Yazar "Şen, Baha" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim Yok
    Öğe
    Assessing the importance of features for detection of hard exudates in retinal images
    (2017) Akyol, Kemal; Şen, Baha; Bayır, Şafak; Çakmak, Hasan Basri
    Diabetes disrupts the operation of the eye and leads to vision loss, affecting particularly the nerve layer and capillary vessels in this layer by changes in the blood vessels of the retina. Suddenly loss and blurred vision problems occur in the image, depending on the phase of the disease, called diabetic retinopathy. Hard exudates are one of the primary signs of diabetic retinopathy. Automatic recognition of hard exudates in retinal images can contribute to detection of the disease. We present an automatic screening system for the detection of hard exudates. This system consists of two main steps. Firstly, the features were extracted from patch images consisting of hard exudate and normal regions using the DAISY algorithm based on the histogram of oriented gradients. After, we utilized the recursive feature elimination (RFE) method, using logistic regression (LR) and support vector classi er (SVC) estimators on the raw dataset. Therefore, we obtained two datasets containing the most important features. The number of important features in each dataset created with LR and SVC was 126 and 259, respectively. Afterward, we observed different classi er algorithms\\' performances by using 5-fold cross validation on these important features\\' dataset and it was observed that the random forest (RF) classi er is the best classi er. Secondly, we obtained important features from the feature vector that corresponds with the region of interest in accordance with the keypoint information in a new retinal fundus image. Then we performed detection of hard exudate regions on the retinal fundus image by using the RF classi er.
  • Küçük Resim Yok
    Öğe
    Cropped quad-tree based solid object colouring with cuda
    (2013) Çavuşoğlu, Abdullah; Şen, Baha; Özcan, Caner; Görgünoglu, Salih
    In this study, surfaces of solid objects are coloured with Cropped Quad-Tree method utilizing GPU computing optimization. There are numerous methods used in solid object colouring. When the studies carried out in different fields are taken into consideration, it is seen that quad-tree method displays a prominent position in terms of speed and performance. Cropped quad-tree is obtained as a result of the developments seen with the frequent use of this method in the field of computer sciences. Two different versions of algorithm which operate recursively on CPU and at the same time which use GPU computing optimization are used in this study. Besides, OpenGL is used for graphics drawing process. Within the setting of the study, results are obtained via CPU and GPU's, at first using Quad-Tree method and then Cropped Quad-Tree method. It is observed that GPU computing is obviously faster than CPU computing and Cropped Quad-Tree method produces rapid results compared to Quad-Tree method as a result of performance. GPU computing method boosted approximately performance by up to 20 times compared to only CPU usage; furthermore, cropped quad-tree method boosted approximately performance of algorithm by up to 25 times on average dependent on screen and object size.
  • Küçük Resim Yok
    Öğe
    Importance of attribute selection for parkinson disease
    (2020) Akyol, Kemal; Bayir, Şafak; Şen, Baha
    Parkinson disease is a neurological disorder occurring at older ages. It is one of the most painful, dangerous and untreated diseases. In this study, a new application based on assessing the importance of attributes using the ranking techniques was carried out for diagnosis of this disease. The effects of the attributes on the Parkinson disease are determined by utilizing Stability Selection method. The selected attributes dataset and all attributes dataset have been sent as input data to the Random Forest and Logistic Regression algorithms in order to investigate the best model which is to be effective in the diagnosis of this disease. This study including the model which presented the best performance might be a powerful tool for effective diagnosis of this disease.
  • Küçük Resim Yok
    Öğe
    Population based procedural artificial city generation using beta distribution
    (2012) Şen, Baha; Çavuşoğlu, Abdullah; Göktaş, Haldun; Atasoy, Nesrın Aydın
    Artificial city generation on computer graphics platforms introduce severalproblems from the point of view of the application programmer. Especially in the caseswhere the product is aimed for virtual reality applications, this becomes more importantsince the target is achieving city layouts akin to the real cities. The same is valid for thecivil engineers where the layouts of the blocks/cities are determined in advance of theconstruction. An important parameter for artificial cities is the determination of thepopulation distribution over the cities which in turn affect the overall appearance of thecity or the blocks forming it. In this study, the Beta distribution has been used todisperse artificial city populations over the city blocks to generate cities that do not lookto regular. The system uses HTF based maps and the produced 3D cities are quiterealistic when compared to the similar products.