Huang Guojun

Dr. Huang Guojun


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
22 February 2023 in Journal of Digital Imaging
Verified
Journal Article
Open access
PDF file
JYJianjun Yuan
Jianjun Yuan
FWFujun Wu
Fujun Wu
YLYuxi Li
Yuxi Li
JLJinyi Li
Jinyi Li
HGHuang Guojun
Huang Guojun
QHQuanyong Huang
Quanyong Huang
COVID-19 has claimed millions of lives since its outbreak in December 2019, and the damage continues, so it is urgent to develop new technologies to aid its diagnosis. However, the state-of-the-art deep learning methods often rely on large-scale labeled data, limiting their clinical application in COVID-19 identification. Recently, capsule networks have achieved highly competitive performance for COVID-19 detection, but they require expensive routing computation or traditional matrix multiplication to deal with the capsule dimensional entanglement. A more lightweight capsule network is developed to effectively address these problems, namely DPDH-CapNet, which aims to enhance the technology of automated diagnosis for COVID-19 chest X-ray images. It adopts depthwise convolution (D), point convolution (P), and dilated convolution (D) to construct a new feature extractor, thus successfully capturing the local and global dependencies of COVID-19 pathological features. Simultaneously, it constructs the classification layer by homogeneous (H) vector capsules with an adaptive, non-iterative, and non-routing mechanism. We conduct experiments on two publicly available combined datasets, including normal, pneumonia, and COVID-19 images. With a limited number of samples, the parameters of the proposed model are reduced by 9x compared to the state-of-the-art capsule network. Moreover, our model has faster convergence speed and better generalization, and its accuracy, precision, recall, and F-measure are improved to 97.99%, 98.05%, 98.02%, and 98.03%, respectively. In addition, experimental results demonstrate that, contrary to the transfer learning method, the proposed model does not require pre-training and a large number of training samples.

20 February 2024 in IEEE Network
Verified
Journal Article
Closed access
XHXiaoya Hu
Xiaoya Hu
HGHuang Guojun
Huang Guojun
YNYuqiao Ning
Yuqiao Ning
LWLicheng Wang
Licheng Wang
JSJingwen Suo
Jingwen Suo
JZJuyuan Zhang
Juyuan Zhang
The electronic control unit (ECU) broadcasts and receives data through the on-vehicle bus, enabling the management of the vehicle’s operations and associated functions. Nevertheless, the plaintext broadcast mechanism of the bus exposes the data to potential security threats. Consequently, researchers have explored incorporating technologies like encryption to ensure secure data transmission among various ECUs. However, due to the inherent constrained resources of ECUs and the imperative for low-latency communication, it is challenging to introduce secure mechanisms without causing excessive computational overhead or delays. In this paper, we present a novel lightweight and confidential communication (LiCoom) scheme for on-vehicle ECUs to address this challenge. Our scheme includes a non-interactive key generation and evolution scheme to facilitate key synchronization between different ECUs, followed by the design of a flexible communication scheme for ECUs based on the sensitivity on the transmitted data. Besides the security analysis according to the conceived threat models, we conducted extensive experiments by using various platforms, including laptops and several typical TBoxs. The experimental results show that our proposal imposes on ECUs neither significant computational overhead nor observable delays.

25 July 2021
Verified
Book Chapter
Closed access
PDF file
HWHongrong Wang
Hongrong Wang
HGHuang Guojun
Huang Guojun
XLXincheng Liang
Xincheng Liang

30 December 2025 in Journal of Information Security and Applications
Verified
Journal Article
Closed access
JYJianjun Yuan
Jianjun Yuan
HSHong Sun
Hong Sun
RCRong Cao
Rong Cao
HGHuang Guojun
Huang Guojun

19 February 2025 in Complex & Intelligent Systems
Verified
Journal Article
Open access
PDF file
LLLi Liu
Li Liu
JGJinrui Guo
Jinrui Guo
ZYZiqi Yin
Ziqi Yin
RCRui Chen
Rui Chen
HGHuang Guojun
Huang Guojun
Class imbalance is a prevalent issue in practical applications, which poses significant challenges for classifiers. The large margin distribution machine (LDM) introduces the margin distribution of samples to replace the traditional minimum margin, resulting in extensively enhanced classification performance. However, the hyperplane of LDM tends to be skewed toward the minority class, due to the optimization property for margin means. Moreover, the absence of non-deterministic options and measurement of the confidence level of samples further restricts the capability to manage uncertainty in imbalanced classification tasks. To solve these problems, we propose a novel three-way distance-based fuzzy large margin distribution machine (3W-DBFLDM). Specifically, we introduce a distance-based factor to mitigate the impact of sample size imbalance on classification results by increasing the distance weights of the minority class. Additionally, three-way decision model is introduced to deal with uncertainty, and the model’s robustness is further enhanced by utilizing the fuzzy membership degree that reflects the importance level of each input point. Comparative experiments conducted on UCI datasets demonstrate that the 3W-DBFLDM model surpasses other models in classification accuracy, stability, and robustness. Furthermore, the cost comparison experiment validate that the 3W-DBFLDM model reduces the overall decision cost.

1 March 2022 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
HGHuang Guojun
Huang Guojun
HWHongrong Wang
Hongrong Wang
XLXincheng Liang
Xincheng Liang
The conventional internal combustion mini-tiller is a vitally agricultural tool with multiple functions, meanwhile the strong vibration may impose damaging effect on the user’s health. Hence, it is inevitable to replace the internal combustion by the electric motor. Although the performance of the electric mini-tiller has been enhanced greatly, the remaining vibration is still distinct and some diseases can be occurred incontrovertibly. The rack is one of the most significant components to connect the different parts for the electric mini-tiller, and the index may be improved through redesigning the structure of rack. In this study the rack has been analysed under different structure by Ansys workbench software, and simulations show that the vibration acceleration from the rack to the human body decreases greatly after the structure had been redesigned, which signifies the handling stability and riding comfort of mini-tiller can be promoted without the extra cost. Although the total vibration acceleration is reduced a lot, the vibration of cutting roller is more distinct than that of before. Therefore, the cutting configuration is needed to be optimized, and vibration transmitting path of cutting roller should be intervened as well in the future, enhancing the handling comfort and energy conservation of electric mini-tiller.