Yazar "Demir, Ibrahim" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Comparative Analysis of Neural Networks in the Diagnosis of Emerging Diseases based on COVID-19
    (Prof. Dr. Mehmet Zeki SARIKAYA, 2021) Kirişci, Murat; Demir, Ibrahim; Şimşek, Necip
    Dermatological diseases are frequently encountered in children and adults for various reasons. There are many factors that cause the onset of these diseases and different symptoms are generally seen in each age group. Artificial Neural Networks can provide expert level accuracy in the diagnosis of dermatological findings of patients with COVID-19 disease. Therefore, the use of neural network classification methods can give the best estimation method in dermatology. In this study, the prediction of cutaneous diseases caused by COVID-19 was analyzed by Scaled Conjugate Gradient, Levenberg Marquardt, Bayesian Regularization neural networks. At some points, Bayesian Regularization and Levenberg Marquardt were almost equally effective, but Bayesian Regularization performed better than Levenberg Marquard and called Conjugate Gradient in performance. It is seen that neural network model predictions achieve the highest ac-curacy. For this reason, Artificial Neural Networks are able to classify these diseases as accurately as human experts in an experimental setting. © 2021, Prof. Dr. Mehmet Zeki SARIKAYA. All rights reserved.
  • Küçük Resim
    Öğe
    Fermatean fuzzy ELECTRE multi-criteria group decision-making and most suitable biomedical material selection
    (Elsevier B.V., 2022) Kirişci, Murat; Demir, Ibrahim; Şimşek, Necip
    ELECTRE is a family of multi-criteria decision analysis techniques, which has the ability to provide as much as possible precise and suitable set of actions or alternatives to the underlying problem by eliminating the alternatives, which are outranked by others. Group decision-making is an effective process to provide the most appropriate solution to real-world decision-making scenarios by considering and merging the expert opinions of multiple individuals on the problem. The aim of this study is to present an extended version of the ELECTRE I model called the Fermatean fuzzy ELECTRE I method for of multi-criteria group decision-making with Fermatean fuzzy human assessments. The method proposed in this study has the possibility to solve multi-criteria group decision-making problems by using the Fermatean fuzzy decision matrix obtained in Fermatean fuzzy number form in the evaluations made with the available alternatives based on expert opinions. First, the mathematical description of the multi-criteria group decision-making problem with Fermatean fuzzy information has been given. Then, the proposed Fermatean fuzzy ELECTRE I method to deal with the problem has been presented. After the determination of the relative importance degree of experts, the Fermatean fuzzy aggregated averaging operator is employed to merge the individual Fermatean fuzzy decision matrices produced by the experts into the aggregated Fermatean fuzzy decision matrix. Next, for pairwise comparison of available alternatives with respect to considered criteria, the concepts of Fermatean fuzzy strong, midrange, and weak concordance and discordance sets are based on the approach of score function and accuracy function defined for Fermatean fuzzy numbers. Afterward, Fermatean fuzzy concordance and discordance matrices are defined, constructed by concordance and discordance indices. Finally, Fermatean fuzzy effective concordance and discordance matrices are computed to obtain Fermatean fuzzy aggregated outranking matrix, indicating abstract information on dominations of suitable alternatives to the others. The proposed method will be used in material selection in distinct implementations, exclusively in biomedical applications where the prosthesis materials should have similar characteristics to human tissues. Since biomedical materials are used in various parts of the human body for many different purposes, in this study, material selection will be made using the method presented for the femoral component of the hip joint prosthesis for orthopedists and practitioners who will choose biomaterials.
  • Küçük Resim Yok
    Öğe
    Soft set based new decision-making method with cardiovascular disease application
    (Yildiz Technical Univ, 2021) Kirisci, Murat; Demir, Ibrahim; Simsek, Necip
    A Pythagorean fuzzy set is characterized by values satisfying the condition that the square sum of the degree of membership and degree of non-membership is less than or equal to 1. As a generalized set, Pythagorean fuzzy sets have a close relationship with intuitionistic fuzzy sets. In this study, an algorithm is given that can select patients at risk of developing heart disease based on cardiovascular data. This given algorithm is created with Pythagorean fuzzy soft sets. The new algorithm is offered a medical decision-making method to assist in medical diagnosis. A medical case was examined as a real-life application to see if the proposed method is applicable. The real dataset which is called the Cleveland heart disease dataset has been chosen. In the application, the dataset is arranged as PFSS. In addition, the parameter set was determined and calculations were made in accordance with PFSS. A comparison table was created with the values obtained from these calculations. By choosing the maximum of the values obtained with the score function, the patient with the highest risk of developing heart disease was determined.