Yazar "Ozic M.U." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Classification of dementia with ANN using multiple variable [Çoklu De?işken Kullanarak YSA Ile Demans Siniflandirilmasi]
    (Institute of Electrical and Electronics Engineers Inc., 2015) Ozic M.U.; Ozbay Y.; Ekmekci A.H.
    Dementia is a stage that identifies all of the symptoms that led to the weakening of multiple cognitive functions. It is usually expressed as 'bunama' among people. Dementia is not a disease itself is known as a transition period that defines the initial stages of many diseases. Proportional change in mental function of many variables that influence causes our body causing this stage, textural and volume losses which may occur in the brain, the person may be counted as demographic and clinical variables. Prediction of disease with a combination of variables is one of the popular sizes in recent topics in the literature. In this study received the demented patients from Open Access Series of Imaging Studies (OASIS) database structural magnetic resonance (MR) imaging features and use in combination with the demographic data of the patients was investigated in artificial neural networks classification performance. © 2015 IEEE.
  • Küçük Resim Yok
    Öğe
    Detection of tumor with Otsu-PSO method on brain MR image [Beyin mr görüntüsünde otsu-pso yöntemi ile tümör tespiti]
    (IEEE Computer Society, 2014) Ozic M.U.; Ozbay Y.; Baykan O.K.
    Multiple image thresholding is a popular method used to separate homogeneous subsets of gray level images. To find the optimum threshold in the image in the literature is still a research topic. Many image thresholding method uses the histogram of the image. In this study, the objective function of Otsu method which is a statistical process, Particle Swarm Optimization with an intuitive algorithm (PSO) by maximizing, the optimal threshold values on a medical image were studied to find. The values obtained were tested with a standard test image and brain magnetic resonance (MR) image exposed on the tumor region in segmentation, Otsu-PSO method performance was monitored. © 2014 IEEE.