Haibin Wang

Haibin Wang


Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

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

Representative Publications

View All Publications
20 January 2020 in IEEE Access
Verified
Journal Article
Open access
YIYounis Ibrahim
Younis Ibrahim
Haibin WangHaibin Wang
Haibin Wang
MBMan Bai
Man Bai
ZLZhi Liu
Zhi Liu
JWJianan Wang
Jianan Wang
ZCZhengming Chen
Zhengming Chen
Convolutional Neural Networks (CNNs) have truly gained attention in object recognition and object classification in particular. When being implemented on Graphics Processing Units (GPUs), deeper networks are more accurate than shallow ones. Residual Networks (ResNets) are one of the deepest CNN architectures used in various fields including safety-critical ones. GPUs have proven to be the major accelerator for CNN models. However, modern GPUs are prone to radiation-induced soft errors, which is a serious issue in safety-compliant systems. In this work, we analyze and propose an approach to address the reliability of ResNet on GPUs. We firstly analyze three popular ResNet models, explicitly, ResNet-50, ResNet-101, and ResNet-152 through NVIDIA’s fault injector, SASSIFI. We perform an in-depth analysis of the model from the perspective of layer and kernel vulnerability. Then, we experimentally show the vulnerability of ResNet models and identify the most vulnerable portions. Finally, we validate our solution, which is a selective-hardening technique, through hardening the worth-hardening kernels to avoid unnecessary overheads. Our strategy is demonstrated to mask up to 93.38% of the injected errors with performance overhead less than 5.35%. Furthermore, the percentage of the errors causing misclassifications can be reduced from 4.2% to 0.104%, thereby significantly improving the model’s reliability.

12 May 2017 in IEEE Transactions on Nuclear Science
Verified
Journal Article
Closed access
YLY.-Q. Li
Y.-Q. Li
Haibin WangHaibin Wang
Haibin Wang
RLR. Liu
R. Liu
LCL. Chen
L. Chen
INI. Nofal
I. Nofal
QWQ. Wu
Q. Wu
A flip-flop circuit hardened against soft errors is presented in this paper. This design is an improved version of Quatro for further enhanced soft-error resilience by integrating the guard-gate technique. The proposed design, as well as reference Quatro and regular flip-flops, was implemented and manufactured in a 65-nm CMOS bulk technology. Experimental characterization results of their alpha and heavy ions soft-error rates verified the superior hardening performance of the proposed design over the other two circuits.

26 February 2021 in IEEE Transactions on Nuclear Science
Verified
Journal Article
Closed access
Haibin WangHaibin Wang
Haibin Wang
YWY.-S. Wang
Y.-S. Wang
JXJ.-H. Xiao
J.-H. Xiao
SWS.-L. Wang
S.-L. Wang
TLT.-J. Liang
T.-J. Liang
Convolutional neural networks (CNNs) are quickly becoming an attractive solution for autonomous vehicles, military weapons, and space exploration. Thanks to their reconfiguration ability, design flexibility, and low power consumption, field-programmable gate arrays (FPGAs) have become a promising candidate for CNN accelerators. However, FPGAs have been proven to be susceptible to radiation-induced single-event upsets (SEUs). One goal of this article is to analyze the impact of quantization on the reliability of CNNs in FPGAs. Therefore, we performed quantization on ZynqNet without affecting its classification accuracy. Meanwhile, we implemented the triple modular redundancy (TMR) version of ZynqNet and we also evaluated the effects of SEUs on these CNNs through both fault injections and neutron exposures. Fault injection results show that TMRed ZynqNet reduces the soft error rate (SER) by 33.59% with a circuit area increase of 111.92% when compared with the standard ZynqNet. The experimental results demonstrate that the quantized ZynqNet reduces the SER by 71.36% with a circuit area reduction of 44.76% when compared with the standard ZynqNet. These results confirm that quantization does contribute to SER reduction of the neural networks. In addition, the operating system on the processing system (PS) side was also found to be highly sensitive to SEUs, and, thus, mitigation techniques should be applied.

29 July 2021 in IET Communications
Verified
Journal Article
Open access
PDF file
Haibin WangHaibin Wang
Haibin Wang
ZYZaid Yemeni
Zaid Yemeni
WIWaleed M. Ismael
Waleed M. Ismael
Ammar HawbaniAmmar Hawbani
Ammar Hawbani
SASaeed H. Alsamhi
Saeed H. Alsamhi
Wireless sensor networks (WSNs) are critically resource‐constrained due to wireless sensor nodes' tiny memory, low processing units, power limitations, and narrow communication bandwidth. The data reduction technique is one of the most widely used techniques to reduce transmitted data over the wireless sensor networks and to minimize the sensor nodes' energy consumption, particularly, the entire network in general. This paper proposes a reliable dual prediction data reduction approach for WSNs. This approach performs data reduction through two phases: the data reduction phase (DRP) and data prediction phase (DPP). The DRP is mainly to decrease the number of transmissions between the sensor node and the sink node, thereby minimizing energy consumption. It also detects faulty data and discards them at the sensor node. The discarded faulty data at the sensor nodes are replaced by estimated values at the sink node to maintain data reliability. DPP runs at the sink node or base station, which works in synchronization with the sensor nodes. This phase is responsible for predicting the non‐transmitted data based on the Kalman filter. The simulation results demonstrate that the proposed approach is efficient and effective in data reduction, data reliability, and energy consumption.

28 May 2021 in Applied Physics A
Verified
Journal Article
Closed access
PDF file
HSHongwen Sun
Hongwen Sun
YSYiwen Song
Yiwen Song
BZBo Zhang
Bo Zhang
YHYunzhe Huan
Yunzhe Huan
CJChenyang Jiang
Chenyang Jiang
Haibin WangHaibin Wang
Haibin Wang

23 August 2021 in IEEE Systems Journal
Verified
Journal Article
Closed access
ZYZaid Yemeni
Zaid Yemeni
Haibin WangHaibin Wang
Haibin Wang
WIWaleed M. Ismael
Waleed M. Ismael
Ammar HawbaniAmmar Hawbani
Ammar Hawbani
ZCZhengming Chen
Zhengming Chen
One of the most challenging problems in wireless sensor networks (WSNs) is detecting and recovering faulty data. Due to resource limitations, WSNs are subject to many failures, including hardware (permanent faults), software, and communication failures. To ensure data reliability, the data collected by WSNs must be clean of faults. This article presents a centralized faulty data detection and recovery approach, which can detect, recover, and recognize different types of faults (offset, gain, stuck-at, out of bound, and random faults). It operates in two phases: Faulty data detection and recovery and fault type identification (FTI). After detecting the fault, the faulty data will be discarded and replaced by an estimated value based on the Kalman filter. FTI provides a unique solution by determining the types of faults and report them to the end-user for an application-specific decision-making process. The effectiveness of the proposed approach is demonstrated through experimental results, with comparison to state-of-the-art techniques of the same application.