Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Prediction Model for Predicting Powdery Mildew using ANN for Medicinal Plant—Picrorhiza kurrooa
Abstract Plant disease fore casting system is an important system as it can be used for prediction of disease, further it can be used as an alert system to warn the farmers in advance so as to protect their crop from being getting infected. Fore casting system will predict the risk of infection for crop by using the environmental factors that favor in germination of disease. In this study an artificial neural network based system for predicting the risk of powdery mildew in Picrorhiza kurrooa was developed. For development, Levenberg–Marquardt backpropagation algorithm was used having a single hidden layer of ten nodes. Temperature and duration of wetness are the major environmental factors that favor infection. Experimental data was used as a training set and some percentage of data was used for testing and validation. The performance of the system was measured in the form of the coefficient of correlation (R), coefficient of determination (R2), mean square error and root mean square error. For simulating the network an inter face was developed. Using this interface the network was simulated by putting temperature and wetness duration so as to predict the level of risk at that particular value of the input data.
Prediction Model for Predicting Powdery Mildew using ANN for Medicinal Plant—Picrorhiza kurrooa
Abstract Plant disease fore casting system is an important system as it can be used for prediction of disease, further it can be used as an alert system to warn the farmers in advance so as to protect their crop from being getting infected. Fore casting system will predict the risk of infection for crop by using the environmental factors that favor in germination of disease. In this study an artificial neural network based system for predicting the risk of powdery mildew in Picrorhiza kurrooa was developed. For development, Levenberg–Marquardt backpropagation algorithm was used having a single hidden layer of ten nodes. Temperature and duration of wetness are the major environmental factors that favor infection. Experimental data was used as a training set and some percentage of data was used for testing and validation. The performance of the system was measured in the form of the coefficient of correlation (R), coefficient of determination (R2), mean square error and root mean square error. For simulating the network an inter face was developed. Using this interface the network was simulated by putting temperature and wetness duration so as to predict the level of risk at that particular value of the input data.
Prediction Model for Predicting Powdery Mildew using ANN for Medicinal Plant—Picrorhiza kurrooa
Shivling, V. D. (Autor:in) / Ghanshyam, C. (Autor:in) / Kumar, Rakesh (Autor:in) / Kumar, Sanjay (Autor:in) / Sharma, Radhika (Autor:in) / Kumar, Dinesh (Autor:in) / Sharma, Atul (Autor:in) / Sharma, Sudhir Kumar (Autor:in)
23.06.2016
5 pages
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Prediction Model for Predicting Powdery Mildew using ANN for Medicinal Plant—Picrorhiza kurrooa
| Springer Verlag | 2017
Genes for resistance to wheat powdery mildew
| British Library Online Contents | 1999
Control of Powdery Mildew in Organic Greenhouse Melon Cultivation
| British Library Conference Proceedings | 2011
Powdery mildew resistance genes in wheat: verification of STS markers
| British Library Online Contents | 2001
| DOAJ | 2022