Scholarships Determination to Talented Students Based on Academic Characteristics with Deep Learning Approach and Particle Swarm Optimization Algorithm

Document Type : Original Article

Authors

1 Faculty of Computer Science, Bialystok University of Technology´╝îWiejska 45A, 15-531, Bialystok, Poland

2 Faculty of Mechanical Engineering, Bialystok University of Technology, Wiejska 45C, 15-531, Bialystok, Poland

Abstract

Knowledge is the most basic and important principle for students. Students can be classified based on knowledge. This classification is based on students' abilities and activities. Since MsC students need to receive scholarships to other countries to gain more knowledge, it is essential to provide a decision management and knowledge management system. Therefore, there is a need for a data set of students' information in order to perform a data mining process in order to find those elite students based on their activities and abilities of students and recommend them scholarships. Therefore, the present research tries to present such a system which is based on Natural Language Processing (NLP), feature extraction operations with Particle Swarm Optimization (PSO) algorithm and finally offers suggestions with deep Convolutional Neural Network (CNN). The results show that the accuracy of the proposed approach is higher than previous methods.

Keywords