Chenguang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Chenguang Zhang has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Yan Zhang
School of Mathematics and Statistics, Hainan University, Haikou, China
3 shared publications - Xuejiao Du
School of Mathematics and Statistics, Hainan University, Haikou 570100, China
2 shared publications - Yuexian Hou
College of Intelligence and Computing Tianjin University Tianjin China
2 shared publications - Chaozhi Yu
School of Mathematics and Statistics, Hainan University, Haikou, China
1 shared publication Chengyin Wang
College of Chemistry and Chemical Engineering, Yangzhou University, Yangzhou 225002, China
1 shared publicationDaohan Zha
Hunan Key Laboratory of Land Resources Evaluation and Utilization, Changsha, Hunan, 410007, China
1 shared publication
Latest Publications
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1926-1930
EAL-ICNet: Enhanced Attention Lightweight Network With Multi-Scale Transformer Modules for IC Image Segmentation
The rapid development of deep learning, especially convolutional neural networks, has greatly enhanced automated segmentation of integrated circuit (IC) images. However, current methods face challenges: 1) Large-scale industrial IC images require high-throughput models, which many high-parameter networks struggle to meet. 2) Conventional convolutions are limited in capturing global dependencies within circuit structures. 3) Optical microscopy images often contain noise and artifacts that hinder accurate segmentation. To address these issues, we propose EAL-ICNet (Enhanced Attention Lightweight IC Network), a lightweight architecture designed for IC image segmentation. EAL-ICNet integrates a Depthwise Asymmetric Bottleneck (DAB) module, combining depthwise asymmetric and dilated convolutions for improved efficiency and reduced complexity. Inspired by Transformer mechanisms, Token Statistics Self-Attention (TSSA) and Parallel Multi-Scale Attention (PMA) are introduced to capture non-local dependencies and suppress noise. EAL-ICNet also employs multi-scale contextual modeling for better feature extraction. We evaluate the model on four real IC datasets and demonstrate its ability to balance accuracy and inference speed, making it suitable for industrial applications. The code is available at https://github.com/chndaz/EAL-ICNet.
- 20 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 33 (10709908) , 1926-1930
EAL-ICNet: Enhanced Attention Lightweight Network With Multi-Scale Transformer Modules for IC Image Segmentation
The rapid development of deep learning, especially convolutional neural networks, has greatly enhanced automated segmentation of integrated circuit (IC) images. However, current methods face challenges: 1) Large-scale industrial IC images require high-throughput models, which many high-parameter networks struggle to meet. 2) Conventional convolutions are limited in capturing global dependencies within circuit structures. 3) Optical microscopy images often contain noise and artifacts that hinder accurate segmentation. To address these issues, we propose EAL-ICNet (Enhanced Attention Lightweight IC Network), a lightweight architecture designed for IC image segmentation. EAL-ICNet integrates a Depthwise Asymmetric Bottleneck (DAB) module, combining depthwise asymmetric and dilated convolutions for improved efficiency and reduced complexity. Inspired by Transformer mechanisms, Token Statistics Self-Attention (TSSA) and Parallel Multi-Scale Attention (PMA) are introduced to capture non-local dependencies and suppress noise. EAL-ICNet also employs multi-scale contextual modeling for better feature extraction. We evaluate the model on four real IC datasets and demonstrate its ability to balance accuracy and inference speed, making it suitable for industrial applications. The code is available at https://github.com/chndaz/EAL-ICNet.
- 30 September 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 298
PFL-TEnet: Personalized federated learning for wind power forecasting via time-series embedding and hypernetwork modeling
- 30 September 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 298
PFL-TEnet: Personalized federated learning for wind power forecasting via time-series embedding and hypernetwork modeling
- Open Access
- 4 December 2024
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (6) , 1-22
Label-Based Disentanglement Measure among Hidden Units of Deep Learning
- 4 December 2024
- Published by Springer Nature in Neural Processing Letters
- Vol. 56 (6) , 1-22
Open AccessLabel-Based Disentanglement Measure among Hidden Units of Deep Learning
- Open Access
A Deep Neural Network Regularization Measure: The Class-Based Decorrelation Method
In response to the challenge of overfitting, which may lead to a decline in network generalization performance, this paper proposes a new regularization technique, called the class-based decorrelation method (CDM). Specifically, this method views the neurons in a specific hidden layer as base learners, and aims to boost network generalization as well as model accuracy by minimizing the correlation among individual base learners while simultaneously maximizing their class-conditional correlation. Intuitively, CDM not only promotes diversity among the hidden neurons, but also enhances their cohesiveness among them when processing samples from the same class. Comparative experiments conducted on various datasets using deep models demonstrate that CDM effectively reduces overfitting and improves classification performance.
Open AccessA Deep Neural Network Regularization Measure: The Class-Based Decorrelation Method
In response to the challenge of overfitting, which may lead to a decline in network generalization performance, this paper proposes a new regularization technique, called the class-based decorrelation method (CDM). Specifically, this method views the neurons in a specific hidden layer as base learners, and aims to boost network generalization as well as model accuracy by minimizing the correlation among individual base learners while simultaneously maximizing their class-conditional correlation. Intuitively, CDM not only promotes diversity among the hidden neurons, but also enhances their cohesiveness among them when processing samples from the same class. Comparative experiments conducted on various datasets using deep models demonstrate that CDM effectively reduces overfitting and improves classification performance.
- Open Access
- 6 December 2023
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 16 (1) , 1-15
A Quantum-Inspired Direct Learning Strategy for Positive and Unlabeled Data
Learning from only positive and unlabeled (PU) data has broad applications in fields such as web data mining, product recommendations and medical diagnosis, which aims to train a binary classifier in the absence of negative labeled data. However, due to the lack of negative label information, prevailing PU learning methods usually rely on prior knowledge of unknown class distributions heavily. In fact, without additional constraints imposed by the prior knowledge, a direct learning strategy to coordinate the underlying clustering information in unlabeled data with the label information from positive training data is often considered challenging. To tackle this challenge, we propose a direct PU learning strategy using quantum formalization. By employing neural networks as backends, the samples are mapped into two-qubit composite systems, which should be understood here as mathematical entities encapsulating various classical distributions of two classical bits. Subsequently, the two qubits within the systems are trained to be as independent as possible from each other, capturing patterns of different classes. At the same time, their measurement results serving as the model outputs are encouraged to be maximally dissimilar. These characteristics enable effective training of classifiers on PU data. After formulating an appropriate discriminant rule, we introduce a quantum-inspired PU method named qPU using the direct learning strategy. This method not only has the potential to alleviate parameter sensitivity issues caused by prior estimation in other methods but is also straightforward to implement. Finally, experiments conducted on 13 classical datasets validate the effectiveness of qPU.
- 6 December 2023
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 16 (1) , 1-15
Open AccessA Quantum-Inspired Direct Learning Strategy for Positive and Unlabeled Data
Learning from only positive and unlabeled (PU) data has broad applications in fields such as web data mining, product recommendations and medical diagnosis, which aims to train a binary classifier in the absence of negative labeled data. However, due to the lack of negative label information, prevailing PU learning methods usually rely on prior knowledge of unknown class distributions heavily. In fact, without additional constraints imposed by the prior knowledge, a direct learning strategy to coordinate the underlying clustering information in unlabeled data with the label information from positive training data is often considered challenging. To tackle this challenge, we propose a direct PU learning strategy using quantum formalization. By employing neural networks as backends, the samples are mapped into two-qubit composite systems, which should be understood here as mathematical entities encapsulating various classical distributions of two classical bits. Subsequently, the two qubits within the systems are trained to be as independent as possible from each other, capturing patterns of different classes. At the same time, their measurement results serving as the model outputs are encouraged to be maximally dissimilar. These characteristics enable effective training of classifiers on PU data. After formulating an appropriate discriminant rule, we introduce a quantum-inspired PU method named qPU using the direct learning strategy. This method not only has the potential to alleviate parameter sensitivity issues caused by prior estimation in other methods but is also straightforward to implement. Finally, experiments conducted on 13 classical datasets validate the effectiveness of qPU.
- 24 July 2022
- Published by Elsevier in Chinese Chemical Letters
- Vol. 34 (4) , 107700
Detection of avian influenza virus H9N2 based on self-driving and self-sensing microcantilever piezoelectric sensor
- 24 July 2022
- Published by Elsevier in Chinese Chemical Letters
- Vol. 34 (4) , 107700
Detection of avian influenza virus H9N2 based on self-driving and self-sensing microcantilever piezoelectric sensor
- 7 July 2021
- Published by Springer Nature
- p. 172-183
A Regularization-Based Positive and Unlabeled Learning Algorithm for One-Class Classification of Remote Sensing Data
- 7 July 2021
- Published by Springer Nature
- p. 172-183
A Regularization-Based Positive and Unlabeled Learning Algorithm for One-Class Classification of Remote Sensing Data
- 3 June 2020
- Published by American Physical Society (APS) in Physical Review A
- Vol. 101 (6) , 062103
Quantum observation scheme universally identifying causalities from correlations
It has long been recognized as a difficult problem to determine whether the observed statistical correlations between two classical variables arise from causality or from common causes. Recent research has shown that, in a quantum theoretical framework, the mechanisms of entanglement and quantum coherence provide advantages in tackling this problem. In some particular cases, quantum common causes and quantum causality can be effectively distinguished by using observations alone. However, these solutions do not apply to all cases. There still exist a large class of cases in which quantum common causes and quantum causality cannot be distinguished. In this paper, along the line of considering unitary transformation as causality in the quantum world, we formally show that quantum common causes and quantum causality are universally separable. Based on the analysis, we further provide a general method to discriminate the two.
- 3 June 2020
- Published by American Physical Society (APS) in Physical Review A
- Vol. 101 (6) , 062103
Quantum observation scheme universally identifying causalities from correlations
It has long been recognized as a difficult problem to determine whether the observed statistical correlations between two classical variables arise from causality or from common causes. Recent research has shown that, in a quantum theoretical framework, the mechanisms of entanglement and quantum coherence provide advantages in tackling this problem. In some particular cases, quantum common causes and quantum causality can be effectively distinguished by using observations alone. However, these solutions do not apply to all cases. There still exist a large class of cases in which quantum common causes and quantum causality cannot be distinguished. In this paper, along the line of considering unitary transformation as causality in the quantum world, we formally show that quantum common causes and quantum causality are universally separable. Based on the analysis, we further provide a general method to discriminate the two.
- Open Access
- 1 December 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 371 (3) , 032030
Geological Disaster Survey and Treatment Strategies of Yingwanzhen Subway Station, Changsha
In order to solve such problems as ground subsidence, water and mud bursting and shield machine foundering in subway construction which are caused by water-rich karst geological conditions, complete technological process is established to detect and treat karst in urban areas. The occurrence of natural electric field frequency selection method and groundwater determine groundwater occurrence vector that karst and fault fracture zone, and make use of the grouting technology of karst fracture with the treatment. The construction of Yingwanzhen Stationon Changsha Metro Line No. 4 provesthe favorable effect of the detection technology and treatment measures, which provides experience and reference for the construction of Changsha subway and underground engineeringin other cities with water-rich karst areas.
- 1 December 2019
- Published by IOP Publishing in IOP Conference Series: Earth and Environmental Science
- Vol. 371 (3) , 032030
Open AccessGeological Disaster Survey and Treatment Strategies of Yingwanzhen Subway Station, Changsha
In order to solve such problems as ground subsidence, water and mud bursting and shield machine foundering in subway construction which are caused by water-rich karst geological conditions, complete technological process is established to detect and treat karst in urban areas. The occurrence of natural electric field frequency selection method and groundwater determine groundwater occurrence vector that karst and fault fracture zone, and make use of the grouting technology of karst fracture with the treatment. The construction of Yingwanzhen Stationon Changsha Metro Line No. 4 provesthe favorable effect of the detection technology and treatment measures, which provides experience and reference for the construction of Changsha subway and underground engineeringin other cities with water-rich karst areas.