Ang Hu

Ang Hu

Auto-generated profile, based on publicly available information

Ang Hu

School of Integrated Circuits, Huazhong University of Science and Technology, Wuhan, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
16 August 2022 in IEEE Transactions on Circuits and Systems I: Regular Papers
Verified
Journal Article
Closed access
JLJiahao Lu
Jiahao Lu
DLDong-Sheng Liu
Dong-Sheng Liu
XCXuan Cheng
Xuan Cheng
LWLai Wei
Lai Wei
AHAng Hu
Ang Hu
XZXuecheng Zou
Xuecheng Zou
Convolution neural network (CNN) with pruning techniques has shown remarkable prospects in electrocardiogram (ECG) classification. However, efficiently deploying the existing pruned neural network to wearable devices for ECG classification is a great challenge due to the limited hardware resource and randomly distributed sparse weights. To address this issue, an efficient unstructured sparse CNN accelerator is proposed in this paper. A tile-first dataflow with compressed data storage format is presented to skip zero weight multiplications and increase the computing efficiency during inference of small-scale model with large sparsity. The two-level weight index matching structure in the dataflow exploits shifting operation to select valid data pairs and maintain the fully-pipelined calculation process. A configurable processing element (PE) array with 32-bit instruction control is proposed to increase the flexibility of the accelerator. Verified in FPGA and post-synthesis simulations in SMIC 40nm process, the proposed sparse CNN accelerator consumes $3.93~\mu $ J/classification at 2MHz clock frequency and it achieves an averaged ECG classification accuracy of 98.99%. A computing efficiency of 118.75% is realized which is improved by 48% compared to the dense baseline. In brief, the proposed efficient CNN accelerator is especially suitable for wearable ECG classification device.

15 April 2022 in Microelectronics Journal
Verified
Journal Article
Closed access
HLHao Li
Hao Li
AHAng Hu
Ang Hu
ZNZheng Nie
Zheng Nie
DLDong-Sheng Liu
Dong-Sheng Liu
GNGuangda Niu
Guangda Niu
JTJiang Tang
Jiang Tang

25 August 2022 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
ALAobo Li
Aobo Li
DLDong-Sheng Liu
Dong-Sheng Liu
CZCong Zhang
Cong Zhang
XLXiang Li
Xiang Li
SYShuo Yang
Shuo Yang
NTNi Tianming
Ni Tianming
Progress of quantum computing technology seriously threaten the industrial information security based on traditional public-key cryptosystem. Thus, the cryptosystem with anti-quantum attack characteristics is gradually becoming a significant research in the security field. In this article, a flexible and high-performance secure coprocessor is designed for security in industrial processes, which can execute the post-quantum cryptographic algorithm Saber efficiently. Custom instruction set and arithmetic accelerators are proposed to effectively optimize the flexibility of system architecture, and improve the performance of calculation. The hardware implementation results show that the maximum operating frequency of the coprocessor can reach 345 MHz. Compared with related state-of-the-art works, it achieves the highest operating frequency on the same Xilinx UltraScale+ FPGA platform, performing the encryption and decryption operations within 13.5 and 15.4 μ s, respectively. Meanwhile, this article achieves 1.7/3.1/5.9× area-time product improvements in look-up table flip-flop block memory storage with good flexibility.

12 February 2024 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
YSYanwen Su
Yanwen Su
HLHao Li
Hao Li
ZJZhijie Jian
Zhijie Jian
KLKaiyue Li
Kaiyue Li
AHAng Hu
Ang Hu
DLDong-Sheng Liu
Dong-Sheng Liu
This brief presents an 8×8 event-based vision readout integrated circuit (ROIC) for the InGaAs infrared detector. Traditional event-based vision sensors (EVS) use predefined threshold voltage to generate output events, which could fluctuate according to the corner or temperature and increase the error event rates. In order to solve this problem, an adaptive threshold voltage generation circuit is proposed. By using this adaptive circuit, the simulated threshold voltage VTH variation is decreased from 60-200 mV to 128-132 mV, and the error event rate is optimized from 5%-25% to 2.5%-5% in different corners and temperature conditions. The sensor ROIC is implemented in 40 nm CMOS process and the pixel pitch is 40 μm. The power consumption is 16 mW with an area of 1.53 mm2. The measured events latency is 2 μs and the response frequency is 5 kHz.

31 March 2024 in Microelectronics Journal
Verified
Journal Article
Closed access
CZChengcheng Zhang
Chengcheng Zhang
AHAng Hu
Ang Hu
DLDongsheng Liu
Dongsheng Liu
SMShuo Ma
Shuo Ma
HLHao Li
Hao Li
ZJZirui Jin
Zirui Jin

13 October 2023 in Microelectronics Journal
Verified
Journal Article
Closed access
CZChengcheng Zhang
Chengcheng Zhang
AHAng Hu
Ang Hu
DLDongsheng Liu
Dongsheng Liu
SMShuo Ma
Shuo Ma
HLHao Li
Hao Li
WYWentao Yang
Wentao Yang