Yazar "Çelik, Sümeyye" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • [ X ]
    Öğe
    Classification of Autism Spectrum Disorder for Adolescents Using Artificial Neural Networks
    (2022) Çelik, Sümeyye; Çeşmeli, Melike Şişeci; Peçe, İhsan; Bozkurt, Özlem Çetinkaya
    Artificial neural networks, is one of the most preferred artificial intelligence techniques in the modeling of complex systems today and the models are based on the working structure of the nerve cells in the human brain. Autism spectrum disorder is a complex neuro-developmental disorder that is congenital or occurs at an early age. Since early diagnosis has a very important role in the treatment, there are many studies on this subject. In this study, a subset of current autism spectrum disorder data obtained from UCI machine learning repository for adolescents has used. In order to test the success of the model, after the necessary preprocesses have performed on the data set, the data has separated into training and test set and classified with the trained network. As a result, 100% accuracy rate in the training set and 96.77% accuracy rate in the test set are achieved. Sensitivity, Specificity and F-measure values obtained in the test set are 0.94, 1.0 and 0.97, respectively and reveals the model success.
  • [ X ]
    Öğe
    Çocuklar İçin Otizm Spektrum Bozukluğunun VeriMadenciliği Yöntemleri ile Analizi
    (2021) Çelik, Sümeyye; Çeşmeli, Melike Şişeci
    Veri madenciliği teknikleri, veriler arasında gizli kalmış olan örüntüleri ortaya çıkarmayı amaçlamaktadır. Bukapsamda, tıp gibi birçok alanda yaygın bir biçimde kullanılmaktadır. Teşhis ve tedavisi oldukça zor ve uzunbir süreçten oluşan otizm spektrum bozukluğu doğuştan gelen ya da yaşamın ilk yıllarında ortaya çıkankarmaşık bir nöro-gelişimsel bozukluktur. Bu çalışmada 292 çocuktan toplanan gerçek ve güncel otizmspektrum bozukluğu verileri kullanılmıştır. Veri seti 20 girdi özniteliği ve 1 çıktı özniteliğine sahiptir. Çıktıözniteliği otizmin bulunup bulunmadığını ifade etmektedir. Çalışma da öncelikle veri seti üzerinde eksikverilerin tamamlanması, kategorik verilerin sayısallaştırılması, normalizasyon gibi veri ön işleme aşamalarıgerçekleştirilmiştir. Devamında ise öznitelikler yapay sinir ağları ve dilsel kuvvetli sinir-bulanık sınıflayıcı ilesınıflandırılmış, k-means ve x-means ile kümelenmiştir. Her bir yöntemin sonuçları değerlendirilmiş veperformanslar karşılaştırılmıştır.
  • [ X ]
    Öğe
    Determination and Classification of Importance of Attributes Used in Diagnosing Pregnant Women's Birth Method
    (2020) Çelik, Sümeyye
    The rapid development of information technologies enables successful results in computer-aided studies. This has led researchers to investigate the usability of technologies such as computer and software supported systems, machine learning, and artificial intelligence in many studies. One of these areas is health. For example, in order not to risk the condition of the mother and baby, in some cases, it is very important to correctly determine the times when the cesarean operation, which is mandatory, is mandatory. In this context, in order to make a faster and more accurate decision, it is very important to determine which attributes and how important the level is in making obligatory cesarean. In this study, to determine whether or not caesarean is necessary in the literature, the importance level of the five criteria taken into consideration has been determined and an attribute determination has been carried out and then a classification has been made. The data set used belongs to 80 pregnant women with 6 attributes. Although the same data set was previously classified with different methods, no study was foundon determining the significance levels of the attributes and using artificial neural networks as a method. For this reason, in this study, the feature was determined using an adaptive nerve-fuzzy classifier and classified using artificial neural networks.When the results are examined, it is concluded that the importance levels of the attributes are different. Although the values such as accuracy, Sensitivity, and Specificity calculated to evaluate the classification results were found to be quite high forthe training set, it was observed that the desired success was not achieved in the test data. While this result is promising, it also reveals the need to increase the learning performed with larger data sets.