Cunlu Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cunlu Xu has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
- Bin Wang
School of Computer Science and Artificial Intelligence, Nanjing University of Finance and Economics, Nanjing, China
2 shared publications - Chuangji Meng
School of Information and Communications Engineering, Xian Jiaotong University, Xian, China
2 shared publications - Jun Liu
Ulster University
2 shared publications Liman Lu
2 shared publicationsBin Wang
1 shared publicationDing Hong
School of Information Science and Engineering, Lanzhou University, Lanzhou, China
1 shared publication
Latest Publications
- 27 September 2025
- Published by Elsevier in Sleep Medicine
- Vol. 136, 106836
Neural correlates of shift work in nurses: Alterations in cortical gyrification and functional connectivity
- 27 September 2025
- Published by Elsevier in Sleep Medicine
- Vol. 136, 106836
Neural correlates of shift work in nurses: Alterations in cortical gyrification and functional connectivity
- 7 July 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 326
ADBNet: Asymmetric dual-branch network for indoor real-time RGB-D semantic segmentation
- 7 July 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 326
ADBNet: Asymmetric dual-branch network for indoor real-time RGB-D semantic segmentation
- 31 March 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 175
Multi-stage feature fusion network for polyp segmentation
- 31 March 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 175
Multi-stage feature fusion network for polyp segmentation
- 21 December 2024
- Published by Springer Nature
- p. 755-760
Semi-supervised Polyp Segmentation via a Dual-Teacher Student Framework
- 21 December 2024
- Published by Springer Nature
- p. 755-760
Semi-supervised Polyp Segmentation via a Dual-Teacher Student Framework
- Open Access
- 21 July 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (14) , 2531
Deep Transfer Learning Method Based on Automatic Domain Alignment and Moment Matching
Domain discrepancy is a key research problem in the field of deep domain adaptation. Two main strategies are used to reduce the discrepancy: the parametric method and the nonparametric method. Both methods have achieved good results in practical applications. However, research on whether the combination of the two can further reduce domain discrepancy has not been conducted. Therefore, in this paper, a deep transfer learning method based on automatic domain alignment and moment matching (DA-MM) is proposed. First, an automatic domain alignment layer is embedded in the front of each domain-specific layer of a neural network structure to preliminarily align the source and target domains. Then, a moment matching measure (such as MMD distance) is added between every domain-specific layer to map the source and target domain features output by the alignment layer to a common reproduced Hilbert space. The results of an extensive experimental analysis over several public benchmarks show that DA-MM can reduce the distribution discrepancy between the two domains and improve the domain adaptation performance.
- 21 July 2022
- Published by MDPI AG in Mathematics
- Vol. 10 (14) , 2531
Open AccessDeep Transfer Learning Method Based on Automatic Domain Alignment and Moment Matching
Domain discrepancy is a key research problem in the field of deep domain adaptation. Two main strategies are used to reduce the discrepancy: the parametric method and the nonparametric method. Both methods have achieved good results in practical applications. However, research on whether the combination of the two can further reduce domain discrepancy has not been conducted. Therefore, in this paper, a deep transfer learning method based on automatic domain alignment and moment matching (DA-MM) is proposed. First, an automatic domain alignment layer is embedded in the front of each domain-specific layer of a neural network structure to preliminarily align the source and target domains. Then, a moment matching measure (such as MMD distance) is added between every domain-specific layer to map the source and target domain features output by the alignment layer to a common reproduced Hilbert space. The results of an extensive experimental analysis over several public benchmarks show that DA-MM can reduce the distribution discrepancy between the two domains and improve the domain adaptation performance.
- Open Access
- 31 May 2019
- Published by Frontiers Media SA in Frontiers in Chemistry
- Vol. 7, 385
Prediction of the Antioxidant Response Elements' Response of Compound by Deep Learning
The antioxidant response elements (AREs) play a significant role in occurrence of oxidative stress and may cause multitudinous toxicity effects in the pathogenesis of a variety of diseases. Determining if one compound can activate AREs is crucial for the assessment of potential risk of compound. Here, a series of predictive models by applying multiple deep learning algorithms including deep neural networks (DNN), convolution neural networks (CNN), recurrent neural networks (RNN), and highway networks (HN) were constructed and validated based on Tox21 challenge dataset and applied to predict whether the compounds are the activators or inactivators of AREs. The built models were evaluated by various of statistical parameters, such as sensitivity, specificity, accuracy, Matthews correlation coefficient (MCC) and receiver operating characteristic (ROC) curve. The DNN prediction model based on fingerprint features has best prediction ability, with accuracy of 0.992, 0.914, and 0.917 for the training set, test set, and validation set, respectively. Consequently, these robust models can be adopted to predict the ARE response of molecules fast and accurately, which is of great significance for the evaluation of safety of compounds in the process of drug discovery and development.
- 31 May 2019
- Published by Frontiers Media SA in Frontiers in Chemistry
- Vol. 7, 385
Open AccessPrediction of the Antioxidant Response Elements' Response of Compound by Deep Learning
The antioxidant response elements (AREs) play a significant role in occurrence of oxidative stress and may cause multitudinous toxicity effects in the pathogenesis of a variety of diseases. Determining if one compound can activate AREs is crucial for the assessment of potential risk of compound. Here, a series of predictive models by applying multiple deep learning algorithms including deep neural networks (DNN), convolution neural networks (CNN), recurrent neural networks (RNN), and highway networks (HN) were constructed and validated based on Tox21 challenge dataset and applied to predict whether the compounds are the activators or inactivators of AREs. The built models were evaluated by various of statistical parameters, such as sensitivity, specificity, accuracy, Matthews correlation coefficient (MCC) and receiver operating characteristic (ROC) curve. The DNN prediction model based on fingerprint features has best prediction ability, with accuracy of 0.992, 0.914, and 0.917 for the training set, test set, and validation set, respectively. Consequently, these robust models can be adopted to predict the ARE response of molecules fast and accurately, which is of great significance for the evaluation of safety of compounds in the process of drug discovery and development.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 593-597
Kernel Extreme Learning Machine Based Domain Adaptation
In this paper, a new domain adaptation learning method is proposed by jointing weighted balanced feature matching and instance reweighting based on kernel extreme learning machine (KELM). Specifically, for the weighted balance feature matching, it can not only adapt the importance of the difference between the marginal and the condition, but also deal with the class imbalances adaptively for the domain adaptation learning. In addition, the instance reweighting is combined to reduce the effect of unrelated instances on inter domain differences in source domain instances. The experimental results show the performance of the proposed approach is better than the state-of-the-art approaches in terms of the classification accuracy and operation speed, especially in the speed of operation is particularly prominent.
- 1 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 593-597
Kernel Extreme Learning Machine Based Domain Adaptation
In this paper, a new domain adaptation learning method is proposed by jointing weighted balanced feature matching and instance reweighting based on kernel extreme learning machine (KELM). Specifically, for the weighted balance feature matching, it can not only adapt the importance of the difference between the marginal and the condition, but also deal with the class imbalances adaptively for the domain adaptation learning. In addition, the instance reweighting is combined to reduce the effect of unrelated instances on inter domain differences in source domain instances. The experimental results show the performance of the proposed approach is better than the state-of-the-art approaches in terms of the classification accuracy and operation speed, especially in the speed of operation is particularly prominent.
- 1 July 2009
- Published by Elsevier in Pattern Recognition Letters
- Vol. 30 (9) , 799-804
Rolling penetrate descriptor for shape-based image retrieval and object recognition
- 1 July 2009
- Published by Elsevier in Pattern Recognition Letters
- Vol. 30 (9) , 799-804
Rolling penetrate descriptor for shape-based image retrieval and object recognition