Education 4.0-Fostering Student's Performance with Machine Learning Methods

被引:0
作者
Ciolacu, Monica [1 ,2 ]
Tehrani, Ali Fallah [2 ]
Beer, Rick [2 ]
Popp, Heribert [2 ]
机构
[1] Univ Politehn Bucuresti, UPB CETTI, Bucharest, Romania
[2] DIT, Fac Business Informat, Bavaria, Germany
来源
2017 IEEE 23RD INTERNATIONAL SYMPOSIUM FOR DESIGN AND TECHNOLOGY IN ELECTRONIC PACKAGING (SIITME) | 2017年
关键词
Education; 4.0; learning analytics; machine learning; neural networks; k-means clustering; kernel methods;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Educational activity is increasingly moving online and course contents are becoming available in digital format. This enables data collection and the use of data for analyzing learning process. For the 4th Revolution in Education, an active and interactive presence of students contributes to a higher learning quality. Machine Learning techniques recently have shown impressive development steps of the use of data analysis and predictions. However, it has been far less used for assessing the learning quality. For this paper we conducted analysis based on neural networks, support vector machine, decision trees and cluster analysis to estimate student's performance at examination and shape the next generation's talent for Industry 4.0 skills.
引用
收藏
页码:432 / 437
页数:6
相关论文
共 16 条
  • [1] [Anonymous], 2001, Learning with Kernels |
  • [2] [Anonymous], 2017, WHATS DIFF LEARN TEC
  • [3] [Anonymous], ADAM METHOD STOCHAST
  • [4] [Anonymous], 2005, FINDING GROUPS DATA
  • [5] Ciolacu M., 2017, IEEE 23 INT IN PRESS
  • [6] Ciolacu M., 2016, IEEE 22 INT S SIITME, P300, DOI DOI 10.1109/SIITME.2016.7777299
  • [7] Cochran Martin J., 2008, THESIS
  • [8] Ferguson R., LEARNING ANAL VISION
  • [9] Keras Documentation, PYTH DEEP LEARN LIB
  • [10] McAfee A, 2012, HARVARD BUS REV, V90, P60