Particle swarm optimization application in optimization

Bon, Abdul Talib Particle swarm optimization application in optimization. In: Prosiding Seminar Kebangsaan Pengoptimuman Berangka dun Penyelidikan Operasi Ke-2.



The Particle Swarm Optimization (PSO) was used to select the three best inputs to explain the input-output relationship of both 'defects' and 'time' models. A ranking-based system was used to select the best features. Using this system, the value of each particle in the swarm represents the importance of each feature. During optimization, the three best-ranked features were used to train the Multilayer Perceptron (MLP). The objective of the PSO is to minimize the MSE fitting error between the actual output and the modelled output. If the features are discriminative, the generalization error should be small since the MLP approximation is close to the actual output.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:particle swarm optimization; multilayer perceptron; optimization; defects; time
Subjects:Q Science > QC Physics
Divisions:Faculty of Technology Management and Business > Department of Production and Operation
ID Code:6803
Deposited On:14 Jun 2015 15:25
Last Modified:14 Jun 2015 15:25

Repository Staff Only: item control page