A binary Hopfield neural-network approach for satellite broadcast scheduling problems

1997 ◽  
Vol 8 (2) ◽  
pp. 441-445 ◽  
Author(s):  
N. Funabiki ◽  
S. Nishikawa
Keyword(s):  
Neural Network ◽  
Hopfield Neural Network ◽  
Broadcast Scheduling ◽  
Scheduling Problems ◽  
Network Approach ◽  
Neural Network Approach

scholarly journals A 2D Hopfield Neural Network approach to mechanical beam damage detection

2015 ◽  
Vol 26 (4) ◽  
pp. 1081-1095 ◽  
Author(s):  
Juliana Almeida ◽  
Hugo Alonso ◽  
Pedro Ribeiro ◽  
Paula Rocha
Keyword(s):  
Neural Network ◽  
Damage Detection ◽  
Hopfield Neural Network ◽  
Network Approach ◽  
Neural Network Approach ◽  
Beam Damage

scholarly journals The Task Scheduling Problem: A NeuroGenetic Approach

2014 ◽  
Vol 12 (4) ◽  
pp. 327
Author(s):  
Anurag Agarwal ◽  
Selcuk Colak ◽  
Jason Deane ◽  
Terry Rakes
Keyword(s):  
Neural Network ◽  
Task Scheduling ◽  
Computational Time ◽  
Test Problems ◽  
Scheduling Problem ◽  
Scheduling Problems ◽  
Network Approach ◽  
Neural Network Approach ◽  
One Machine ◽  
Better Than

This paper addresses the task scheduling problem which involves minimizing the makespan in scheduling n tasks on m machines (resources) where the tasks follow a precedence relation and preemption is not allowed. The machines (resources) are all identical and a task needs only one machine for processing. Like most scheduling problems, this one is NP-hard in nature, making it difficult to find exact solutions for larger problems in reasonable computational time. Heuristic and metaheuristic approaches are therefore needed to solve this type of problem. This paper proposes a metaheuristic approach - called NeuroGenetic - which is a combination of an augmented neural network and a genetic algorithm. The augmented neural network approach is itself a hybrid of a heuristic approach and a neural network approach. The NeuroGenetic approach is tested against some popular test problems from the literature, and the results indicate that the NeuroGenetic approach performs significantly better than either the augmented neural network or the genetic algorithms alone.

Sign in / Sign up

Export Citation Format

Share Document