Yazar "Firat H." seçeneğine göre listele

Listeleniyor 1 - 2 / 2
  • Küçük Resim Yok
    Öğe
    Classification of hyperspectral images using 3D CNN based ResNet50
    (Institute of Electrical and Electronics Engineers Inc., 2021) Firat H.; Hanbay D.
    Hyperspectral images are images containing rich spectral and spatial information widely used in remote sensing applications. The development of deep learning techniques has had a significant impact on the classification of hyperspectral images. Different Convolutional Neural Network architectures have been used in many hyperspectral image analysis studies. However, the high dimensions of the hyperspectral images increased the computational complexity. For this reason, dimensionality reduction has been used in the preprocessing stage in many studies. Another difficulty encountered in hyperspectral image classification studies is the need to consider both spectral and spatial features. When deep spatial and spectral features are to be extracted, problems such as loss of gradient properties and degradation due to increased depth arise. In this study, the 3D convolutional neural network (CNN) based ResNet50 method is proposed to solve these problems encountered in hyperspectral studies and to extract sufficient spatial spectral properties from the network. Principal Component Analysis (PCA) was used to reduce spectral band excess. The proposed method has been applied to Pavia University and Salinas data sets. Overall accuracy, average accuracy and kappa values were used to measure the performance of the method. Calculated overall accuracy, average accuracy, and kappa values are 99.99% for the Pavia University data set, and while the overall accuracy and kappa values were 99.99% for the Salinas data set, the average accuracy value was 99.98%. © 2021 IEEE.
  • Küçük Resim Yok
    Öğe
    Prevalence of sleep disorders in the Turkish adult population epidemiology of sleep study
    (Springer, 2015) Demir A.U.; Ardic S.; Firat H.; Karadeniz D.; Aksu M.; Ucar Z.Z.; Sevim S.
    Sleep disorders constitute an important public health problem. Prevalence of sleep disorders in Turkish adult population was investigated in a nationwide representative sample of 5021 Turkish adults (2598 women and 2423 men, response rate: 91%) by an interviewer-administered questionnaire. Insomnia was defined by the DSM-IV criteria, habitual snoring and risk for sleep-related breathing disorders (SDB) by the Berlin questionnaire, excessive daytime sleepiness (EDS) by the Epworth sleepiness scale score, and restless legs syndrome (RLS) by the complaints according to the International Restless Legs Syndrome Study Group criteria. Mean age of the participants was 40.7 ± 15.1 (range 18 to 90) years. Prevalence rates (men/women) were insomnia 15.3% (10.5%/20.2%; P < 0.001), high probability of SDB 13.7% (11.1%/20.2%; P < 0.001), EDS 5.4% (5.0%/5.7%; P: 0.09), RLS 5.2% (3.0%/7.3%; P < 0.001). Aging and female gender were associated with higher prevalence of sleep disorders except for habitual snoring. Prevalence rates of the sleep disorders among Turkish adults based on the widely used questionnaires were close to the lower end of the previous estimates reported from different parts of the world. These findings would help for the assessment of the health burden of sleep disorders and addressing the risk groups for planning and implementation of health care. Sleep and Biological Rhythms © 2015 Japanese Society of Sleep Research.