Huilin Zheng

Mr. Huilin Zheng

Ph.D Candidate, Chungbuk National University, Korea
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
26 July 2021 in IEEE Access
Verified
Journal Article
Open access
HZHuilin Zheng
Huilin Zheng
SSSyed Waseem Abbas Sherazi
Syed Waseem Abbas Sherazi
JLJong Yun Lee
Jong Yun Lee
The major adverse cardiovascular events (MACE) often occur with high morbidity and mortality globally. It is very important to predict the MACE occurrences accurately in patients with acute coronary syndrome (ACS). Therefore, this paper proposes a stacking ensemble model for the prediction of MACE occurrences in patients with ACS at early stage. Our research contents are summarized as follows. First, we use the Korea Acute Myocardial Infarction Registry National Institutes of Health (KAMIR-NIH) dataset, and our experimental data are extracted from the raw data and preprocessed. Second, we apply three data sampling approaches, such as borderline synthetic minority oversampling technique (Borderline-SMOTE1), cluster centroids undersampling, and synthetic minority oversampling techniques (SMOTE) plus Tomek Links (SMOTETomek) hybrid technique, to solve the class imbalance problem. Third, to develop a stacking ensemble prediction model for the occurrences of MACE, we apply seven widely used machine learning algorithms, such as logistic regression (LR), support vector machine (SVM), K-Nearest Neighbors (KNN), decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), and adaptive boosting (AdaBoost), as base learners. Fourth, the performance of the proposed stacking ensemble model is compared with the seven base learners using the three data sampling techniques. In the result, the proposed stacking ensemble model with the SMOTETomek shows the best performance with accuracy of 0.9862, precision 0.9976, recall 0.975, F1-score 0.9862, g-mean 0.9863, and AUC 0.9863 and provided a better solution for imbalanced dataset. Consequently, our finding is that the proposed stacking ensemble model with the SMOTETomek outperforms the base learners and improves the accuracy of diagnosis and prediction of the MACE occurrences in patients with ACS at early stage.

19 October 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
HZHuilin Zheng
Huilin Zheng
SSSyed Waseem Abbas Sherazi
Syed Waseem Abbas Sherazi
SSSang Hyeok Son
Sang Hyeok Son
JLJong Yun Lee
Jong Yun Lee
Wafer maps provide engineers with important information about the root causes of failures during the semiconductor manufacturing process. Through the efficient recognition of the wafer map failure pattern type, the semiconductor manufacturing process and its product performance can be improved, as well as reducing the product cost. Therefore, this paper proposes an accurate model for the automatic recognition of wafer map failure types using a deep learning-based convolutional neural network (DCNN). For this experiment, we use WM811K, which is an open-source real-time wafer map dataset containing wafer map images of nine failure classes. Our research contents can be briefly summarized as follows. First, we use random sampling to extract 500 images from each class of the original image dataset. Then we propose a deep convolutional neural network model to generate a multi-class classification model. Lastly, we evaluate the performance of the proposed prediction model and compare it with three other popular machine learning-based models—logistic regression, random forest, and gradient boosted decision trees—and several well-known deep learning models—VGGNet, ResNet, and EfficientNet. Consequently, the comprehensive analysis showed that the performance of the proposed DCNN model outperformed those of other popular machine learning and deep learning-based prediction models.

25 January 2023 in Sensors
Verified
Journal Article
Open access
PDF file
SSSyed Waseem Abbas Sherazi
Syed Waseem Abbas Sherazi
HZHuilin Zheng
Huilin Zheng
JLJong Yun Lee
Jong Yun Lee
Nowadays, machine learning (ML) is a revolutionary and cutting-edge technology widely used in the medical domain and health informatics in the diagnosis and prognosis of cardiovascular diseases especially. Therefore, we propose a ML-based soft-voting ensemble classifier (SVEC) for the predictive modeling of acute coronary syndrome (ACS) outcomes such as STEMI and NSTEMI, discharge reasons for the patients admitted in the hospitals, and death types for the affected patients during the hospital stay. We used the Korea Acute Myocardial Infarction Registry (KAMIR-NIH) dataset, which has 13,104 patients’ data containing 551 features. After data extraction and preprocessing, we used the 125 useful features and applied the SMOTETomek hybrid sampling technique to oversample the data imbalance of minority classes. Our proposed SVEC applied three ML algorithms, such as random forest, extra tree, and the gradient-boosting machine for predictive modeling of our target variables, and compared with the performances of all base classifiers. The experiments showed that the SVEC outperformed other ML-based predictive models in accuracy (99.0733%), precision (99.0742%), recall (99.0734%), F1-score (99.9719%), and the area under the ROC curve (AUC) (99.9702%). Overall, the performance of the SVEC was better than other applied models, but the AUC was slightly lower than the extra tree classifier for the predictive modeling of ACS outcomes. The proposed predictive model outperformed other ML-based models; hence it can be used practically in hospitals for the diagnosis and prediction of heart problems so that timely detection of proper treatments can be chosen, and the occurrence of disease predicted more accurately.

15 August 2016 in Journal of Materials Chemistry C
Verified
Journal Article
Closed access
PDF file
DDDakang Ding
Dakang Ding
WCWeiye Chen
Weiye Chen
JWJiuxing Wang
Jiuxing Wang
MQMeng Qiu
Meng Qiu
HZHuilin Zheng
Huilin Zheng
RYRenqiang Yang
Renqiang Yang
A novel monomer alkoxybiphenyl-substituted benzodithiophene (BDTBP) was synthesized and used as the donor to construct a donor–acceptor copolymer PBDTBP–DTffBT with 4,7-di(4-(2-ethylhexyl)-2-thienyl)-5,6-difluoro-2,1,3-benzothiadiazole (DTffBT) as the acceptor unit. Compared with the corresponding polymer PBDTP–DTffBT based on alkoxyphenyl-substituted BDT, PBDTBP–DTffBT exhibits a red-shifted UV-vis absorption spectra due to its extended π-conjugation structure. The maximum power conversion efficiency (PCE) of PBDTBP–DTffBT based polymer solar cells (PSCs) is 6.70% with Voc = 0.85 V, Jsc = 12.72 mA cm−2 and FF = 62.14%, and the hole mobility is 3.45 × 10−4 cm2 V−1 s−1 while the maximum PCE of PSCs based on PBDTP–DTffBT is only 4.91% and the hole mobility is 1.70 × 10−5 cm2 V−1 s−1. These findings demonstrate that BDTBP unit is a promising building block for constructing a copolymer with high hole mobility, and extending the π-conjugation length on the alkoxyphenyl-substituted BDT is helpful to improve the photovoltaic properties.

1 November 2018
Verified
Conference Paper
Closed access
HZHuilin Zheng
Huilin Zheng
HPHyun Woo Park
Hyun Woo Park
DLDingkun Li
Dingkun Li
KPKwang Ho Park
Kwang Ho Park
KRKeun Ho Ryu
Keun Ho Ryu
Recent years, the diabetes mellitus is an important public health problem and has been the top 10 leading causes of death in lower-middle-income countries and upper-middle-income countries in the world. In this study, we tried to use a hybrid feature selection approach to find proper and optimal feature subsets to classify and predict the diabetes mellitus patients in Korea based on the data from Korea National Health and Nutrient Examination Survey (KNHANES). We used the information gain feature selection approach as the filter phase and used the support vector machine with sequential search method as the wrapper phase. To validate the efficiency of the proposed approach, we also compared our proposed approach with several popular feature selection approaches. The results showed that our proposed approach can significantly improve the classification accuracy and outperformed other feature selection approaches.