Abstract
This paper focuses on prediction of change in agricultural lands by using ART2 algorithm. The existing method used ENVI and ARCGIS software to predict the changes in land, which showed less accuracy due to human errors. To overcome this user friendly GUI based ART2 algorithm has been developed in java to obtain more accuracy in prediction of changes in land. The input is satellite temporal images of the years 1990 and 2014. By using the ART2 algorithm, the input images of the years 1990 and 2014 are classified, where the features are identified to form cluster. The clustered image is given as input and pixel to pixel comparison method in ART2 is implemented in java, for detecting the changes in agricultural lands. The comparison results of ENVI and ARCGIS and GUI based ART2 with in situ data show that the prediction of changes in agricultural land is more accurate in the case of GUI based ART2 implementation.
Highlights
B) ENVI 4.7—This is used for the development of land use land cover classes and determine the statistics of change detection c) JAVA AND APPLET—This is used for modeling of agricultural land change detection
The classification was done based on training samples for the images of 1990 and 2014.The classified images of 1990 and 2014 were produced by using supervised image classification technique based on the Maximum Likelihood Classifier(MLC)
The statistics shows that the agricultural land has decreased to 26,695 sq·m
Summary
Agriculture plays a vital role in the district’s economy. Agriculture land change detection is an inevitable one. Proper land use planning is essential for a sustainable development of agriculture. Changes of agricultural land detection are essential to understand the existing situation and plan for the future. Artificial neural networks have more general and flexible functional forms than the traditional statistical methods and can effectively deal with supervised and unsupervised learning methods and address problems such as pattern recognition and prediction [4]. ART can be used as a real time neural network model which performs supervised and unsupervised learning. It performs pattern recognition and prediction [6] [7]. Most of the applications in ART, uses fast learning, for each input vector pattern, the updation of weights converge to equilibrium. The orienting subsystem can to accommodate real valued data [3] [8]-[13]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
