Linwei Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Linwei Guo has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Weihua Cao
School of Automation, China University of Geosciences, Hubei, China
6 shared publications - Wenkai Hu
School of Automation, China University of Geosciences, Wuhan, China
6 shared publications - Min Wu
China University of Geosciences
5 shared publications - Leyu Bi
School of Automation, China University of Geosciences, Wuhan, China
2 shared publications - Jiang He1 shared publication
Min Wu
1 shared publication
Latest Publications
- 16 February 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 193
Spatial multiple attention-driven intelligent tuning of shape-performance coupling devices
- 16 February 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 193
Spatial multiple attention-driven intelligent tuning of shape-performance coupling devices
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 33 (10) , 3835-3847
Fuzzy Nonuniform Sampling for Inverse Decision-Making Modeling to Tune Microwave Filters
Microwave filters (MFs) are indispensable in communication systems for selecting specific frequency signals. The tuning of MFs is a demanding and time-consuming task, which can be addressed by the inverse decision-making model (IDMM). However, two main challenges arise in the sampling process for IDMM, namely, low efficiency due to the large number of samples and poor adaptability in the presence of uncertain initial positions. To overcome these challenges, a fuzzy nonuniform sampling (FNUS) method is proposed, leveraging the flexibility of the fuzzy logic system. Specifically, an adaptive sampling framework based on a fuzzy logic system is presented to handle the uncertainty of initial positions. Under this framework, a nonuniform sampling approach is devised to collect fewer samples far from the target and more samples close to the target. Given the similarity and single-sided distribution of samples in the raw dataset oriented to modeling, the tailored enhancement strategies are designed to improve dataset quality. Finally, the efficiency and adaptability of FNUS are demonstrated to be superior to the existing methods through simulations. Furthermore, the practicality of FNUS is validated by experiments on physical MFs.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 33 (10) , 3835-3847
Fuzzy Nonuniform Sampling for Inverse Decision-Making Modeling to Tune Microwave Filters
Microwave filters (MFs) are indispensable in communication systems for selecting specific frequency signals. The tuning of MFs is a demanding and time-consuming task, which can be addressed by the inverse decision-making model (IDMM). However, two main challenges arise in the sampling process for IDMM, namely, low efficiency due to the large number of samples and poor adaptability in the presence of uncertain initial positions. To overcome these challenges, a fuzzy nonuniform sampling (FNUS) method is proposed, leveraging the flexibility of the fuzzy logic system. Specifically, an adaptive sampling framework based on a fuzzy logic system is presented to handle the uncertainty of initial positions. Under this framework, a nonuniform sampling approach is devised to collect fewer samples far from the target and more samples close to the target. Given the similarity and single-sided distribution of samples in the raw dataset oriented to modeling, the tailored enhancement strategies are designed to improve dataset quality. Finally, the efficiency and adaptability of FNUS are demonstrated to be superior to the existing methods through simulations. Furthermore, the practicality of FNUS is validated by experiments on physical MFs.
- 4 September 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 165
Spatiotemporal feature fusion modeling for multistep prediction of strip temperature in continuous annealing processes
- 4 September 2025
- Published by Elsevier in Control Engineering Practice
- Vol. 165
Spatiotemporal feature fusion modeling for multistep prediction of strip temperature in continuous annealing processes
- 27 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Microwave and Wireless Technology Letters
- Vol. 35 (4) , 376-379
Attention-Modulated Feature Fusion Neural Network for Inverse Modeling of Microwave Filters
Inverse modeling is extensively applied in the design and tuning of microwave filters (MFs). Inverse models (IMs) take the features extracted from the high-dimensional electromagnetic parameters as input. How to make full use of features from multiple perspective is a critical issue for improving model accuracy. To solve it, this letter proposes an attention-modulated feature fusion neural network (AMFFNN). AMFFNN achieves multiperspective feature fusion (MPFF) at the input side and independent feature fusion (IFF) at the output side. In addition, feature fusion in AMFFNN is enhanced by attention modules to dynamically identify the importance of each feature. Statistical and comparative results of simulations demonstrate that AMFFNN outperforms existing methods in terms of accuracy, stability, and generalization.
- 27 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Microwave and Wireless Technology Letters
- Vol. 35 (4) , 376-379
Attention-Modulated Feature Fusion Neural Network for Inverse Modeling of Microwave Filters
Inverse modeling is extensively applied in the design and tuning of microwave filters (MFs). Inverse models (IMs) take the features extracted from the high-dimensional electromagnetic parameters as input. How to make full use of features from multiple perspective is a critical issue for improving model accuracy. To solve it, this letter proposes an attention-modulated feature fusion neural network (AMFFNN). AMFFNN achieves multiperspective feature fusion (MPFF) at the input side and independent feature fusion (IFF) at the output side. In addition, feature fusion in AMFFNN is enhanced by attention modules to dynamically identify the importance of each feature. Statistical and comparative results of simulations demonstrate that AMFFNN outperforms existing methods in terms of accuracy, stability, and generalization.
- 5 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54 (8) , 4828-4840
Dynamic Hybrid Models With Active Sampling and Adaptive Selection of Double-Domain Features for the Tuning of Microwave Cavity Filters
Microwave cavity filters are essential electromechanical coupling devices in communication systems. Structural-parameter tuning by experienced operators improves the filter performance but is demanding and time-consuming. The automatic tuning method has received extensive research attentions using data-driven modeling approaches. However, two main issues affect the accuracy and efficiency of the model construction: 1) features of tuning processes, as model inputs, have limited adaptability and extraction accuracy to different resonant states and 2) models require plentiful training data and the training process is time-consuming. Thus, dynamic hybrid models are developed in this study with self-selected inputs, self-organized samples, and a self-learning structure. First, spatial features are extracted to flexibly depict the tuning characteristic, and double-domain (spatial or circuital) features are selected adaptively to accommodate distinct resonance states. Second, a trustworthiness-curiosity-driven active sampling method is exploited to attain fewer and better-training data. Third, an improved broad learning systemBLS is developed using new modules of incremental node calculation and weight pruning, characterized by more lightweight and flexible structures. The proposed method is effective and flexible demonstrated by simulations and experiments, and the tuning task of microwave cavity filters is fulfilled in a more accurate and efficient manner.
- 5 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 54 (8) , 4828-4840
Dynamic Hybrid Models With Active Sampling and Adaptive Selection of Double-Domain Features for the Tuning of Microwave Cavity Filters
Microwave cavity filters are essential electromechanical coupling devices in communication systems. Structural-parameter tuning by experienced operators improves the filter performance but is demanding and time-consuming. The automatic tuning method has received extensive research attentions using data-driven modeling approaches. However, two main issues affect the accuracy and efficiency of the model construction: 1) features of tuning processes, as model inputs, have limited adaptability and extraction accuracy to different resonant states and 2) models require plentiful training data and the training process is time-consuming. Thus, dynamic hybrid models are developed in this study with self-selected inputs, self-organized samples, and a self-learning structure. First, spatial features are extracted to flexibly depict the tuning characteristic, and double-domain (spatial or circuital) features are selected adaptively to accommodate distinct resonance states. Second, a trustworthiness-curiosity-driven active sampling method is exploited to attain fewer and better-training data. Third, an improved broad learning systemBLS is developed using new modules of incremental node calculation and weight pruning, characterized by more lightweight and flexible structures. The proposed method is effective and flexible demonstrated by simulations and experiments, and the tuning task of microwave cavity filters is fulfilled in a more accurate and efficient manner.
- 28 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 70 (2) , 601-605
A Dynamic Tuning Decision-Making Model Using Multi-Feature Fusion
Dielectric Filters (DFs) are tuned to meet the requirements of 5G communication systems. The tuning methods based on Tuning Decision-Making Models (TDMMs) are efficient. However, how to build TDMMs accurately and fast is rather difficult due to the complex performance representation and the poor consistency of DFs. In this brief, a dynamic tuning decision-making model using multi-feature fusion is proposed. The contributions of this paper are as follows: 1) For the problem of incomplete feature representation of DFs performance, the multiple features are fused to improve the accuracy of TDMMs; 2) to deal with the problem that high-quality samples are challenging to obtain, a guided sampling method is designed to determine the sampling range, driven by the characteristics of DFs; 3) to solve the problem of inefficient modeling for inconsistent DFs, TDMMs are built dynamically using transfer learning. Finally, the excellent performance of the proposed method is demonstrated through comparative simulations.
- 28 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 70 (2) , 601-605
A Dynamic Tuning Decision-Making Model Using Multi-Feature Fusion
Dielectric Filters (DFs) are tuned to meet the requirements of 5G communication systems. The tuning methods based on Tuning Decision-Making Models (TDMMs) are efficient. However, how to build TDMMs accurately and fast is rather difficult due to the complex performance representation and the poor consistency of DFs. In this brief, a dynamic tuning decision-making model using multi-feature fusion is proposed. The contributions of this paper are as follows: 1) For the problem of incomplete feature representation of DFs performance, the multiple features are fused to improve the accuracy of TDMMs; 2) to deal with the problem that high-quality samples are challenging to obtain, a guided sampling method is designed to determine the sampling range, driven by the characteristics of DFs; 3) to solve the problem of inefficient modeling for inconsistent DFs, TDMMs are built dynamically using transfer learning. Finally, the excellent performance of the proposed method is demonstrated through comparative simulations.