Influence of fitness quantization noise on the performance of interactive PSO

Yu Nakano, Hideyuki Takagi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

We analyze the influence of quantization noise in fitness values on the search performance of Particle Swarm Optimization (PSO) and propose methods for reducing the negative influence of the noise to help realize a practical Interactive PSO. First, we compare the convergences of PSO and genetic algorithms (GA) with several different levels of quantized fitness values and show that PSO has a higher sensitivity to quantization noise than GA. Second, we analyze the sensitivity of each of the three components that determine the subsequent generation's PSO velocities and show that the sensitivities of the three components are almost equivalent.This implies that we need to develop methods for reducing the effect of quantization noise on all three components of the PSO velocity. As one of the solution, we propose a method using the average location of multiple global bests of same fitness value and another method for multimodal searching spaces using subglobal bests obtained by clustering.

Original languageEnglish
Title of host publication2009 IEEE Congress on Evolutionary Computation, CEC 2009
Pages2416-2422
Number of pages7
DOIs
Publication statusPublished - 2009
Event2009 IEEE Congress on Evolutionary Computation, CEC 2009 - Trondheim, Norway
Duration: May 18 2009May 21 2009

Other

Other2009 IEEE Congress on Evolutionary Computation, CEC 2009
CountryNorway
CityTrondheim
Period5/18/095/21/09

Fingerprint

Particle swarm optimization (PSO)
Fitness
Particle Swarm Optimization
Quantization
Genetic Algorithm
Genetic algorithms
Particle Swarm Optimization Algorithm
Influence
Clustering
Imply

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

Nakano, Y., & Takagi, H. (2009). Influence of fitness quantization noise on the performance of interactive PSO. In 2009 IEEE Congress on Evolutionary Computation, CEC 2009 (pp. 2416-2422). [4983243] https://doi.org/10.1109/CEC.2009.4983243

Influence of fitness quantization noise on the performance of interactive PSO. / Nakano, Yu; Takagi, Hideyuki.

2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. p. 2416-2422 4983243.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nakano, Y & Takagi, H 2009, Influence of fitness quantization noise on the performance of interactive PSO. in 2009 IEEE Congress on Evolutionary Computation, CEC 2009., 4983243, pp. 2416-2422, 2009 IEEE Congress on Evolutionary Computation, CEC 2009, Trondheim, Norway, 5/18/09. https://doi.org/10.1109/CEC.2009.4983243
Nakano Y, Takagi H. Influence of fitness quantization noise on the performance of interactive PSO. In 2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. p. 2416-2422. 4983243 https://doi.org/10.1109/CEC.2009.4983243
Nakano, Yu ; Takagi, Hideyuki. / Influence of fitness quantization noise on the performance of interactive PSO. 2009 IEEE Congress on Evolutionary Computation, CEC 2009. 2009. pp. 2416-2422
@inproceedings{3cb74e687fa24004902f27e2d54114e6,
title = "Influence of fitness quantization noise on the performance of interactive PSO",
abstract = "We analyze the influence of quantization noise in fitness values on the search performance of Particle Swarm Optimization (PSO) and propose methods for reducing the negative influence of the noise to help realize a practical Interactive PSO. First, we compare the convergences of PSO and genetic algorithms (GA) with several different levels of quantized fitness values and show that PSO has a higher sensitivity to quantization noise than GA. Second, we analyze the sensitivity of each of the three components that determine the subsequent generation's PSO velocities and show that the sensitivities of the three components are almost equivalent.This implies that we need to develop methods for reducing the effect of quantization noise on all three components of the PSO velocity. As one of the solution, we propose a method using the average location of multiple global bests of same fitness value and another method for multimodal searching spaces using subglobal bests obtained by clustering.",
author = "Yu Nakano and Hideyuki Takagi",
year = "2009",
doi = "10.1109/CEC.2009.4983243",
language = "English",
isbn = "9781424429592",
pages = "2416--2422",
booktitle = "2009 IEEE Congress on Evolutionary Computation, CEC 2009",

}

TY - GEN

T1 - Influence of fitness quantization noise on the performance of interactive PSO

AU - Nakano, Yu

AU - Takagi, Hideyuki

PY - 2009

Y1 - 2009

N2 - We analyze the influence of quantization noise in fitness values on the search performance of Particle Swarm Optimization (PSO) and propose methods for reducing the negative influence of the noise to help realize a practical Interactive PSO. First, we compare the convergences of PSO and genetic algorithms (GA) with several different levels of quantized fitness values and show that PSO has a higher sensitivity to quantization noise than GA. Second, we analyze the sensitivity of each of the three components that determine the subsequent generation's PSO velocities and show that the sensitivities of the three components are almost equivalent.This implies that we need to develop methods for reducing the effect of quantization noise on all three components of the PSO velocity. As one of the solution, we propose a method using the average location of multiple global bests of same fitness value and another method for multimodal searching spaces using subglobal bests obtained by clustering.

AB - We analyze the influence of quantization noise in fitness values on the search performance of Particle Swarm Optimization (PSO) and propose methods for reducing the negative influence of the noise to help realize a practical Interactive PSO. First, we compare the convergences of PSO and genetic algorithms (GA) with several different levels of quantized fitness values and show that PSO has a higher sensitivity to quantization noise than GA. Second, we analyze the sensitivity of each of the three components that determine the subsequent generation's PSO velocities and show that the sensitivities of the three components are almost equivalent.This implies that we need to develop methods for reducing the effect of quantization noise on all three components of the PSO velocity. As one of the solution, we propose a method using the average location of multiple global bests of same fitness value and another method for multimodal searching spaces using subglobal bests obtained by clustering.

UR - http://www.scopus.com/inward/record.url?scp=70350195376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70350195376&partnerID=8YFLogxK

U2 - 10.1109/CEC.2009.4983243

DO - 10.1109/CEC.2009.4983243

M3 - Conference contribution

AN - SCOPUS:70350195376

SN - 9781424429592

SP - 2416

EP - 2422

BT - 2009 IEEE Congress on Evolutionary Computation, CEC 2009

ER -