Denghui Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Denghui Wang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
Junhui Zhao
2 shared publications- Bin Huang
Department of Information Engineering, East China Jiaotong University, Nanchang 330013, P. R. China
1 shared publication - Dezhong Yao
School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, China
1 shared publication - Hanqing Xiong
School of Information and Software Engineering, East China Jiaotong University, Nanchang, China
1 shared publication - Jian Liu
Department of Information Engineering, East China Jiaotong University, Nanchang, China
1 shared publication - Liwei Hu
School of Information Engineering Department, East China Jiaotong University, Nanchang 330013, China
1 shared publication
Latest Publications
- 16 July 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 38 (10)
Structured Deep Graph Clustering Network Based on Consistency Constraint
Graph clustering is an essential task in data analysis. Recently, there has been a notable trend in the application of deep learning in graph clustering. However, it is worth noting that existing deep graph clustering methods primarily focus on the topological information of nodes while overlooking the use of attribute information in the learned feature representations. In addition, they do not address the consistency of the space distribution in attribute and structure clustering results. To tackle these critical issues, a novel structured deep graph clustering network with consistency constraint (CC-DGC) is proposed. The network first constructs an autoencoder to learn and transmit hierarchical attribute information to the graph autoencoder (GAE). Subsequently, the GAE integrates the received hierarchical attribute information with extracted topological information to generate enhanced clustering representations. Moreover, this paper designs a consistency constraint module to promote consistency between the autoencoder and the GAE by optimizing the cluster space distributions they produce. Finally, the feature extraction and clustering classification processes are synchronized and optimized in a self-supervised manner within a unified framework. Extensive experiments illustrate that the proposed CC-DGC demonstrates superiority over the state-of-the-art deep graph clustering methods on five benchmark datasets.
- 16 July 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Pattern Recognition and Artificial Intelligence
- Vol. 38 (10)
Structured Deep Graph Clustering Network Based on Consistency Constraint
Graph clustering is an essential task in data analysis. Recently, there has been a notable trend in the application of deep learning in graph clustering. However, it is worth noting that existing deep graph clustering methods primarily focus on the topological information of nodes while overlooking the use of attribute information in the learned feature representations. In addition, they do not address the consistency of the space distribution in attribute and structure clustering results. To tackle these critical issues, a novel structured deep graph clustering network with consistency constraint (CC-DGC) is proposed. The network first constructs an autoencoder to learn and transmit hierarchical attribute information to the graph autoencoder (GAE). Subsequently, the GAE integrates the received hierarchical attribute information with extracted topological information to generate enhanced clustering representations. Moreover, this paper designs a consistency constraint module to promote consistency between the autoencoder and the GAE by optimizing the cluster space distributions they produce. Finally, the feature extraction and clustering classification processes are synchronized and optimized in a self-supervised manner within a unified framework. Extensive experiments illustrate that the proposed CC-DGC demonstrates superiority over the state-of-the-art deep graph clustering methods on five benchmark datasets.
- Open Access
- 19 April 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (8) , 3460
Research and Application of an Improved Sparrow Search Algorithm
Association rule mining utilizing metaheuristic algorithms is a prominent area of study in the field of data mining. However, when working with extensive data, conventional metaheuristic algorithms exhibit limited search efficiency and face challenges in deriving high-quality rules in multi-objective association rule mining. In order to tackle this issue, a novel approach called the adaptive Weibull distribution sparrow search algorithm is introduced. This algorithm leverages the adaptive Weibull distribution to improve the traditional sparrow search algorithm’s capability to escape local optima and enhance convergence during different iterations. Secondly, an enhancement search strategy and a multidirectional learning strategy are introduced to expand the search range of the population. This paper empirically evaluates the proposed method under real datasets and compares it with other leading methods by using three association rule metrics, namely, support, confidence, and lift, as the fitness function. The experimental results show that the quality of the obtained association rules is significantly improved when dealing with datasets of different sizes.
- 19 April 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (8) , 3460
Open AccessResearch and Application of an Improved Sparrow Search Algorithm
Association rule mining utilizing metaheuristic algorithms is a prominent area of study in the field of data mining. However, when working with extensive data, conventional metaheuristic algorithms exhibit limited search efficiency and face challenges in deriving high-quality rules in multi-objective association rule mining. In order to tackle this issue, a novel approach called the adaptive Weibull distribution sparrow search algorithm is introduced. This algorithm leverages the adaptive Weibull distribution to improve the traditional sparrow search algorithm’s capability to escape local optima and enhance convergence during different iterations. Secondly, an enhancement search strategy and a multidirectional learning strategy are introduced to expand the search range of the population. This paper empirically evaluates the proposed method under real datasets and compares it with other leading methods by using three association rule metrics, namely, support, confidence, and lift, as the fitness function. The experimental results show that the quality of the obtained association rules is significantly improved when dealing with datasets of different sizes.
- Open Access
- 27 May 2023
- Published by MDPI AG in Electronics
- Vol. 12 (11) , 2431
Predicting Power Generation from a Combined Cycle Power Plant Using Transformer Encoders with DNN
With the development of the Smart Grid, accurate prediction of power generation is becoming an increasingly crucial task. The primary goal of this research is to create an efficient and reliable forecasting model to estimate the full-load power generation of a combined-cycle power plant (CCPP). The dataset used in this research is a subset of the publicly available UCI Machine Learning Repository. It contains 9568 items of data collected from a CCPP during its full load operation over a span of six years. To enhance the accuracy of power generation forecasting, a novel forecasting method based on Transformer encoders with deep neural networks (DNN) was proposed. The proposed model exploits the ability of the Transformer encoder to extract valuable information. Furthermore, bottleneck DNN blocks and residual connections are used in the DNN component. In this study, a series of experiments were conducted, and the performance of the proposed model was evaluated against other state-of-the-art machine learning models based on the CCPP dataset. The experimental results illustrated that using Transformer encoders along with DNN can considerably improve the accuracy of predicting CCPPs power generation (RMSE = 3.5370, MAE = 2.4033, MAPE = 0.5307%, and R2 = 0.9555).
- 27 May 2023
- Published by MDPI AG in Electronics
- Vol. 12 (11) , 2431
Open AccessPredicting Power Generation from a Combined Cycle Power Plant Using Transformer Encoders with DNN
With the development of the Smart Grid, accurate prediction of power generation is becoming an increasingly crucial task. The primary goal of this research is to create an efficient and reliable forecasting model to estimate the full-load power generation of a combined-cycle power plant (CCPP). The dataset used in this research is a subset of the publicly available UCI Machine Learning Repository. It contains 9568 items of data collected from a CCPP during its full load operation over a span of six years. To enhance the accuracy of power generation forecasting, a novel forecasting method based on Transformer encoders with deep neural networks (DNN) was proposed. The proposed model exploits the ability of the Transformer encoder to extract valuable information. Furthermore, bottleneck DNN blocks and residual connections are used in the DNN component. In this study, a series of experiments were conducted, and the performance of the proposed model was evaluated against other state-of-the-art machine learning models based on the CCPP dataset. The experimental results illustrated that using Transformer encoders along with DNN can considerably improve the accuracy of predicting CCPPs power generation (RMSE = 3.5370, MAE = 2.4033, MAPE = 0.5307%, and R2 = 0.9555).
- 3 October 2022
- Published by Elsevier in Ad Hoc Networks
- Vol. 138
A node trust evaluation method of vehicle-road-cloud collaborative system based on federated learning
- 3 October 2022
- Published by Elsevier in Ad Hoc Networks
- Vol. 138
A node trust evaluation method of vehicle-road-cloud collaborative system based on federated learning
- Open Access
- 23 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 185730-185739
A Novel QoS-Awared Grid Routing Protocol in the Sensing Layer of Internet of Vehicles Based on Reinforcement Learning
This paper proposes a novel Quality of Service (QoS) grid routing protocol in Wireless Multimedia Sensor Networks (WMSN) based on reinforcement learning to guarantee Quality of Service in WMSN based on the sensing layer of the Internet of Vehicles (IoV). The sensing layer of IoV acquires abundant information to handle complex road traffic problems. Moreover, WMSN is rich in perceptual data. This suggests a need for complex acquisition, processing, storage, transfer of text and video data. These issues are elevated due, impart, increased requirements for QoS in WMSN. However, WMSN is heterogeneous, and its network topology is changing dynamically. Therefore, ensuring high QoS in a complex environment has become a challenge. This research suggests that least delay can be accomplished by calculating the distance among the nodes through grid identification number (GID) to acquire the nearest path from the source to the sink. Additionally, optimal grid coordinators with the highest reliability can be elected by making all the nodes in the grid for reinforcement learning to acquire their performance knowledge of reliability and delay. This enables high QoS performance in terms of reliability and end-to-end delay. The results indicate that the QoS of QoS-awared grid routing (QAGR) protocol is higher compared with the traditional grid-based clustering routing protocol.
- 23 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 185730-185739
Open AccessA Novel QoS-Awared Grid Routing Protocol in the Sensing Layer of Internet of Vehicles Based on Reinforcement Learning
This paper proposes a novel Quality of Service (QoS) grid routing protocol in Wireless Multimedia Sensor Networks (WMSN) based on reinforcement learning to guarantee Quality of Service in WMSN based on the sensing layer of the Internet of Vehicles (IoV). The sensing layer of IoV acquires abundant information to handle complex road traffic problems. Moreover, WMSN is rich in perceptual data. This suggests a need for complex acquisition, processing, storage, transfer of text and video data. These issues are elevated due, impart, increased requirements for QoS in WMSN. However, WMSN is heterogeneous, and its network topology is changing dynamically. Therefore, ensuring high QoS in a complex environment has become a challenge. This research suggests that least delay can be accomplished by calculating the distance among the nodes through grid identification number (GID) to acquire the nearest path from the source to the sink. Additionally, optimal grid coordinators with the highest reliability can be elected by making all the nodes in the grid for reinforcement learning to acquire their performance knowledge of reliability and delay. This enables high QoS performance in terms of reliability and end-to-end delay. The results indicate that the QoS of QoS-awared grid routing (QAGR) protocol is higher compared with the traditional grid-based clustering routing protocol.
- 22 November 2018
- Published by Springer Nature in Photonic Network Communications
- Vol. 37 (2) , 179-186
A new approach to heterogeneous wireless sensor networks reliability evaluation based on perception layer in internet of vehicles
- 22 November 2018
- Published by Springer Nature in Photonic Network Communications
- Vol. 37 (2) , 179-186
A new approach to heterogeneous wireless sensor networks reliability evaluation based on perception layer in internet of vehicles