Qingkun Chen

Qingkun Chen

Auto-generated profile, based on publicly available information

Qingkun Chen

Institute of Medical Information, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 February 2021 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
WHWenjin Huang
Wenjin Huang
HWHuangtao Wu
Huangtao Wu
QCQingkun Chen
Qingkun Chen
CLConghui Luo
Conghui Luo
SZShihao Zeng
Shihao Zeng
YHYihua Huang
Yihua Huang
The field-programmable gate array (FPGA)-based CNN hardware accelerator adopting single-computing-engine (CE) architecture or multi-CE architecture has attracted great attention in recent years. The actual throughput of the accelerator is also getting higher and higher but is still far below the theoretical throughput due to the inefficient computing resource mapping mechanism and data supply problem, and so on. To solve these problems, a novel composite hardware CNN accelerator architecture is proposed in this article. To perform the convolution layer (CL) efficiently, a novel multiCE architecture based on a row-level pipelined streaming strategy is proposed. For each CE, an optimized mapping mechanism is proposed to improve its computing resource utilization ratio and an efficient data system with continuous data supply is designed to avoid the idle state of the CE. Besides, to relieve the off-chip bandwidth stress, a weight data allocation strategy is proposed. To perform the fully connected layer (FCL), a single-CE architecture based on a batch-based computing method is proposed. Based on these design methods and strategies, visual geometry group network-16 (VGG-16) and ResNet-101 are both implemented on the XC7VX980T FPGA platform. The VGG-16 accelerator consumed 3395 multipliers and got the throughput of 1 TOPS at 150 MHz, that is, about 98.15% of the theoretical throughput ( $2 \times 3395 \times 150$ MOPS). Similarly, the ResNet-101 accelerator achieved 600 GOPS at 100 MHz, about 96.12% of the theoretical throughput ( $2 \times 3121 \times 100$ MOPS).

26 July 2021 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
QCQingkun Chen
Qingkun Chen
WHWenjin Huang
Wenjin Huang
YPYuze Peng
Yuze Peng
YHYihua Huang
Yihua Huang
In network-on-chip (NoC) designs, the intellectual property (IP) mapping problem is a critical issue and is usually solved by heuristic searches. However, heuristic searches suffer from the problem of easily falling into the local optimum. To tackle this problem, this article proposes a reinforcement learning-based framework (RLF), which enhances the performance of heuristic searches through the neural network-based probability model. Within this framework, first, a neural network-based probability model for IP mapping is built and trained by reinforcement learning instead of supervised learning to overcome the difficulty of obtaining a high-quality labeled training set. Second, based on the pretrained probability model, the model-based heuristic uses the probability model to generate the initial population and then employs heuristic searches to find the optimal solution. Two model-based heuristics, i.e., the message passing neural network-pointer network-based genetic algorithm (MPN-GA) and the message passing neural network-pointer network-based PSMAP (MPN-PSMAP), are proposed as specific instances. Simulation results show that the MPN-GA reduces the communication cost by an average of 9.32% than the genetic algorithm (GA). The MPN-PSMAP achieves an average reduction in the communication cost of 8.37% than the PSMAP. Finally, two extensions are given as examples to show the good extensibility of this framework.

6 November 2020 in IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Verified
Journal Article
Closed access
QCQingkun Chen
Qingkun Chen
WHWenjin Huang
Wenjin Huang
YZYuanshan Zhang
Yuanshan Zhang
YHYihua Huang
Yihua Huang
The IP core mapping optimization problem is an NP-hard problem in network-on-chip design. Because of the computational complexity of an IP core mapping, the MPNN-Ptr networks composed of the graph networks and the pointer networks are proposed to model the IP core mapping. The neural network IP core mapping model (NNMM) can effectively evaluate the probability of each mapping solution as the optimal solution to an IP core mapping optimization problem. Then, an IP core mapping algorithm, the neural mapping algorithm (NMA), is proposed. In this algorithm, the global search is realized by sampling the mapping solutions with a high probability evaluated by NNMM. The sampled candidate mapping solutions according to probability can effectively decrease the candidate mapping solution space, which can reduce invalid searches and avoid getting stuck at local minima. Then, the 2-opt algorithm is used as a local search to improve the quality of mapping further. Simulation results show that the MPNN-Ptr networks can effectively model the IP core mapping. Compared with the state-of-the-art mapping algorithms, NMA produces better solutions for both specific applications and random applications. NMA achieves a 7.90% communication cost reduction on average than the classic mapping algorithm: NMAP.

19 October 2022 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
QCQingkun Chen
Qingkun Chen
WHWenjin Huang
Wenjin Huang
YHYihua Huang
Yihua Huang
The intellectual property (IP) mapping problem is an NP-hard problem in network-on-chip (NoC) designs and is often solved by the genetic Algorithm. In the genetic algorithm (GA), new populations are generated by crossover and mutation operators. However, these operators consider neither the prior knowledge of the IP mapping problem nor the historical experience of the population evolution, easily causing the GA to converge prematurely to the local optima. To solve this problem, a learnable model-based GA (LMGA) is proposed, which introduces a learnable model and a hybridization scheme of the model and GA. 1) the learnable model is implemented by a novel neural network-based probability model for the IP mapping problem, i.e., the message passing attention network (MAN). Moreover, the learnable model is pretrained then updated by learning the features of high-fitness individuals among the population to predict a better probability distribution of the optimal solution in a specific IP mapping problem. 2) The scheme updates the population of certain generations of the GA by sampling the learnable model. Hence, the population evolution is guided by the learnable model to avoid premature convergence. Simulation results show that the MAN achieves a faster training speed and models the large-scale IP mapping problem better than the message passing neural network-pointer network (MPN) in the previous work. The LMGA saves an average of 5.68% and 5.23% in the communication energy and average network delay, respectively, than the state-of-the-art algorithm, i.e., the message passing neural network-pointer network-based genetic algorithm (MPN-GA).

1 January 2026 in IET Image Processing
Verified
Journal Article
Open access
JZJiahao Zhao
Jiahao Zhao
HHHaibo Hong
Haibo Hong
QCQingkun Chen
Qingkun Chen
Skeleton‐based hand gesture recognition is critical for human–computer interaction and virtual reality. However, two fundamental challenges persist in existing methods. Regarding spatial modelling, the inability to capture global dependencies among distant joints remains a bottleneck. Regarding temporal modelling, the prevalent coupled scheme tends to obscure fine‐grained spatial structures during temporal aggregation, thereby limiting the learning of accurate gesture dynamics. To address these issues, this paper proposes the synergistic graph‐transformer network (SGT‐Net). First, a dynamic dual‐stream attention (DDA) module integrates a graph convolutional network (GCN) stream and a Transformer stream for synergistic spatial modelling, where a dynamic fusion gate (DFG) dynamically orchestrates the two streams via context‐aware fusion weights coordinating local and global cues complementarily. Second, a hierarchical cascaded architecture based on spatiotemporal units (STUs) progressively refines spatial features through the DDA module prior to temporal aggregation by the MS‐TCN module. By stacking STUs and progressively expanding channels, the network achieves hierarchical abstraction to higher‐level semantic features for better spatiotemporal modelling. Experiments on SHREC'17 Track, NTU‐RGB+D, and NW‐UCLA datasets demonstrate competitive accuracy, particularly in multi‐view settings and small‐sample datasets.

18 October 2024
Verified
Conference Paper
Open access
HHHongpu Hu
Hongpu Hu
QCQingkun Chen
Qingkun Chen
YWYanli Wan
Yanli Wan
QHQile He
Qile He
XGXing Gao
Xing Gao
JYJianhong Yao
Jianhong Yao
In order to solve the issues/problems existing in the current public health emergency management system in China, such as imperfect cross-sectoral collaborative management model, incomplete emergency response mechanism caused by long-term medical care and prevention fragmentation, difficulty in early screening, discovery, timely warning and continuous dynamic monitoring of major infectious diseases, ineffective information support, and unformed intelligent emergency management model, we integrated emerging information technologies such as big data (BD) and artificial intelligence (AI) into public health emergency management, designed a new intelligent public health emergency management model, and established an early identification and early risk warning model of public health emergencies. The knowledge base and model base of infectious disease prevention and control were built, the intelligent pre-hospital emergency treatment and emergency disposal system were studied, the intelligent public health emergency management platform was developed and pilot application was carried out in order to make up for the shortcomings of traditional emergency management work, realize intelligent public health risk identification, disease prevention and control and emergency handling, and improve public health emergency management service capacity.