APPLICATION OF ARTIFICIAL NEURAL NETWORKS FOR THE CLASSIFICATION OF REMOTE SENSING SPECTRAL REFLECTANCE DATA OF FUNGAL INFECTED SOYBEAN LEAF.Mathematics, Computer Science and Statistics APPLICATION OF ARTIFICIAL NEURAL NET neural network also neural net n. A real or virtual device, modeled after the human brain, in which several interconnected elements process information simultaneously, adapting and learning from past patterns. Noun 1. WORKS FOR THE CLASSIFICATION OF RE MOTE SENSING SPECTRAL REFLECTANCE DATA OF FUNGAL INFECTED SOYBEAN soybean, soya bean, or soy pea, leguminous plant (Glycine max, G. soja, or Soja max) of the family Leguminosae (pulse family), native to tropical and warm temperate regions of Asia, where it has been LEAF Abdullah [Faruque.sup.*][1], Raj Bahadur Ba`ha´dur n. 1. A title of respect or honor given to European officers in East Indian state papers, and colloquially, and among the natives, to distinguished officials and other important personages. [1], and Gregory A. Carter [2], (1.) Mississippi Valley State University Mississippi Valley State University is a historically black university located in Itta Bena, Mississippi. The university is commonly referred to as MVSU or simply "The Valley." MVSU is a member school of the Thurgood Marshall Scholarship Fund. , Itta Bena, MS 38941 and (2.) Earth System Science Office, NASA NASA: see National Aeronautics and Space Administration. NASA in full National Aeronautics and Space Administration Independent U.S. , Stennis Space Center, MS 39529 This paper describes the application of artificial neural networks as a preferred pattern recognition tool for the classification of remote sensing spectral reflectance data of fungal infected soybean leaves. The objective of this study funded by National Aeronautics Space Administration (NASA) at Stennis Space Center was to record and classify the spectral reflectance differences of leaf and canopy stress caused by drought and disease. Reflectance spectra of three different classes of fungal infected leaves were measured using GER GER German/Germany GER Gastroesophageal Reflux GER Geriatrics GER General Education Requirement GER Great Eastern Railway (UK) GER Gross Enrollment Ratio (education) GER Gain Electrons Reduction 1500 Spectroradiometer for 512 spectral bands from 305 nm to 1089 nm. Multi-layer feed-forward neural network model was used to train and predict the different classes of fungal infected leaves from their spectral signature. Network parameters and architectures were optimized to obtain maximum network classification performance. The classification performance of neural networks was compared to K-nearest neighbor and other statistical pattern recognition techniques. The superior classification capability of neural networks can be used to monitor more precisely the signs of damaging stress on economic crops. |
|
||||||||||||||||||
Printer friendly
Cite/link
Email
Feedback
Reader Opinion