TY - JOUR
T1 - Adaptive genetic algorithm-based particle herding scheme for mitigating particle impoverishment
AU - Kuptametee, Chanin
AU - Michalopoulou, Zoi Heleni
AU - Aunsri, Nattapol
N1 - Funding Information:
The authors are grateful for the grant from Mae Fah Luang University under the National Science, Research, and Innovation Fund (NSRF), Thailand: in part by Mae Fah Luang University under the grant Fundamental Fund/Basic Research Fund, Thailand: 652A03004, in part by Mae Fah Luang University under the grant Fundamental Fund/Basic Research Fund, Thailand : 662A03013, and in part by Computer and Communication Engineering for Capacity Building Research Center at Mae Fah Luang University, Thailand. The authors would like to thank the School of Information Technology at Mae Fah Luang University for providing facilities to this work.
Funding Information:
The authors are grateful for the grant from Mae Fah Luang University under the National Science, Research, and Innovation Fund (NSRF), Thailand : in part by Mae Fah Luang University under the grant Fundamental Fund/Basic Research Fund, Thailand : 652A03004 , in part by Mae Fah Luang University under the grant Fundamental Fund/Basic Research Fund, Thailand : 662A03013 , and in part by Computer and Communication Engineering for Capacity Building Research Center at Mae Fah Luang University, Thailand . The authors would like to thank the School of Information Technology at Mae Fah Luang University for providing facilities to this work.
Publisher Copyright:
© 2023 Elsevier Ltd
PY - 2023/6/15
Y1 - 2023/6/15
N2 - Particle filters (PFs) estimate the true parameter state from samples of states, called particles, that are drawn to construct an approximated posterior probability density function (PDF). Each drawn particle has its own probability of being the true state called importance weight. Both particle degeneracy and impoverishment are important problems found in generic PFs that cause particles to become trapped at local maxima. Genetic algorithms (GAs) were applied to herd the drawn particles to discover new high-likelihood state values in order to reshape the approximated posterior PDF and to enhance the accuracy of state estimation, while the particle diversity is maintained. We calculated the threshold weight for classifying particles as low-weight particles and high-weight particles. Each parent pair consists of a high-weight particle and a low-weight particle. High-weight particles are always kept unchanged. After each new offspring particle is found using GA operations, we must check its weight to ensure that it is actually superior to its low-weight parent. Otherwise, this offspring must not be allowed to replace its low-weight parent and must be destroyed. To ensure that the number of high-weight particles is adequate, some offspring particles evolve to be the new high-weight parent particles to produce high-weight offspring with further promoted diversity. Results showed that our approach significantly improves posterior PDF approximation and reduces errors in state estimation.
AB - Particle filters (PFs) estimate the true parameter state from samples of states, called particles, that are drawn to construct an approximated posterior probability density function (PDF). Each drawn particle has its own probability of being the true state called importance weight. Both particle degeneracy and impoverishment are important problems found in generic PFs that cause particles to become trapped at local maxima. Genetic algorithms (GAs) were applied to herd the drawn particles to discover new high-likelihood state values in order to reshape the approximated posterior PDF and to enhance the accuracy of state estimation, while the particle diversity is maintained. We calculated the threshold weight for classifying particles as low-weight particles and high-weight particles. Each parent pair consists of a high-weight particle and a low-weight particle. High-weight particles are always kept unchanged. After each new offspring particle is found using GA operations, we must check its weight to ensure that it is actually superior to its low-weight parent. Otherwise, this offspring must not be allowed to replace its low-weight parent and must be destroyed. To ensure that the number of high-weight particles is adequate, some offspring particles evolve to be the new high-weight parent particles to produce high-weight offspring with further promoted diversity. Results showed that our approach significantly improves posterior PDF approximation and reduces errors in state estimation.
KW - Genetic algorithms (GAs)
KW - Particle degeneracy
KW - Particle diversity
KW - Particle filtering (PF)
KW - Particle herding
KW - Particle impoverishment
KW - Posterior PDF
KW - Probability density function (PDF)
KW - Signal processing
UR - http://www.scopus.com/inward/record.url?scp=85151243144&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85151243144&partnerID=8YFLogxK
U2 - 10.1016/j.measurement.2023.112785
DO - 10.1016/j.measurement.2023.112785
M3 - Article
AN - SCOPUS:85151243144
SN - 0263-2241
VL - 214
JO - Measurement: Journal of the International Measurement Confederation
JF - Measurement: Journal of the International Measurement Confederation
M1 - 112785
ER -