Murat Kayri

Dr. Murat Kayri


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
MKMurat Kayri
Murat Kayri
The objective of this study is to compare the predictive ability of Bayesian regularization with Levenberg–Marquardt Artificial Neural Networks. To examine the best architecture of neural networks, the model was tested with one-, two-, three-, four-, and five-neuron architectures, respectively. MATLAB (2011a) was used for analyzing the Bayesian regularization and Levenberg–Marquardt learning algorithms. It is concluded that the Bayesian regularization training algorithm shows better performance than the Levenberg–Marquardt algorithm. The advantage of a Bayesian regularization artificial neural network is its ability to reveal potentially complex relationships, meaning it can be used in quantitative studies to provide a robust model.

2 February 2021 in Arabian Journal for Science and Engineering
Verified
Journal Article
Closed access
PDF file
EEerdal eker
erdal eker
MKMurat Kayri
Murat Kayri
SESerdar Ekinci
Serdar Ekinci
Davut IzciDavut Izci
Davut Izci


18 November 2021 in Arabian Journal for Science and Engineering
Verified
Journal Article
Closed access
PDF file
SESerdar Ekinci
Serdar Ekinci
Davut IzciDavut Izci
Davut Izci
MKMurat Kayri
Murat Kayri

5 April 2020 in Education and Science
Verified
Journal Article
Open access
PDF file
ÖGÖzlem Bezek Güre
Özlem Bezek Güre
MKMurat Kayri
Murat Kayri
FEFevzi Erdoğan
Fevzi Erdoğan
The aim of this study is to determine the factors affecting PISA 2015 Mathematics literacy by using data mining methods such as Multi-layer Perceptron Artificial Neural Networks and Random Forest. Cause and effect relation within the context of the study was tried to be discovered by means of data mining methods at the level of deep learning. In terms of Prediction Ability, the findings of the method whose performance was high were accepted as the factors determining the qualifications in Mathematics literacy in Turkey. In this study, the information, which was collected from a total of 4422 students, 215 (49%) of whom were boys and 2257 (51%) of whom were girls participating in PISA 2015 test, was used. The scores, which the students, having gone in for PISA 2015 test, got from mathematics test, and dependent variables and 25 variables, which were thought to have connection with dependent variables institutionally, were included in the analysis as predictors. As a result of analysis, it was witnessed that Random Forest (RF) method made prediction with smaller errors in terms of a number of performance indicators. The factors that random forest method found important after anxiety variable are Turkish success level of students, mother education level, motivation level, the belief in epistemology, interest level of teachers and class disciplinary environment, respectively. The statistical meaning, significance and impact levels of other variables were tackled together with their details in this study. It is expected that this study will set an example for data mining use in the process of educational studies and that the factors whose affects were found out about the students’ mathematics literacy will shed light on National Education system.