IIUC Journal of Science and Engineering

Permanent URI for this communityhttp://dspace.iiuc.ac.bd/handle/123456789/8468

Browse

Filters

2023 - 20242

Settings

Subject: search.filters.subject.COVID-19

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Covid-19 detection using dominant SMOTE in imbalance classification
    (Center for Research and Publication (CRP), 2024-12) Islam, Saiful
    Global healthcare systems have faced difficulties since the start of the COVID-19 epidemic. For overburdened hospitals, identifying positive patients is a simple and effective fix. The disproportionate distribution of classes poses a significant challenge in identifying the positive case of COVID-19, leading to biased prediction outcomes favoring dominant classes. Consequently, classifiers struggle to learn from imbalanced datasets, resulting in reduced performance. Various techniques, such as oversampling, undersampling, and hybrid sampling, have been proposed to mitigate this issue. However, the Synthetic Minority Oversampling Technique (SMOTE) remains a commonly utilized resampling method despite its limitations, including class mixture. To address these shortcomings, I introduce Dominant SMOTE, a modified version of SMOTE. The proposed method comprises of developing a dominant sample selection approach based on numerical attribute values from the minority class, and selecting the nearest neighbors from the majority class for each minority class sample based on dominance values to achieve balanced dataset. The proposed method is compared with traditional SMOTE and Out-Layer SMOTE, evaluating accuracy, precision, recall, and F1-score on two benchmark datasets. The results indicate that the proposed model outperforms than both the traditional SMOTE and Out-Layer SMOTE.
  • No Thumbnail Available
    Item
    Investigation of some heterocyclic derivatives as sars-cov-2 main protease inhibitors: An in-silico approach
    (CRP, International Islamic University Chittagong, 2023-12) Kabir, Emranul
    A respiratory disease termed COVID-19 is brought on by one of the most potent ribonucleic acids (RNA) viruses. It has captivated the interest of scientists, virologists, and medical experts to create mechanisms to fight the disease. Computational research is needed on COVID-19 proteins and drugs due to their health risks. Till now, the only appropriate therapy was a vaccination. As a consequence, in the current study, a few heterocyclic derivatives with isoxazole, as well as pyrazole functionalities, are selected for docking studies with the primary proteases of SARS-CoV-2 (PDB ID: 7BQY and 6LU7). Compared to well-known antibiotics like azithromycin, remdesivir, and hydroxychloroquine, heterocyclic analogs 2-7 have significant docking scores (-8.0 to -6.2 kcal/mol). This study clearly showed that the pyrazole analogue 7 exhibited the most binding affinity with both 7BQY and 6LU7 (-8.0 and -7.1 respectively) proteins as well as the interactions between the residues of amino acid in proteins and drugs in the docked conformers to explain such high scores incorporating B3LYP and 6-31G+ DFT method.