SASamia M. Abd-Alhalem

Samia M. Abd-Alhalem

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Samia M. Abd-Alhalem has a total of 11 co-authors. Here are the top co-authors by number of shared publications:

  • Abeer D. Algarni

    Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia

    1 shared publication
  • Ali E. Takieldeen

    IEEE Senior Member, Faculty of Artificial Intelligence, Delta University for Science and Technology

    1 shared publication
  • Esraa Mahmoud

    Faculty of Artificial Intelligence, Delta University for Science and Technology, Gamasa, 35712, Egypt

    1 shared publication
  • Fathi E. Abd El-Samie

    Department of Information Technology, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia

    1 shared publication
  • Fatimah Algarni

    Ministry of Education, Riyadh, Saudi Arabia

    1 shared publication
  • Hanaa Salem Marie

    Faculty of Artificial Intelligence, Delta University for Science and Technology, Gamasa, Egypt

    1 shared publication

Latest Publications

  • Open Access

    Exploiting fuzzy weights in CNN model-based taxonomic classification of 500-bp sequence bacterial dataset

    by Abeer D. Algarni, Fathi E. Abd El-Samie, Naglaa F. Soliman, Heba M. Emara, Fatimah Algarni, Samia M. Abd-Alhalem, Hanaa Salem Marie

    Taxonomic classification plays a crucial role in understanding the diversity and evolutionary relationships among bacteria. Accurately classifying bacterial DNA sequences based on a limited 500-bp segment remains challenging. This paper presents an improved Fuzzy-weighted Convolutional Neural Network (F-CNN) for taxonomic classification of bacterial DNA sequences, specifically focusing on the 500-bp segments. The proposed model aims to overcome the limitations of traditional classification methods by leveraging the power of deep learning and fuzzy logic processing. The improved fuzzy deep learning model is proposed to handle the problem of classifying samples with similar probabilities in the classification layer. It incorporates a feature selection stage using various techniques and a fuzzy weighting system to handle the uncertainty associated with similar classes in the classification layer and optimize parameters using fuzzy weights. The experimental results on the Ribosomal Database Project Release 11 (RDP 11) sequences dataset show the superiority of the proposed model, especially at the 500-bp region. Experimental results on the RDP 11 dataset, which includes over 1.4 million bacterial gene sequences, demonstrate the superior performance of the proposed model, achieving a classification accuracy up to 84.03% at the genus level for 500-bp segments and demonstrating high generalization when applied to longer sequences. This paper has significant implications for various fields, including microbiology, epidemiology, and environmental science, where accurate classification of bacteria is crucial for understanding their roles in different ecosystems and disease outbreaks.


  • Open Access

    An implementation of a Smart System based on Deep Learning for Pneumonia Infection Detection

    by Hesham A. Ali, Rana Osama, Raneem Mohamed, Esraa Mahmoud, Samia M. Abd-Alhalem, Ali E. Takieldeen

    Pneumonia is a serious respiratory infection that can lead to severe health complications if not detected and treated early. In this paper, we propose a smart system based on deep learning for pneumonia infection detection. The system will be deployed as a web app that can receive chest x-ray images uploaded by users and return a prediction of whether the x-ray injured or no. Through the proposed smart Web application, anybody and anywhere may now access the model. There was no need for specialized knowledge, the system uses a convolutional neural network (CNN) to analyze chest X-ray images and identify signs of pneumonia infection. The CNN is trained on a large dataset of chest X-ray images labeled as either normal or infected with pneumonia. The system can be integrated into existing healthcare systems to provide early detection and timely treatment of pneumonia infections, thereby improving patient outcomes and reducing healthcare costs.