bSRWPSO-FKNN: A boosted PSO with fuzzy K-nearest neighbor classifier for predicting atopic dermatitis disease DOI Creative Commons
Yupeng Li, Dong Zhao,

Zhangze Xu

et al.

Frontiers in Neuroinformatics, Journal Year: 2023, Volume and Issue: 16

Published: Jan. 16, 2023

Introduction Atopic dermatitis (AD) is an allergic disease with extreme itching that bothers patients. However, diagnosing AD depends on clinicians’ subjective judgment, which may be missed or misdiagnosed sometimes. Methods This paper establishes a medical prediction model for the first time basis of enhanced particle swarm optimization (SRWPSO) algorithm and fuzzy K-nearest neighbor (FKNN), called bSRWPSO-FKNN, practiced dataset related to patients AD. In SRWPSO, Sobol sequence introduced into (PSO) make distribution initial population more uniform, thus improving population’s diversity traversal. At same time, this study also adds random replacement strategy adaptive weight updating process PSO overcome shortcomings poor convergence accuracy easily fall local optimum PSO. core optimize classification performance FKNN through binary SRWPSO. Results To prove has scientific significance, successfully demonstrates advantages SRWPSO in well-known algorithms benchmark function validation experiments. Secondly, article bSRWPSO-FKNN practical significance effectiveness nine public datasets. Discussion The 10 times 10-fold cross-validation experiments demonstrate can pick up key features AD, including content lymphocytes (LY), Cat dander, Milk, Dermatophagoides Pteronyssinus/Farinae, Ragweed, Cod, Total IgE. Therefore, established method practically aids diagnosis

Language: Английский

Multi-strategy particle swarm and ant colony hybrid optimization for airport taxiway planning problem DOI
Wu Deng, Lirong Zhang, Xiangbing Zhou

et al.

Information Sciences, Journal Year: 2022, Volume and Issue: 612, P. 576 - 593

Published: Sept. 6, 2022

Language: Английский

Citations

122
Co-evolutionary competitive swarm optimizer with three-phase for large-scale complex optimization problem DOI
Chen Huang, Xiangbing Zhou,

Xiaojuan Ran

et al.

Information Sciences, Journal Year: 2022, Volume and Issue: 619, P. 2 - 18

Published: Nov. 11, 2022

Language: Английский

Citations

118
Dynamic hybrid mechanism-based differential evolution algorithm and its application DOI
Yingjie Song,

Xing Cai,

Xiangbing Zhou

et al.

Expert Systems with Applications, Journal Year: 2022, Volume and Issue: 213, P. 118834 - 118834

Published: Sept. 15, 2022

Language: Английский

Citations

106
Adaptive cylinder vector particle swarm optimization with differential evolution for UAV path planning DOI
Chen Huang, Xiangbing Zhou,

Xiaojuan Ran

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2023, Volume and Issue: 121, P. 105942 - 105942

Published: Feb. 9, 2023

Language: Английский

Citations

101
Hierarchical Harris hawks optimizer for feature selection DOI Creative Commons
Lemin Peng, Zhennao Cai, Ali Asghar Heidari

et al.

Journal of Advanced Research, Journal Year: 2023, Volume and Issue: 53, P. 261 - 278

Published: Jan. 20, 2023

Feature selection is a typical NP-hard problem. The main methods include filter, wrapper-based, and embedded methods. Because of its characteristics, the wrapper method must swarm intelligence algorithm, performance in feature closely related to algorithm's quality. Therefore, it essential choose design suitable algorithm improve based on wrapper. Harris hawks optimization (HHO) superb approach that has just been introduced. It high convergence rate powerful global search capability but an unsatisfactory effect dimensional problems or complex problems. we introduced hierarchy HHO's ability deal with selection. To make obtain good accuracy fewer features run faster selection, improved HHO named EHHO. On 30 UCI datasets, (EHHO) can achieve very classification less running time features. We first conducted extensive experiments 23 classical benchmark functions compared EHHO many state-of-the-art metaheuristic algorithms. Then transform into binary (bEHHO) through conversion function verify extraction data sets. Experiments show better speed minimum than other peers. At same time, HHO, significantly weakness dealing functions. Moreover, datasets repository, bEHHO comparative Compared original bHHO, excellent also bHHO time.

Language: Английский

Citations

55
State of health prediction of lithium-ion batteries using particle swarm optimization with Levy flight and generalized opposition-based learning DOI
Bide Zhang, Wei Liu, Yongxiang Cai

et al.

Journal of Energy Storage, Journal Year: 2024, Volume and Issue: 84, P. 110816 - 110816

Published: Feb. 8, 2024

Language: Английский

Citations

21
ABC-GSPBFT: PBFT with grouping score mechanism and optimized consensus process for flight operation data-sharing DOI
Junjie Xu,

Yali Zhao,

Huayue Chen

et al.

Information Sciences, Journal Year: 2022, Volume and Issue: 624, P. 110 - 127

Published: Dec. 27, 2022

Language: Английский

Citations

66
Performance prediction of a reverse osmosis unit using an optimized Long Short-term Memory model by hummingbird optimizer DOI Creative Commons
Fadl A. Essa, Mohamed Abd Elaziz, Mohammed Azmi Al‐Betar

et al.

Process Safety and Environmental Protection, Journal Year: 2022, Volume and Issue: 169, P. 93 - 106

Published: Oct. 29, 2022

Language: Английский

Citations

54
A novel performance trend prediction approach using ENBLS with GWO DOI

Huimin Zhao,

Panpan Zhang, Ruichao Zhang

et al.

Measurement Science and Technology, Journal Year: 2022, Volume and Issue: 34(2), P. 025018 - 025018

Published: Oct. 14, 2022

Abstract Bearings are a core component of rotating machinery, and directly affect its reliability operational efficiency. Effective evaluation bearing’s state is key to ensuring the safe operation equipment. In this paper, novel prediction method bearing performance trends based on elastic net broad learning system (ENBLS) grey wolf optimization (GWO) algorithm proposed. The proposed combines advantages ENBLS GWO algorithms achieve better results. order solve problem that traditional regression may lead unsatisfactory results long training time, we propose trend ENBLS. To further improve accuracy, utilize optimize various parameters present in model model. data whole life cycle from 2012 IEEE PHM challenge selected verify effectiveness method. show has high accuracy stability.

Language: Английский

Citations

47
A Bearing Fault Diagnosis Method Based on Improved Mutual Dimensionless and Deep Learning DOI
Jianbin Xiong, Minghui Liu, Chunlin Li

et al.

IEEE Sensors Journal, Journal Year: 2023, Volume and Issue: 23(16), P. 18338 - 18348

Published: April 26, 2023

Under nonlinear and nonstationary dynamic conditions, the fault diagnosis methods based on multidimensional dimensionless indicators (MDIs) often cannot provide effective accurate health monitoring in of petrochemical units. In view above problems, this article preprocesses signal reconstructs a new indicator. The indicator combines complementary ensemble empirical mode decomposition (CEEMD) with MDI, named multidimensionless (CEMDIs). By using sequential mapping method, CEMDI processed data can be converted into Gramian angular fields (GAFs). processing sparse data, advantages convolutional neural networks (CNNs) were used to identify different types. method is validated three datasets, motor bearing provided by Case Western Reserve University, multistage centrifugal fan machinery failure prevention technology challenge data. Compared traditional index latest published literature, CNN exhibit good performance identifying types under which verifies its effectiveness superiority.

Language: Английский

Citations

28