Syed Waseem Abbas Sherazi

Syed Waseem Abbas Sherazi

Auto-generated profile, based on publicly available information

Syed Waseem Abbas Sherazi

Department of Computer Science, Chungbuk National University, South Korea

Research Focus & Metrics

Academic Career Length

8Years (2019-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.


10 July 2019
Verified
Book Chapter
Closed access
PDF file
BJBilguun Jargalsaikhan
Bilguun Jargalsaikhan
MSMuhammad Saqlain
Muhammad Saqlain
SASherazi Syed Waseem Abbas
Sherazi Syed Waseem Abbas
MJMoon Hyun Jae
Moon Hyun Jae
IKIn Uk Kang
In Uk Kang
JLJong Yun Lee
Jong Yun Lee

17 June 2023
Verified
Conference Paper
Open access
HZHuilin Zheng
Huilin Zheng
SSSyed Waseem Abbas Sherazi
Syed Waseem Abbas Sherazi
SASaba Arif
Saba Arif
MLMyung Jin Lee
Myung Jin Lee
JLJong Yun Lee
Jong Yun Lee
The heart, as the main organ of our human body, plays an important role in pumping blood through our body. Early prevention and prediction of cardiovascular disease (CVD) can save more lives, especially for ordinary people. Hence, this study proposes a voting ensemble-based prediction model for the risk of CVD in ordinary people. We first integrate 2 years of data from the Korea National Health and Nutrition Examination Survey (KNHANES) and then extract the experimental data. Thereafter, the extracted data is preprocessed with missing value imputation and data normalization. A filter-based feature selection approach is also applied to select the efficient attributes for the experiment, then split the data into training (80%) data and test (20%) data. Thenceforth, we use two kinds of hybrid data sampling techniques such as synthetic minority oversampling techniques (SMOTE) plus Tomek Links (SMOTETomek) and SMOTE plus Edited Nearest Neighbors (SMOTEENN) to solve the imbalance issue in the training data. Next, the voting ensemble-based prediction model is designed based on different machine learning algorithms such as logistic regression, support vector machine, and AdaBoost on the balanced training data with selected features and complete features. Lastly, the proposed model is evaluated on the test data and compared with other popularly used machine learning-based models. In the experimental results, the proposed voting ensemble-based prediction model with the SMOTEENN technique on selected features by using the filter-based feature selection approach achieved the best performance with the accuracy of 0.8102, recall 0.8102, g-mean 0.8102, and AUC 0.8102, respectively for the risk of CVD in ordinary people and outperformed other machine learning-based prediction models.