Matematik Eğitiminde Bireye Özgü Öğretim Yönteminin Yapay Sinir Ağları ile Belirlenmesi

View/ Open
Date
2024Author
Gümüş, Rabiya
xmlui.dri2xhtml.METS-1.0.item-emb
Acik erisimxmlui.mirage2.itemSummaryView.MetaData
Show full item recordAbstract
This thesis aims to improve the quality and efficiency of education by identifying the most appropriate learning method for each student through artificial neural networks. In addition, this method will also allow teaching approaches to be adapted to different intelligence types. The study was conducted on students in grades 5, 6, and 7 of middle school. In the first stage of the data collection process, students completed a student profile form consisting of demographic variables and a 27-item multiple intelligence scale. Then, a mathematics pre-test (level determination test) determined by the researchers was applied to determine the students' prior knowledge and mathematics level. Teachers completed the teaching of the determined mathematics gain using one of the different teaching method lesson plans prepared by the researcher. After the completion of the instruction, a mathematics post-test (mathematics test) was applied to measure the effect of the used teaching method on learning. The data obtained from the forms and tests were transferred to an Excel file and brought together for the training and testing of the artificial neural network. An artificial neural network structure suitable for the data was established. The model was created by defining the layers, activation function, and other algorithms of the network using Python. The prepared data sets were used in the training, testing and validation stages of the artificial neural network to complete the model. It was observed that the established model made sufficiently accurate predictions for new data that the model had never encountered before. At the end of the research, it was aimed to determine the appropriate teaching methods according to the individual differences of the students with artificial neural networks. The network outputs the most appropriate teaching method for a new data entered into the system as a result. Thus, real-time insights are provided to educators to make teaching decisions, while allowing students to progress at their own pace by providing timely feedback and scaffolding support.