TY  - JOUR
TI  - Determination of Covid-19 Possible Cases by Using Deep Learning Techniques
AB  - A large number of cases have been identified in the world with the emergence of COVID-19and the rapid spread of the virus. Thousands of people have died due to COVID-19. This veryspreading virus may result in serious consequnces including pneumonia, kidney failure acuterespiratory infection. It can even cause death in severe cases. Therefore, early diagnosis isvital. Due to the limited number of COVID-19 test kits, one of the first diagnostic techniquesin suspected COVID-19 patients is to have Thorax Computed Tomography (CT) applied toindividuals with suspected COVID-19 cases when it is not possible to administer these testkits. In this study, it was aimed to analyze the CT images automatically and to direct probableCOVID-19 cases to PCR test quickly in order to make quick controls and ease the burden ofhealthcare workers. ResNet-50 and Alexnet deep learning techniques were used in theextraction of deep features. Their performance was measured using Support Vector Machines(SVM), Nearest neighbor algorithm (KNN), Linear Discrimination Analysis (LDA), Decisiontrees, Random forest (RF) and Naive Bayes methods as the methods of classification. Thebest results were obtained with ResNet-50 and SVM classification methods. The success ratewas found as 95.18%.
AU  - OĞUZ, Çinare
AU  - Yağanoğlu, Mete
DO  - 10.16984/saufenbilder.774435
PY  - 2021
JO  - Sakarya Üniversitesi Fen Bilimleri Enstitüsü Dergisi
VL  - 25
IS  - 1
SN  - 1301-4048
SP  - 1
EP  - 11
DB  - TRDizin
UR  - http://search/yayin/detay/420204
ER  -