LSTM Deri̇n Si̇ni̇r Ağlari İle Üni̇versi̇te Gi̇ri̇ş Sinavindaki̇ Matemati̇k Soru Sayilarinin Konulara Göre Tahmi̇ni̇

Abstract

In this study, we proposed a model for estimating the number of questions in the long short term memory (LSTM) deep neural network (DNN) and the mathematics test in the university entrance exam. The data set of the model consists of 931 questions divided according to 16 subjects of the mathematics test for the years 1981-2018. The data set is divided into 80% for the training of the model and 20% for the test. Hypercritical parameters have been determined to provide high accuracy in time series estimation problems in the LSTM model. The number of questions for each subject group has been trained one by one in the time series model. As a result of the study, the average accuracy was 98.42% and the average accuracy was 96.82% in the test. The data set was compared with machine learning algorithms to measure the accuracy of the DNN algorithm used and LSTM DSA achieved the highest performance. As a result of study, the future studies will provide the development of robots to predict because of the high accuracy of the model.

Nursing Strategies for Diabetic Patient Management: Predicting Parameter Values Post-Exenatide Treatment with Machine Learning Algorithm

“…Machine learning method, which is used in many scientific studies in different fields [10,28,29,35] is the basis of many studies in the field of health [36][37][38]. In machine learning method, classification and prediction [36][37][38][39][40] operations can be performed on images such as X-ray films, ultrasound records, MR images, and the same operations can be performed on numerical data [41][42][43][44].…”