An efficient approach for land record classification and information retrieval in data warehouse

Abstract

Data warehouse collects recent and old land record data used to generate analytical reports. Depending on factors such as historical evolution and local traditions, the system of land records differs from states. The survey maps, textual data, and registration records are matched with each other and updated for the registration and maintenance of such land records. In addition, citizens must get access to multiple agencies to get full information on land records. In order to eliminate such limitation, we propose a novel Artificial Neural Network (ANN)–FUZZY–cat swarm optimization (CSO) approach to accurately predict and retrieve the information. First, the ANN classifies the input data for ordering the information to construct a database of different classes. Then, the mongo database store a large amount of land record data for facilitating easy maintenance, prompt updating of land records and security. The accurate results for the user query are retrieved using CSO algorithm. Optimal rules allow users to access their posts easily. Finally, better performance results are for the information retrieval in terms of accuracy, precision, and recall.