path identification between cluster heads using a-star and k-means algorithm with obstacle mapping
A.Alad Manoj Peter,Aswinkumar.R,Jawahar.V
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:4 Issue:3 Year: 01 April,2016 Pages:790-795
Abstract
The aim of the project is to find optimal path to reach the enemys place in the war field. It can be done by clustering the vehicles in enemy base by using K-means clustering and the optimal path can be found by using the improved A* algorithm. The input of this project is the satellite image of an enemys base. In this image we can easily identify the location of the enemys vehicles. By using that location we can fix the destination to reach. The advantage of clustering the enemys vehicle is used to reduce the time to traverse the node (here vehicle is considered as a node) and we easily reduce the number of paths. The k-means clustering is most commonly used clustering method and the formula we used to cluster the node is very simple to calculate. In this project the ultimate aim is to find the optimal path instead of finding the shortest path. Finding the shortest path is not efficient because the shortest may have some difficulties like having some snowfall, mountain, Lake Etc. so we need to find the optimal path. We use improved A* algorithm to find the optimal path. Reason for choosing this algorithm is here we dont have single destination and clusters are movable. So improved A* algorithm is feasible to find the optimal path. This project can be nearly based on image processing because we can process the input in the form of image format. And the output of the project is clearly said which is the optimal path to reach the enemies to attack them.
Kewords
clustering the vehicles, optimal path identification
Reference
[1] M. Takai, L. Bajaj, R. Ahuja, R. Bagrodia, M. Gerla. Glomosim: A Scalable Network Simulation Environment. Technical Report 990027; Univ. of California at Los Angeles, Computer Science Department, 2014. [2] X. Hong, M. Gerla, G. Pei, and C.-C. Chiang. A Group Mobility Model for Ad Hoc Wireless Networks. Proceedings of ACM/IEEE MSWiM99; Seattle, WA, Aug. 1999. [3] R Nagel, S Eichler and J Eberspächer , Intelligent Wireless Communication for future autonomous and cognitive automobiles, Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, Istanbul, Turkey, June 13-15 2007, pp:716-721. [4] G Abdalla, M A AbuRgheff and S M Senouci, Current Trends in Vehicular Adhoc Networks, Ubiquitous Computing and Communication Journal (UbiCC) – Special issue of UbiRoads 2007C. J. Kaufman, Rocky Mountain Research Lab., Boulder, CO, private communication, May 1995. [5] Yuma Imi,Tomomichi Hayakawa,Takayuki Ito, Analyzing the Effect of Open Street Map During Crises : The Great East Japan Earthquake, 1730 Massachusetts Ave., NW Washington, DC USA, IEEE Computer Society,2012,pp. 126 – 130.
