Yanxiang He
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
Yanxiang He has a total of 109 co-authors. Here are the top co-authors by number of shared publications:
- Wenjie Li
The Hong Kong Polytechnic University, Hong Kong, China
6 shared publications - Jun Zhang
East China University of Technology
5 shared publications - Fanfan Shen
School of Computer Science, Nanjing Audit University,Nanjing,China,211815
3 shared publications - Fang Liu
Wuhan Software Engineering Vocational College (Wuhan Open University)
3 shared publications - Furu Wei
The Hong Kong Polytechnic University
3 shared publications - Libing Wu
Wuhan University
3 shared publications
Latest Publications
- 3 February 2026
- Published by Elsevier in Information Processing & Management
- Vol. 63 (5)
FedDPKD: Federated learning with dual-phase knowledge distillation for label distribution skew
- 3 February 2026
- Published by Elsevier in Information Processing & Management
- Vol. 63 (5)
FedDPKD: Federated learning with dual-phase knowledge distillation for label distribution skew
- Open Access
VGGNet and Attention Mechanism-Based Image Quality Assessment Algorithm in Symmetry Edge Intelligence Systems
With the rapid development of Internet of Things (IoT) technology, the number of devices connected to the network is exploding. How to improve the performance of edge devices has become an important challenge. Research on quality evaluation algorithms for brain tumor images remains scarce within symmetry edge intelligence systems. Additionally, the data volume in brain tumor datasets is frequently inadequate to support the training of neural network models. Most existing non-reference image quality assessment methods are based on natural statistical laws or construct a single-network model without considering visual perception characteristics, resulting in significant differences between the final evaluation results and subjective perception. To address these issues, we propose the AM-VGG-IQA (Attention Module Visual Geometry Group Image Quality Assessment) algorithm and extend the brain tumor MRI dataset. Visual saliency features with attention mechanism modules are integrated into AM-VGG-IQA. The integration of visual saliency features brings the evaluation outcomes of the model more in line with human perception. Meanwhile, the attention mechanism module cuts down on network parameters and expedites the training speed. For the brain tumor MRI dataset, our model achieves 85% accuracy, enabling it to effectively accomplish the task of evaluating brain tumor images in edge intelligence systems. Additionally, we carry out cross-dataset experiments. It is worth noting that, under varying training and testing ratios, the performance of AM-VGG-IQA remains relatively stable, which effectively demonstrates its remarkable robustness for edge applications.
Open AccessVGGNet and Attention Mechanism-Based Image Quality Assessment Algorithm in Symmetry Edge Intelligence Systems
With the rapid development of Internet of Things (IoT) technology, the number of devices connected to the network is exploding. How to improve the performance of edge devices has become an important challenge. Research on quality evaluation algorithms for brain tumor images remains scarce within symmetry edge intelligence systems. Additionally, the data volume in brain tumor datasets is frequently inadequate to support the training of neural network models. Most existing non-reference image quality assessment methods are based on natural statistical laws or construct a single-network model without considering visual perception characteristics, resulting in significant differences between the final evaluation results and subjective perception. To address these issues, we propose the AM-VGG-IQA (Attention Module Visual Geometry Group Image Quality Assessment) algorithm and extend the brain tumor MRI dataset. Visual saliency features with attention mechanism modules are integrated into AM-VGG-IQA. The integration of visual saliency features brings the evaluation outcomes of the model more in line with human perception. Meanwhile, the attention mechanism module cuts down on network parameters and expedites the training speed. For the brain tumor MRI dataset, our model achieves 85% accuracy, enabling it to effectively accomplish the task of evaluating brain tumor images in edge intelligence systems. Additionally, we carry out cross-dataset experiments. It is worth noting that, under varying training and testing ratios, the performance of AM-VGG-IQA remains relatively stable, which effectively demonstrates its remarkable robustness for edge applications.
- 29 May 2024
- Published by Springer Nature
- p. 481-497
Reliability Scheduling Algorithm for Heterogeneous Multi-verified Time Systems
- 29 May 2024
- Published by Springer Nature
- p. 481-497
Reliability Scheduling Algorithm for Heterogeneous Multi-verified Time Systems
- Open Access
- 15 January 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 17 (1) , 1-31
A Hardware Design Framework for Computer Vision Models Based on Reconfigurable Devices
In computer vision, the joint development of the algorithm and computing dimensions cannot be separated. Models and algorithms are constantly evolving, while hardware designs must adapt to new or updated algorithms. Reconfigurable devices are recognized as important platforms for computer vision applications because of their reconfigurability. There are two typical design approaches: customized and overlay design. However, existing work is unable to achieve both efficient performance and scalability to adapt to a wide range of models. To address both considerations, we propose a design framework based on reconfigurable devices to provide unified support for computer vision models. It provides software-programmable modules while leaving unit design space for problem-specific algorithms. Based on the proposed framework, we design a model mapping method and a hardware architecture with two processor arrays to enable dynamic and static reconfiguration, thereby relieving redesign pressure. In addition, resource consumption and efficiency can be balanced by adjusting the hyperparameter. In experiments on CNN, vision Transformer, and vision MLP models, our work’s throughput is improved by 18.8x–33.6x and 1.4x–2.0x compared to CPU and GPU. Compared to others on the same platform, accelerators based on our framework can better balance resource consumption and efficiency.
- 15 January 2024
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 17 (1) , 1-31
Open AccessA Hardware Design Framework for Computer Vision Models Based on Reconfigurable Devices
In computer vision, the joint development of the algorithm and computing dimensions cannot be separated. Models and algorithms are constantly evolving, while hardware designs must adapt to new or updated algorithms. Reconfigurable devices are recognized as important platforms for computer vision applications because of their reconfigurability. There are two typical design approaches: customized and overlay design. However, existing work is unable to achieve both efficient performance and scalability to adapt to a wide range of models. To address both considerations, we propose a design framework based on reconfigurable devices to provide unified support for computer vision models. It provides software-programmable modules while leaving unit design space for problem-specific algorithms. Based on the proposed framework, we design a model mapping method and a hardware architecture with two processor arrays to enable dynamic and static reconfiguration, thereby relieving redesign pressure. In addition, resource consumption and efficiency can be balanced by adjusting the hyperparameter. In experiments on CNN, vision Transformer, and vision MLP models, our work’s throughput is improved by 18.8x–33.6x and 1.4x–2.0x compared to CPU and GPU. Compared to others on the same platform, accelerators based on our framework can better balance resource consumption and efficiency.
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 32 (6) , 1304-1318
Rating Text Classification with Weighted Negative Supervision on Classifier Layer
Bidirectional encoder representations from transformers (BERT) gives full play to the advantages of the attention mechanism, improves the performance of sentence representation, and provides a better choice for various natural language understanding (NLU) tasks. Many methods using BERT as the pre-trained model achieve state-of-the-art performance in almost various text classification scenarios. Among them, the multitask learning framework combining the negative supervision and the pre-trained model solves the issue of the model performance degradation that occurs as the semantic similarity of texts conflicts with the classification standards. The current model does not consider the degree of difference between labels, which leads to insufficient difference information learned by the model, and affects classification performance, especially in the rating classification tasks. On the basis of the multi-task learning model, this paper fully considers the degree of difference between labels, which is expressed by using weights to solve the above problems. We supervise negative sam-ples on the classifier layer instead of the encoder layer, so that the classifier layer can also learn the difference information between the labels. Experimental results show that our model can not only performs well in 2-class and multi-class rating text classification tasks, but also performs well in different languages.
- 1 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 32 (6) , 1304-1318
Rating Text Classification with Weighted Negative Supervision on Classifier Layer
Bidirectional encoder representations from transformers (BERT) gives full play to the advantages of the attention mechanism, improves the performance of sentence representation, and provides a better choice for various natural language understanding (NLU) tasks. Many methods using BERT as the pre-trained model achieve state-of-the-art performance in almost various text classification scenarios. Among them, the multitask learning framework combining the negative supervision and the pre-trained model solves the issue of the model performance degradation that occurs as the semantic similarity of texts conflicts with the classification standards. The current model does not consider the degree of difference between labels, which leads to insufficient difference information learned by the model, and affects classification performance, especially in the rating classification tasks. On the basis of the multi-task learning model, this paper fully considers the degree of difference between labels, which is expressed by using weights to solve the above problems. We supervise negative sam-ples on the classifier layer instead of the encoder layer, so that the classifier layer can also learn the difference information between the labels. Experimental results show that our model can not only performs well in 2-class and multi-class rating text classification tasks, but also performs well in different languages.
- 1 June 2022
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 94 (11) , 1243-1251
Optimization of Big Data Parallel Scheduling Based on Dynamic Clustering Scheduling Algorithm
- 1 June 2022
- Published by Springer Nature in Journal of Signal Processing Systems
- Vol. 94 (11) , 1243-1251
Optimization of Big Data Parallel Scheduling Based on Dynamic Clustering Scheduling Algorithm
- 9 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 1986-1999
A Fully Authenticated Diffie-Hellman Protocol and Its Application in WSNs
The secure authenticated key establishment between nodes in Wireless Sensor Networks (WSNs) has not been fully solved in the existing schemes. It’s a good idea to apply the Diffie-Hellman protocol to address it perfectly, but the existing authenticated Diffie-Hellman (ADH) protocols are not perfect because their authentication are partial or delayed. In this paper, we first present a concept of full authentication and propose a new fully authenticated Diffie-Hellman (FADH) prototype with light-certificate-based authentication. And then based on the theory of elliptic curve cryptography, we construct the TinyADH (Tiny Authenticated Diffie-Hellman) protocol with applying the FADH in WSNs. Compared with the existing similar solutions, TinyADH has lower communication overload, is easier to implement into existing standards, and more secure under equivalent computational complexity. The experimental results show that using this scheme for a successful key agreement between two nodes averagely takes about 54 seconds on TelosB. Moreover, the simulation results indicate that repeated key agreement can improve the secure connectivity rate. However, considering the cost performance ratio, it is advisable to take 2 runs of the negotiation.
- 9 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 17 (15566013) , 1986-1999
A Fully Authenticated Diffie-Hellman Protocol and Its Application in WSNs
The secure authenticated key establishment between nodes in Wireless Sensor Networks (WSNs) has not been fully solved in the existing schemes. It’s a good idea to apply the Diffie-Hellman protocol to address it perfectly, but the existing authenticated Diffie-Hellman (ADH) protocols are not perfect because their authentication are partial or delayed. In this paper, we first present a concept of full authentication and propose a new fully authenticated Diffie-Hellman (FADH) prototype with light-certificate-based authentication. And then based on the theory of elliptic curve cryptography, we construct the TinyADH (Tiny Authenticated Diffie-Hellman) protocol with applying the FADH in WSNs. Compared with the existing similar solutions, TinyADH has lower communication overload, is easier to implement into existing standards, and more secure under equivalent computational complexity. The experimental results show that using this scheme for a successful key agreement between two nodes averagely takes about 54 seconds on TelosB. Moreover, the simulation results indicate that repeated key agreement can improve the secure connectivity rate. However, considering the cost performance ratio, it is advisable to take 2 runs of the negotiation.
- Open Access
- 26 June 2019
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
- Vol. 15 (3) , 1-46
CORES
The relatively high cost of record deserialization is increasingly becoming the bottleneck of column-based storage systems in tree-structured applications [58]. Due to record transformation in the storage layer, unnecessary processing costs derived from fields and rows irrelevant to queries may be very heavy in nested schemas, significantly wasting the computational resources in large-scale analytical workloads. This leads to the question of how to reduce both the deserialization and IO costs of queries with highly selective filters following arbitrary paths in a nested schema. We present CORES (Column-Oriented Regeneration Embedding Scheme) to push highly selective filters down into column-based storage engines, where each filter consists of several filtering conditions on a field. By applying highly selective filters in the storage layer, we demonstrate that both the deserialization and IO costs could be significantly reduced. We show how to introduce fine-grained composition on filtering results. We generalize this technique by two pair-wise operations, rollup and drilldown, such that a series of conjunctive filters can effectively deliver their payloads in nested schema. The proposed methods are implemented on an open-source platform. For practical purposes, we highlight how to build a column storage engine and how to drive a query efficiently based on a cost model. We apply this design to the nested relational model especially when hierarchical entities are frequently required by ad hoc queries. The experiments, including a real workload and the modified TPCH benchmark, demonstrate that CORES improves the performance by 0.7×--26.9× compared to state-of-the-art platforms in scan-intensive workloads.
- 26 June 2019
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Storage
- Vol. 15 (3) , 1-46
Open AccessCORES
The relatively high cost of record deserialization is increasingly becoming the bottleneck of column-based storage systems in tree-structured applications [58]. Due to record transformation in the storage layer, unnecessary processing costs derived from fields and rows irrelevant to queries may be very heavy in nested schemas, significantly wasting the computational resources in large-scale analytical workloads. This leads to the question of how to reduce both the deserialization and IO costs of queries with highly selective filters following arbitrary paths in a nested schema. We present CORES (Column-Oriented Regeneration Embedding Scheme) to push highly selective filters down into column-based storage engines, where each filter consists of several filtering conditions on a field. By applying highly selective filters in the storage layer, we demonstrate that both the deserialization and IO costs could be significantly reduced. We show how to introduce fine-grained composition on filtering results. We generalize this technique by two pair-wise operations, rollup and drilldown, such that a series of conjunctive filters can effectively deliver their payloads in nested schema. The proposed methods are implemented on an open-source platform. For practical purposes, we highlight how to build a column storage engine and how to drive a query efficiently based on a cost model. We apply this design to the nested relational model especially when hierarchical entities are frequently required by ad hoc queries. The experiments, including a real workload and the modified TPCH benchmark, demonstrate that CORES improves the performance by 0.7×--26.9× compared to state-of-the-art platforms in scan-intensive workloads.
- 8 April 2019
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 75 (10) , 6220-6238
Periodic learning-based region selection for energy-efficient MLC STT-RAM cache
- 8 April 2019
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 75 (10) , 6220-6238
Periodic learning-based region selection for energy-efficient MLC STT-RAM cache
- Open Access
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 27 (5) , 985-994
Memory Request Priority Based Warp Scheduling for GPUs
High performance of GPGPU comes from its super massive multithreading, which makes it more and more widely used especially in the field of throughputoriented. Data locality is one of the important factors affecting the performance of GPGPU. Although GPGPU can exploit intra/inter-warp locality by itself in part, there is still large improvement space for that. In our work, we analyze the characteristics of different applications and propose memory request based warp scheduling to better exploit inter-warp spatial locality. This method can make some warps with good inter-warp locality run faster, which is beneficial to improve the whole performance. Our experimental results show that our proposed method can achieve 24.7% and 11.9% average performance improvement over LRR and MRPB respectively.
- 1 September 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Chinese Journal of Electronics
- Vol. 27 (5) , 985-994
Open AccessMemory Request Priority Based Warp Scheduling for GPUs
High performance of GPGPU comes from its super massive multithreading, which makes it more and more widely used especially in the field of throughputoriented. Data locality is one of the important factors affecting the performance of GPGPU. Although GPGPU can exploit intra/inter-warp locality by itself in part, there is still large improvement space for that. In our work, we analyze the characteristics of different applications and propose memory request based warp scheduling to better exploit inter-warp spatial locality. This method can make some warps with good inter-warp locality run faster, which is beneficial to improve the whole performance. Our experimental results show that our proposed method can achieve 24.7% and 11.9% average performance improvement over LRR and MRPB respectively.