Browsing by Author "Ahmed, Meraj"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Enhancing ICU Patient Outcomes Trough Machine Learning and Ensemble Technique
    (Daffodil International University, 2025-05-14) Ahmed, Meraj
    In order to identify the mortality risk and estimate the death rate of ICU patients, machine learning (ML) and ensemble learning approaches are utilized to analyse a variety of patient data and provide an accurate prognosis. The mortality rate of ICU patients nowadays is very high. If we can identify the reason as early as possible then we can start diagnosis as early as possible. First, relevant attributes such as test results, symptoms, and demographic data are taken out of patient files. ML algorithms like logistic regression, decision trees, and support vector machines classify patients into low- and high-risk categories during the mortality risk identification stage. Through model aggregation, ensemble techniques like random forests and gradient boosting improve predictive performance. Regression models such as ridge regression, neural networks, and linear regression evaluate the probability of death within given time frames to predict mortality rates. These estimates are then improved using ensemble learning strategies like stacking or bagging. This abstraction, which improves patient outcomes in the ICU, enables healthcare workers to quickly identify at-risk patients and make well-informed decisions through careful feature engineering, model hyperparameter tuning, and cross-validation. The best accuracy comes with logistic regression (90%) and 2nd highest accuracy comes with both random forest and KNN which is 89%. The results of xgboost and adaboost are 87.07% and 84%
  • Thumbnail Image
    Item
    Modelling and analysis of a triple-band metamaterial absorber for early-stage cervical cancer HeLa cell detection
    (2024-10-24) Anowarul Haque, S.M.; Ahmed, Meraj; Alqahtani, Abdulrahman; Rahman, Mahamudur; Tariqul Islam, Mohammad; Samsuzzaman, Md.
    The paper introduces a unique design and analysis of a terahertz metamaterial absorber (MMA) that can be used for early detection of cervical cancer by employing microwave imaging techniques. Computer Simulation Technology (CST) is used to design and analyze the proposed absorber. The MMA operates in the frequency range of 6–8 THz and can absorb energy in three specific spectral bands: 6.606 THz, 6.824 THz, and 7.426 THz, with absorption peaks of 99.75 %, 99.87 %, and 99.73 % correspondingly. The working principle of the absorber is described using the impedance matching and interference theory. The electric field (E), magnetic field (H), and surface current of the MMA are also examined. Finally, detecting cancerous HeLa cells is also being investigated by analyzing the E-field and H-field using microwave imaging. The suggested biosensor features a high-quality factor of 494.3, a frequency shifts per refractive index of 1.08 THz/RIU, and a figure of merit (FOM) of 42. The suggested MMA-based sensor has numerous advantages and can be utilized for early-stage cervical cancer detection.