Prediction of Prospective Mathematics Teachers Academic Success in Entering Graduate Education by Using Back-Propagation Neural NetworkReportar como inadecuado

Prediction of Prospective Mathematics Teachers Academic Success in Entering Graduate Education by Using Back-Propagation Neural Network - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Journal of Education and Training Studies, v4 n5 p113-122 May 2016

The purpose of this study is to examine a neural network based approach to predict achievement in graduate education for Elementary Mathematics prospective teachers. With the help of this study, it can be possible to make an effective prediction regarding the students' achievement in graduate education with Artificial Neural Networks (ANN). Two different neural networks are used for an effective prediction of the first network in which some core courses are taken by prospective Mathematics teachers in their first two years, including General Mathematics, Pure Mathematics, Analysis I, Analysis II, Geometry, Linear Algebra-I. The scores received from the above courses are used as an input for the back-propagation neural network (BPNN). Additionally, the scores of vocational core courses taken by third year students, including Analysis 3, Special Teaching Methods 2, Elementary Number Theory, Algebra, Problem Solving, are used as the output of the BPNN. The second network uses the scores of all courses which are previously mentioned and uses them as an input of BPNN and also uses ALES (Academic Personnel and Postgraduate Education Entrance Exam) score. They are used as an output of the BPNN. Besides, the correlation analysis is conducted by using the average graduation and ALES scores components. Analytical results demonstrate that the BPNN model offers relatively accurate predictions for the student success in graduate education with a high average of accuracy (Neural Network1 is 77.125% and Neural Network2 is 68.5%). Another finding is that there is no significant correlation between the graduate average scores of candidates who qualified for a graduate education and their ALES scores. These results indicate that BPNN is a suitable tool to predict the academic success of all education majors. Student career advisors can use the ANN model to identify the students who have particular potential for graduate education, and this prediction model can help these students adjust their own teaching strategies, and provide guidance and support for their careers.

Descriptors: Preservice Teachers, Graduate Study, Academic Achievement, Elementary Education, Mathematics Teachers, Prediction, Artificial Intelligence, Courses, Correlation, Scores, College Entrance Examinations, Foreign Countries

Redfame Publishing Inc. 9450 SW Gemini Drive #99416, Beaverton, OR 97008. Tel: 503-828-0536 ext. 503; Fax: 503-828-0537; e-mail: jets[at]; Web site:

Autor: Bahadir, Elif



Documentos relacionados