|
Title:
|
NEURAL NETWORK PARALLEL COMPUTATION FOR DYNAMIC WEAPON TARGET ASSIGNMENT PROBLEM |
|
Author(s):
|
Kanae Yamaoka, Keisuke Iwai, Hidema Tanaka, Takakazu Kurokawa |
|
ISBN:
|
978-989-8704-10-8 |
|
Editors:
|
Ajith P. Abraham, Antonio Palma dos Reis and Jörg Roth |
|
Year:
|
2014 |
|
Edition:
|
Single |
|
Keywords:
|
Neural network, dynamic weapon target assignment problem, binary neuron, military operation. |
|
Type:
|
Short Paper |
|
First Page:
|
195 |
|
Last Page:
|
199 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
This paper proposes a neural network architecture consisting of blocks of two dimensional Hopfield type neural network array to solve dynamic weapon target assignment problem. This problem finds out the best allocation strategy for weapons to protect assets from incoming enemy missiles through stages, and is a significant problem in military operation field. Through a large number of simulation runs for an example problem, a naval single platform warfare scenario, the proposed neural network could find out efficient assignment schedules in less than 20 microseconds in average. Their qualities show about a 4.15% improvement compared with the best method presented as TS-DS (a combination of Tabu Search method and Diversification Strategy) in previous papers. |
|
|
|
|
|
|
