Yazar "Alnussairi, Muqdad Hanoon Dawood" seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim
    Öğe
    Malaria parasite detection using deep learning algorithms
    (Altınbaş Üniversitesi / Lisansüstü Eğitim Enstitüsü, 2023) Alnussairi, Muqdad Hanoon Dawood; Ibrahim, Abdullahi Abdu
    The most astounding achievements in domains as disparate as robotics, NLP, image recognition, AI, and so on are the result of deep learning, an automated learning technique. one of the main benefits of deep learning is that the model only needs to be trained and taught once, in contrast to machine learning. Training and teaching in machine learning must be redone whenever the input changes. Red blood cell (RBC) examination under a microscope is the standard method for detecting malaria, which affects millions of people worldwide. Manual microscopic malaria diagnosis is difficult due to time restrictions and a lack of expertise. Using a data-driven approach to education and training, we are able to assess whether or not a person in a photograph is suffering from malaria. This proposed system aids medical students, physicians, and others in diagnosing malaria. we are working on a way for Giemsa-stained smears to detect parasites in the blood, such as those that cause malaria. When the sample size is small, deep learning algorithms perform poorly. Transfer learning means getting visual features from large general datasets and using limited problemspecific datasets to solve classification problems that are specific to that problem. in this study, we use transfer learning to find and sort malaria parasites. we employ three commonly used pre-trained CNN models: VGG19, ResNet50, and MobileNetV2. the NIH Malaria Dataset is used in all experimental evaluations, and the algorithm is found to be 100% accurate in detecting malaria.
  • [ X ]
    Öğe
    Malaria parasite detection using deep learning algorithms based on (CNNs) technique
    (Elsevier Ltd, 2022) Alnussairi, Muqdad Hanoon Dawood; İbrahim, Abdullahi Abdu
    Malaria is a life-threatening disease caused by female anopheles mosquito bites that are prevalent in many regions of the world. We introduce a deep convolutional neural network (CNN) to improve malaria diagnosis accuracy using patches segmented from microscopic images of red blood cell smears. We design the automatic parasite detection in blood from Giemsa-stained smears using three CNN pre-trained models such as VGG19, ResNet50, and MobileNetV2. As the CNNs are poorly performing for small datasets, we introduce the transfer learning technique. Transfer learning involves acquiring visual features from large general datasets and resolving issues using small datasets. We use a transfer learning approach to detect and classify malaria parasites with three CNN pre-trained models. We evaluated proposed CNN models experimentally using the National Institute of Health (NIH) Malaria Dataset. Our proposed model achieves an accuracy of almost 100%.