Bin Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Bin Wang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
Jie Xue
College of Information and Network Security, Yunnan Police College, Kunming, China
3 shared publicationsXin Xiong
Faculty of Information Engineering & Automation, Kunming University of Science and Technology, Kunming, China
3 shared publications- Biao Yang
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650500, China
2 shared publications - Huaiping Jin
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China
2 shared publications Baojie Yang
Faculty of Information Engineering & Automation, Kunming University of Science and Technology, Kunming, China
1 shared publicationBi He
1 shared publication
Latest Publications
- 15 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-19
Soft Sensor Development Based on Unsupervised Dynamic Weighted Domain Adaptation for Quality Prediction of Batch Processes
Batch processes often encounter insufficiency of modeling data and differences of data distributions between different tanks and batches, which pose great challenges for accurate data-driven soft sensor modeling. Transfer learning has become a promising solution for addressing such problems; however, the existing transfer learning soft sensors still have problems, such as not considering the quality of source domain samples, insufficient utilization of hidden feature information, and only considering single distribution alignment. To address these issues, a dynamic weighted multilayer domain adaptation network (DWMDAN) is proposed for online estimation of key variables in batch processes. The training of the model consists of two stages: Stage I, the feature extractor and the first domain discriminator are utilized for adversarial training to compute the importance weights of the source domain samples, and the whole model is updated by combining weighted regression with global domain adaptation. Stage II, a hybrid domain adaptation mechanism is further designed to fine-tune the target model based on importance-weighted information. Specifically, adversarial and distribution domain adaptation methods are combined to adapt the marginal and conditional distributions between domains at multiple network layers of the model, where an adaptive factor is introduced to dynamically adjust the distribution weights. The superiority and effectiveness of the proposed method are demonstrated by an industrial fed-batch chlortetracycline (CTC) fermentation process. The experimental results show that the proposed method can extract richer and more reliable domain-invariant features for tank-to-tank knowledge transfer, thus delivering more accurate quality predictions.
- 15 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-19
Soft Sensor Development Based on Unsupervised Dynamic Weighted Domain Adaptation for Quality Prediction of Batch Processes
Batch processes often encounter insufficiency of modeling data and differences of data distributions between different tanks and batches, which pose great challenges for accurate data-driven soft sensor modeling. Transfer learning has become a promising solution for addressing such problems; however, the existing transfer learning soft sensors still have problems, such as not considering the quality of source domain samples, insufficient utilization of hidden feature information, and only considering single distribution alignment. To address these issues, a dynamic weighted multilayer domain adaptation network (DWMDAN) is proposed for online estimation of key variables in batch processes. The training of the model consists of two stages: Stage I, the feature extractor and the first domain discriminator are utilized for adversarial training to compute the importance weights of the source domain samples, and the whole model is updated by combining weighted regression with global domain adaptation. Stage II, a hybrid domain adaptation mechanism is further designed to fine-tune the target model based on importance-weighted information. Specifically, adversarial and distribution domain adaptation methods are combined to adapt the marginal and conditional distributions between domains at multiple network layers of the model, where an adaptive factor is introduced to dynamically adjust the distribution weights. The superiority and effectiveness of the proposed method are demonstrated by an industrial fed-batch chlortetracycline (CTC) fermentation process. The experimental results show that the proposed method can extract richer and more reliable domain-invariant features for tank-to-tank knowledge transfer, thus delivering more accurate quality predictions.
- 7 October 2022
- Published by Elsevier in Energy Conversion and Management
- Vol. 271, 116296
Adaptive forecasting of wind power based on selective ensemble of offline global and online local learning
- 7 October 2022
- Published by Elsevier in Energy Conversion and Management
- Vol. 271, 116296
Adaptive forecasting of wind power based on selective ensemble of offline global and online local learning
- Open Access
- 7 October 2019
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2019, 1-12
Tracking the Brain State Transition Process of Dynamic Function Connectivity Based on Resting State fMRI
BOLD-fMRI technology provides a good foundation for the research of human brain dynamic functional connectivity and brain state analysis. However, due to the complexity of brain function connectivity and the high dimensionality expression of brain dynamic attributions, more research studies are focusing on tracking the time-varying characteristics through the transition between different brain states. The transition process is considered to occur instantaneously at some special time point in the above research studies, whereas our work found the brain state transition may be completed in a time section gradually rather than instantaneously. In this paper, a brain state conversion rate model is constructed to observe the procedure of brain state transition trend at each time point, and the state change can be observed by the values of conversion rate. According to the results, the transition of status always lasts for a few time points, and a brain state network model with both steady state and transition state is presented. Network topological overlap coefficient is built to analyze the features of time-varying networks. With this method, some common regular patterns of time-varying characteristics can be observed strongly in healthy children but not in the autism children. This distinct can help us to distinguish children with autism from healthy children.
- 7 October 2019
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2019, 1-12
Open AccessTracking the Brain State Transition Process of Dynamic Function Connectivity Based on Resting State fMRI
BOLD-fMRI technology provides a good foundation for the research of human brain dynamic functional connectivity and brain state analysis. However, due to the complexity of brain function connectivity and the high dimensionality expression of brain dynamic attributions, more research studies are focusing on tracking the time-varying characteristics through the transition between different brain states. The transition process is considered to occur instantaneously at some special time point in the above research studies, whereas our work found the brain state transition may be completed in a time section gradually rather than instantaneously. In this paper, a brain state conversion rate model is constructed to observe the procedure of brain state transition trend at each time point, and the state change can be observed by the values of conversion rate. According to the results, the transition of status always lasts for a few time points, and a brain state network model with both steady state and transition state is presented. Network topological overlap coefficient is built to analyze the features of time-varying networks. With this method, some common regular patterns of time-varying characteristics can be observed strongly in healthy children but not in the autism children. This distinct can help us to distinguish children with autism from healthy children.
- Open Access
- 21 June 2017
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2017, 1-9
Research of Hubs Location Method for Weighted Brain Network Based on NoS-FA
As a complex network of many interlinked brain regions, there are some central hub regions which play key roles in the structural human brain network based on T1 and diffusion tensor imaging (DTI) technology. Since most studies about hubs location method in the whole human brain network are mainly concerned with the local properties of each single node but not the global properties of all the directly connected nodes, a novel hubs location method based on global importance contribution evaluation index is proposed in this study. The number of streamlines (NoS) is fused with normalized fractional anisotropy (FA) for more comprehensive brain bioinformation. The brain region importance contribution matrix and information transfer efficiency value are constructed, respectively, and then by combining these two factors together we can calculate the importance value of each node and locate the hubs. Profiting from both local and global features of the nodes and the multi-information fusion of human brain biosignals, the experiment results show that this method can detect the brain hubs more accurately and reasonably compared with other methods. Furthermore, the proposed location method is used in impaired brain hubs connectivity analysis of schizophrenia patients and the results are in agreement with previous studies.
- 21 June 2017
- Published by Wiley in Computational Intelligence and Neuroscience
- Vol. 2017, 1-9
Open AccessResearch of Hubs Location Method for Weighted Brain Network Based on NoS-FA
As a complex network of many interlinked brain regions, there are some central hub regions which play key roles in the structural human brain network based on T1 and diffusion tensor imaging (DTI) technology. Since most studies about hubs location method in the whole human brain network are mainly concerned with the local properties of each single node but not the global properties of all the directly connected nodes, a novel hubs location method based on global importance contribution evaluation index is proposed in this study. The number of streamlines (NoS) is fused with normalized fractional anisotropy (FA) for more comprehensive brain bioinformation. The brain region importance contribution matrix and information transfer efficiency value are constructed, respectively, and then by combining these two factors together we can calculate the importance value of each node and locate the hubs. Profiting from both local and global features of the nodes and the multi-information fusion of human brain biosignals, the experiment results show that this method can detect the brain hubs more accurately and reasonably compared with other methods. Furthermore, the proposed location method is used in impaired brain hubs connectivity analysis of schizophrenia patients and the results are in agreement with previous studies.
- 20 November 2013
- Published by China Science Publishing & Media Ltd. in Journal of Computer Applications
- Vol. 33 (11) , 3284-3287
Real-time monitoring and warning system of tunnel strain based on improved principal component analysis method
- 20 November 2013
- Published by China Science Publishing & Media Ltd. in Journal of Computer Applications
- Vol. 33 (11) , 3284-3287
Real-time monitoring and warning system of tunnel strain based on improved principal component analysis method
- 20 November 2012
- Published by China Science Publishing & Media Ltd. in Journal of Computer Applications
- Vol. 32 (11) , 3085-3088
Graphical meta-model construction method of embedded control system
- 20 November 2012
- Published by China Science Publishing & Media Ltd. in Journal of Computer Applications
- Vol. 32 (11) , 3085-3088
Graphical meta-model construction method of embedded control system
- 1 July 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19341768,p. 736-739
Time-Triggered Architecture (TTA) in Industry Hard R-T Embedded Control Software Design
Conventional event-triggered architecture (ETA) can not meet the industry hard R-T control requirements in security field. This paper studies a hard R-T control embedded control software design mode based on TTA; discusses the task scheduling principle and mode switching method which are based on TTA; and give a series of concrete formalized description and the sequence chart of execution.
- 1 July 2006
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19341768,p. 736-739
Time-Triggered Architecture (TTA) in Industry Hard R-T Embedded Control Software Design
Conventional event-triggered architecture (ETA) can not meet the industry hard R-T control requirements in security field. This paper studies a hard R-T control embedded control software design mode based on TTA; discusses the task scheduling principle and mode switching method which are based on TTA; and give a series of concrete formalized description and the sequence chart of execution.