Yazar "Alazawi, Esraa Mohammed" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Advanced Generative AI Methods for Academic Text Summarization
    (Institute of Electrical and Electronics Engineers Inc., 2024) Dar, Zaema; Raheel, Muhammad; Bokhari, Usman; Jamil, Akhtar; Alazawi, Esraa Mohammed; Hameed, Alaa Ali
    The exponential growth of scientific literature emphasizes the need for employing advanced techniques for effective text summarization, which can significantly speed up the research process. This study tackles the challenge by advancing scientific text summarization through AI and deep learning methods. We delve into the integration and fine-tuning of cutting-edge models, including LED-Large, Pegasus variants, and BART, aiming to refine the summarization process. Unique combinations, such as SciBERT with LED-Large, were investigated to ensure the capture of critical details frequently missed by traditional methods. This novel approach led to notable improvements in summarization effectiveness. Our findings indicate that models like LED-Large excel in quickly adapting to training data, achieving impressive semantic understanding with fewer training epochs, evidenced by achieving a FRES score of 28.5852 and ROUGE scores, including a ROUGE-l F1-Score of 0.4991. However, while extensively trained models like BART -large and Pegasus displayed strong semantic capabilities, they also pointed to the necessity for refinements in readability and higher-order n-gram overlap in the produced summaries. © 2024 IEEE.
  • Küçük Resim
    Öğe
    Exploring Deep Learning-based Approaches for Brain Tumor Diagnosis from MRI Images
    (Institute of Electrical and Electronics Engineers Inc., 2024) Abdullah, Fasih; Jamil, Akhtar; Alazawi, Esraa Mohammed; Hameed, Alaa Ali
    Brain tumors significantly impair health due to their aggressive growth, necessitating rapid and accurate detection and classification for effective treatment. Traditional methods relying on medical professionals' manual MRI analysis are time-consuming and resource-intensive. This study leverages Artificial Intelligence-based deep learning approaches to streamline and enhance the accuracy of brain tumor classification from MRI images. We evaluated five advanced deep learning models: a custom CNN, DeepTumor-Net, VGG-16, ResNet-50, and Xception. These models were applied to the 'Brain tumors 256×256' dataset, classifying brain tumors into four distinct categories: no tumor, Glioma, Meningioma, and Pituitary Tumors. These models were trained and then fine-tuned, which further refined their performance. The models were evaluated using the standard evaluation metrics, including accuracy, precision, recall, F1-Score, specificity, and Cohen's Kappa. The final results showed that high accuracies can be obtained for MRI classification using these deep learning models. Notably, ResNet-50 and VGG-16 stood out with test accuracies of 92.6 % and 92.1 %, respectively, indicating their significant potential in medical imaging analysis. © 2024 IEEE.