Using MATLAB to achieve improved BP neural network model of remote sensing image classification

Journal Title: Scholars Journal of Engineering and Technology - Year 2015, Vol 3, Issue 4

Abstract

Application of improved BP neural network (NN) model to research the ETM + remote sensing (RS) data classification. Select six of LANDSAT 7 ETM + multi-spectral bands as the data source, through read the six ETM image respectively in each pixel’s gray value, construct a six - dimensional input sample of the sample space: Vi={Vil,Vi2,Vi3,Vi4,Vi5,Vi6}. Through the experiment, ETM1, ETM3, ETM5, ETM7 was determined four wave bands as the input layer(the number of input layer neurons M = 4), and the geological object was divided into five categories(the number of output neurons N = 5), the optimal improved BP NN structure for the three-layers BP network, the number of the hidden layer nodes is 24, the input layer node number is 4, the output layer nodes is 5, excitation function for the S-type logarithmic function. The optimal network training parameters : the initial weights is 0.1, the learning rate is 0.9 , increasing rate of learning speed is 1.0 , decreasing rate of learning speed is 0.05 , the momentum factor is 0.001 , the network 's global error is 0.01 .Network model after 2000 times or less training, to achieve convergence. The model was applied to RS images of Mulei County of Xinjiang carry out geology type classification, the total classification precision reaches 89.06%, rapid classification quality is good, meet the production quality requirements. Keywords: RS image; Improved BP model; Classification

Authors and Affiliations

482 486

Keywords

Related Articles

Well Integrity Evaluation during CO2 Storage and Enhanced Gas Recovery

With the industrialization in the 19th century the desire for energy rose continuously resulting in a high emission of CO2 which is one of the greenhouse gases. Storage of CO2 in the underground, e.g., depleted oil and g...

Integral Points On The Cone

The ternary quadratic equation representing a homogeneous cone is analyzed for its non-zero distinct integer solutions. Also, given an integer solution, three different triples of integers generating infinitely many in...

Experimental Investigation for the Magnetic-Caloric Effect on the Refrigeration Cycle Performance

The present research aims to investigate experimentally applying of the magnetic-caloric effect on the performance of vapor compression cycle. Three levels of magnetic fields of 1300, 2400, and 3600 Gauss are used and tw...

Computerization of the Students’ Industrial Work Experience Scheme (SIWES) Registration and Payment System (SIWES-RPS) in Nigeria

The current registration and payment processes for the Student Industrial Work Experience Scheme is semi-automated if not completely manual. Students have to queue at the Student’s Industrial Work Experience Scheme (SIWE...

Depelopment of Hydraulic Design Criteria for Runoff on Residential Area in Bekasi, Indonesia

Abstract:The incompatibilities of urban or residential area’s drainage channel construction with design criteria were often found caused by the difficulties in designing drainage channel. This research aims to determine...

Download PDF file
  • EP ID EP385098
  • DOI -
  • Views 49
  • Downloads 0

How To Cite

482 486 (2015). Using MATLAB to achieve improved BP neural network model of remote sensing image classification. Scholars Journal of Engineering and Technology, 3(4), 482-486. https://europub.co.uk/articles/-A-385098