would help both the agricultural and irrigation sectors. The plant area module is fitted with a mobile camera that captures images of all of the plants in the area, and all of the plants’ information is saved in a database, which is accessible from any computer with Internet access. It is planned to record information on the plant’s name, the type of illness that has been afflicted, and an image of the plant. In a wide range of applications, bots are used to collect images of various plants as well as to prevent disease transmission. To ensure that all information given is retained on the Internet, data is collected and stored in cloud storage as it becomes essential to regulate the condition. According to our findings from our research on wide images of healthy and ill fruit and plant leaves, real-time diagnosis of plant leaf diseases may be done with 98.78% accuracy in a laboratory environment. We utilized 40,000 photographs and then analyzed 10,000 photos to construct a DCDM deep learning model, which was then used to train additional models on the data set. Using a cloud-based image diagnostic and classification service, consumers may receive information about their condition in less than a second on average, with the process requiring only 0.349 s on average.
Editor: Cham: Springer International Publishing
Idioma: Inglês

Voltar para lista de resultados

Anterior Resultado 3 Avançar Ir para próxima página

Realização: Logos de Redes Sociais:

Mobile application using DCDM and cloud-based automatic plant disease detection

Kumar, Parasuraman ; Raghavendran, Srinivasan ; Silambarasan, Karunagaran ; Kannan, Kaliaperumal Senthamarai ; Krishnan, Nallaperumal

Cham: Springer International Publishing

Buscando em bases de dados remotas. Favor aguardar.