Fusion k-means clustering and multi-head self-attention mechanism for a multivariate time prediction model with feature selection DOI
Mingwei Cai, Xueling Ma, Chao Zhang

et al.

International Journal of Machine Learning and Cybernetics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 12, 2024

Language: Английский

Specific surface area (SSA) of perovskites with uncertainty estimation approach DOI Creative Commons
Zied Hosni, Sofiene Achour,

Fatma Saâdi

et al.

Computational Materials Science, Journal Year: 2025, Volume and Issue: 249, P. 113668 - 113668

Published: Jan. 9, 2025

Language: Английский

Citations

1
A new multivariate decomposition-ensemble approach with denoised neighborhood rough set for stock price forecasting over time-series information system DOI
Juncheng Bai, Bingzhen Sun,

Yuqi Guo

et al.

Applied Intelligence, Journal Year: 2025, Volume and Issue: 55(4)

Published: Jan. 9, 2025

Language: Английский

Citations

0
Hybrid experimental design methodology for non-destructive transfer of industrial-scale frozen sand molds: an improved response surface approach with engineering validation DOI

Benfengnian Dong,

Hu Wu,

Wu Binglin

et al.

The International Journal of Advanced Manufacturing Technology, Journal Year: 2025, Volume and Issue: unknown

Published: March 15, 2025

Language: Английский

Citations

0
Short-term multi-site solar irradiance prediction with dynamic-graph-convolution-based spatial-temporal correlation capturing DOI
Haixiang Zang, Wentao Li, Lilin Cheng

et al.

Renewable Energy, Journal Year: 2025, Volume and Issue: unknown, P. 122945 - 122945

Published: March 1, 2025

Language: Английский

Citations

0
An Enhanced Tunicate Swarm Algorithm with Symmetric Cooperative Swarms for Training Feedforward Neural Networks DOI Open Access

Chengtao Du,

Jinzhong Zhang

Symmetry, Journal Year: 2024, Volume and Issue: 16(7), P. 866 - 866

Published: July 8, 2024

The input layer, hidden and output layer are three models of neural processors that comprise feedforward networks. In this paper, an enhanced tunicate swarm algorithm based on a differential sequencing alteration operator (ETSA) with symmetric cooperative swarms is presented to train objective accomplish minimum classification errors the most appropriate network layout by regulating layers’ connection weights neurons’ deviation thresholds according transmission error between anticipated authentic output. TSA mimics jet motorization scavenging mitigate directional collisions maintain greatest solution customized regional. However, exhibits disadvantages low computational accuracy, slow convergence speed, easy search stagnation. has adaptable localized extraction screening broaden identification scope, enrich population creativity, expedite computation productivity, avoid ETSA integrates exploration exploitation stagnation, which sufficient stability flexibility acquire finest solution. was distinguished from ETTAO, EPSA, SABO, SAO, EWWPA, YDSE, monitoring seventeen alternative datasets. experimental results confirm maintains profound sustainability durability exaggerated convergence, locate acceptable error, equalize prospection yield faster superior calculation greater categorization accuracy.

Language: Английский

Citations

2
Fuzzy Neural Network Applications in Biomass Gasification and Pyrolysis for Biofuel Production: A Review DOI Creative Commons
V V Bukhtoyarov, В С Тынченко, K A Bashmur

et al.

Energies, Journal Year: 2024, Volume and Issue: 18(1), P. 16 - 16

Published: Dec. 24, 2024

The increasing demand for sustainable energy has spurred interest in biofuels as a renewable alternative to fossil fuels. Biomass gasification and pyrolysis are two prominent thermochemical conversion processes biofuel production. While these effective, they often influenced by complex, nonlinear, uncertain factors, making optimization prediction challenging. This study highlights the application of fuzzy neural networks (FNNs)—a hybrid approach that integrates strengths logic networks—as novel tool address challenges. Unlike traditional methods, FNNs offer enhanced adaptability accuracy modeling nonlinear systems, them uniquely suited biomass processes. review not only ability optimize predict performance but also identifies their role advancing decision-making frameworks. Key challenges, benefits, future research opportunities explored, showcasing transformative potential

Language: Английский

Citations

1
DSGN: Log-Based Anomaly Diagnosis with Dynamic Semantic Gate Networks DOI

Haitian Yang,

Degang Sun,

Yan Wang

et al.

Information Sciences, Journal Year: 2024, Volume and Issue: 680, P. 121174 - 121174

Published: July 11, 2024

Language: Английский

Citations

0
Optimization of the cruising speed for high-speed trains to reduce energy consumed by motion resistances DOI

Fang-Ru Zhou,

Kai Zhou, Duo Zhang

et al.

Applied Energy, Journal Year: 2024, Volume and Issue: 374, P. 124039 - 124039

Published: Aug. 1, 2024

Language: Английский

Citations

0
VTNet: A multi-domain information fusion model for long-term multi-variate time series forecasting with application in irrigation water level DOI
Rui Dai, Zheng Wang, Wanliang Wang

et al.

Applied Soft Computing, Journal Year: 2024, Volume and Issue: 167, P. 112251 - 112251

Published: Sept. 17, 2024

Language: Английский

Citations

0
Fusion k-means clustering and multi-head self-attention mechanism for a multivariate time prediction model with feature selection DOI
Mingwei Cai, Xueling Ma, Chao Zhang

et al.

International Journal of Machine Learning and Cybernetics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 12, 2024

Language: Английский

Citations

0