# Integrating A* algorithm with neural network

 Author: Lv, Ye Title: Integrating A* algorithm with neural network Degree: M.Sc. Year: 2011 Subject: Neural networks (Computer science)Computer algorithms.Hong Kong Polytechnic University -- Dissertations Department: Dept. of Computing Pages: viii, 78 leaves : ill. ; 30 cm. Language: English InnoPac Record: http://library.polyu.edu.hk/record=b2473585 URI: http://theses.lib.polyu.edu.hk/handle/200/6411 Abstract: This dissertation mainly talks the pathfinding algorithm and its relevant domain. A star algorithm is regarded the traditional and core pathfinding algorithm. There are two ways I research for improving the efficiency of the A star algorithm. One method is called block separated method; the other is using the neural network to implement the pathfinding prediction. The core idea of block separated method is to rebuild hierarchy of the map. The source map will be divided into some small blocks. Each block will be applied with the A star algorithm. Because of the characteristic of A star algorithm, small map will own high performance if the A star algorithm implements in it. The hierarchy method will give A star upgrade in efficiency. Neural network is general method for classification, pattern recognition and prediction. In pathfinding algorithm, especially A star algorithm, neural network can predict for the correction path or direction in order to decrease the cost what traditional A star algorithm spends. This study was an exercise to try to improve the traditional A star algorithm. The data source was created by a series of random number. It can affect the reliability of the result. The approach invented by me is a test or mark for the future work

## Files in this item

Files Size Format
b24735851.pdf 2.420Mb PDF
 Copyright Undertaking As a bona fide Library user, I declare that: I will abide by the rules and legal ordinances governing copyright regarding the use of the Database. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage. By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.