Tao Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Tao Zhang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
Haohao Yi
2 shared publicationsQing Tao
2 shared publications- Bernardo Nugroho Yahya
Hankuk University of Foreign Studies – Global Campus Department of Industrial and Management Engineering
1 shared publication - Fang Chen
School of Information and Mathematics, Yangtze University, Jingzhou 434023, China
1 shared publication - Haohao Yi1 shared publication
Huiwen Yu
1 shared publication
Latest Publications
- 14 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 694
Hybrid Gaussian mixture model and Bayesian classification for predictive dynamic multi-objective optimization
- 14 May 2026
- Published by Elsevier in Neurocomputing
- Vol. 694
Hybrid Gaussian mixture model and Bayesian classification for predictive dynamic multi-objective optimization
- 21 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
The genetic algorithm based on generative adversarial network for dynamic multi-objective optimization problem and application
- 21 November 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 332
The genetic algorithm based on generative adversarial network for dynamic multi-objective optimization problem and application
- Open Access
- 5 August 2025
- Published by MIT Science Policy Review
- Vol. 6, 14-22
Artificial intelligence in biomedical diagnostics: Recent advances and transitions to liable regulation
Artificial intelligence (AI) technology has revolutionized the healthcare industry by enhancing the accuracy, efficiency, cost-effectiveness, and automation of modern biomedical diagnostics. AI algorithms and models such as machine learning (ML), deep learning (DL), natural language processing (NLP), tensor computing, and generative artificial intelligence have made significant progress and are integral in biomedical diagnosis. However, the development of AI in the biomedical field faces challenges related to policy regulation and ethical issues that need to be addressed for continued progress. This article briefly reviews the recent progress of AI technology in biomedical diagnosis and related policy regulation issues. We aim to provide new insights into transforming AI for biomedical diagnosis towards more liable, effective regulation and improve adaptive innovation of enterprises.
- 5 August 2025
- Published by MIT Science Policy Review
- Vol. 6, 14-22
Open AccessArtificial intelligence in biomedical diagnostics: Recent advances and transitions to liable regulation
Artificial intelligence (AI) technology has revolutionized the healthcare industry by enhancing the accuracy, efficiency, cost-effectiveness, and automation of modern biomedical diagnostics. AI algorithms and models such as machine learning (ML), deep learning (DL), natural language processing (NLP), tensor computing, and generative artificial intelligence have made significant progress and are integral in biomedical diagnosis. However, the development of AI in the biomedical field faces challenges related to policy regulation and ethical issues that need to be addressed for continued progress. This article briefly reviews the recent progress of AI technology in biomedical diagnosis and related policy regulation issues. We aim to provide new insights into transforming AI for biomedical diagnosis towards more liable, effective regulation and improve adaptive innovation of enterprises.
- 1 May 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 319
Improved proximal policy optimization for UAV tracking in complex environments
- 1 May 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 319
Improved proximal policy optimization for UAV tracking in complex environments
- Open Access
- 22 March 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (7) , 1033
A Solution Method for Partial Differential Equations by Fusing Fourier Operators and U-Net
In scientific and engineering calculation, the effective solution of partial differential equations (PDEs) has great significance. This paper presents an innovative method based on the combination of a U-Net neural network with Fourier neural operators, aiming to improve the accuracy and efficiency of solving partial differential equations. U-Net neural networks with a unique encoding–decoder structure and hopping connections can efficiently extract and integrate spatial-domain features and accurately describe the spatial structure of PDEs. The Fourier neural operator combines the advantages of neural networks and Fourier transform to learn the mapping relationship of high-dimensional data by training the linear transformation parameters in the detailed frequency domain of the data. Fourier transform is used to explore and process the frequency-domain features and capture the frequency characteristics of the solution of partial differential equations. By combining the two, this method not only retains spatial details but also makes full use of frequency-domain information, which significantly reduces the dependence of the model on large-scale data and improves the generalization ability of the model. The experimental results show that compared with the traditional method, this method performs well in various complex partial differential equation (PDE) solving tasks and achieves high accuracy.
- 22 March 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (7) , 1033
Open AccessA Solution Method for Partial Differential Equations by Fusing Fourier Operators and U-Net
In scientific and engineering calculation, the effective solution of partial differential equations (PDEs) has great significance. This paper presents an innovative method based on the combination of a U-Net neural network with Fourier neural operators, aiming to improve the accuracy and efficiency of solving partial differential equations. U-Net neural networks with a unique encoding–decoder structure and hopping connections can efficiently extract and integrate spatial-domain features and accurately describe the spatial structure of PDEs. The Fourier neural operator combines the advantages of neural networks and Fourier transform to learn the mapping relationship of high-dimensional data by training the linear transformation parameters in the detailed frequency domain of the data. Fourier transform is used to explore and process the frequency-domain features and capture the frequency characteristics of the solution of partial differential equations. By combining the two, this method not only retains spatial details but also makes full use of frequency-domain information, which significantly reduces the dependence of the model on large-scale data and improves the generalization ability of the model. The experimental results show that compared with the traditional method, this method performs well in various complex partial differential equation (PDE) solving tasks and achieves high accuracy.
- Open Access
- 25 February 2025
- Published by MDPI AG in Preprints.org
A Solution Method for Partial Differential Equations by Fusing Fourier Operators and U-Net
In scientific and engineering computations, the efficient solution of partial differential equations (PDEs) is of great significance. This paper proposes an innovative method based on the combination of the U-Net neural network and the Fourier neural operator, aiming to improve the accuracy and efficiency of solving PDEs. The unique encoder-decoder structure and skip connections of the U-Net neural network can effectively extract and integrate spatial domain features, accurately depicting the spatial structure of PDEs. The Fourier neural operator, by means of the Fourier transform, deeply explores and processes features in the frequency domain, capturing the frequency characteristics of the solutions of PDEs. By organically combining the two, this method not only preserves spatial details but also makes full use of frequency domain information. It significantly reduces the model's dependence on large scale data and enhances its generalization ability. Experimental results show that compared with traditional methods, this method performs outstandingly in various complex partial differential equation(PDE) solving tasks, achieving higher accuracy. It provides a new and highly promising solution for the solution of PDEs and is expected to be widely applied in related fields.
- 25 February 2025
- Published by MDPI AG in Preprints.org
Open AccessA Solution Method for Partial Differential Equations by Fusing Fourier Operators and U-Net
In scientific and engineering computations, the efficient solution of partial differential equations (PDEs) is of great significance. This paper proposes an innovative method based on the combination of the U-Net neural network and the Fourier neural operator, aiming to improve the accuracy and efficiency of solving PDEs. The unique encoder-decoder structure and skip connections of the U-Net neural network can effectively extract and integrate spatial domain features, accurately depicting the spatial structure of PDEs. The Fourier neural operator, by means of the Fourier transform, deeply explores and processes features in the frequency domain, capturing the frequency characteristics of the solutions of PDEs. By organically combining the two, this method not only preserves spatial details but also makes full use of frequency domain information. It significantly reduces the model's dependence on large scale data and enhances its generalization ability. Experimental results show that compared with traditional methods, this method performs outstandingly in various complex partial differential equation(PDE) solving tasks, achieving higher accuracy. It provides a new and highly promising solution for the solution of PDEs and is expected to be widely applied in related fields.
- 28 December 2024
- Published by Elsevier in Neurocomputing
- Vol. 621
A new prediction strategy for dynamic multi-objective optimization using hybrid Fuzzy C-Means and support vector machine
- 28 December 2024
- Published by Elsevier in Neurocomputing
- Vol. 621
A new prediction strategy for dynamic multi-objective optimization using hybrid Fuzzy C-Means and support vector machine
- Open Access
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
An Active Learning Method Based on Variational Autoencoder and DBSCAN Clustering
Active learning is aimed to sample the most informative data from the unlabeled pool, and diverse clustering methods have been applied to it. However, the distance‐based clustering methods usually cannot perform well in high dimensions and even begin to fail. In this paper, we propose a new active learning method combined with variational autoencoder (VAE) and density‐based spatial clustering of applications with noise (DBSCAN). It overcomes the difficulty of distance representation in high dimensions and prevents the distance concentration phenomenon from occurring in the computational learning literature with respect to high‐dimensional p‐norms. Finally, we compare our method with four common active learning methods and two other clustering algorithms combined with VAE on three datasets. The results demonstrate that our approach achieves competitive performance, and it is a new batch mode active learning algorithm designed for neural networks with a relatively small query batch size.
- 1 January 2021
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2021 (1)
Open AccessAn Active Learning Method Based on Variational Autoencoder and DBSCAN Clustering
Active learning is aimed to sample the most informative data from the unlabeled pool, and diverse clustering methods have been applied to it. However, the distance‐based clustering methods usually cannot perform well in high dimensions and even begin to fail. In this paper, we propose a new active learning method combined with variational autoencoder (VAE) and density‐based spatial clustering of applications with noise (DBSCAN). It overcomes the difficulty of distance representation in high dimensions and prevents the distance concentration phenomenon from occurring in the computational learning literature with respect to high‐dimensional p‐norms. Finally, we compare our method with four common active learning methods and two other clustering algorithms combined with VAE on three datasets. The results demonstrate that our approach achieves competitive performance, and it is a new batch mode active learning algorithm designed for neural networks with a relatively small query batch size.