logo

SCIENCE CHINA Information Sciences, Volume 62 , Issue 2 : 029101(2019) https://doi.org/10.1007/s11432-017-9371-y

Pre-course student performance prediction with multi-instance multi-label learning

More info
  • ReceivedDec 1, 2017
  • AcceptedFeb 26, 2018
  • PublishedJun 27, 2018

Abstract

There is no abstract available for this article.


Acknowledgment

This work was supported by National Natural Science Foundation of China (Grant Nos. 61671274, 61573219, 61701281), Science and Technology Plan Project of Shandong Higher Education Institutions (Grant No. J15LN55), Shandong Provincial Natural Science Foundation (Grant No. ZR2017QF009), Fostering Project of Dominant Discipline and Talent Team of Shandong Province Higher Education Institutions, and China Postdoctoral Science Foundation (Grant No. 2016M592190).


Supplement

Appendixes A–C.


References

[1] Ren Z, Rangwala H, Johri A. Predicting performance on MOOC assessments using multi-regression models. In: Proceedings of the 9th International Conference on Educational Data Mining, Raleigh, 2016. 484--489. Google Scholar

[2] Meier Y, Xu J, Atan O. Predicting Grades. IEEE Trans Signal Process, 2016, 64: 959-972 CrossRef ADS arXiv Google Scholar

[3] Zhou Z H, Zhang M L. Multi-instance multi-label learning with application to scene classification. In: Proceedings of International Conference on Neural Information Processing Systems, Vancouver, 2006. 1609--1616. Google Scholar

[4] Zafra A, Romero C, Ventura S. Multiple instance learning for classifying students in learning management systems. Expert Syst Appl, 2011, 38: 15020-15031 CrossRef Google Scholar

[5] Sweeney M, Rangwala H, Lester J, et al. Next-term student performance prediction: a recommender systems approach,. arXiv Google Scholar

[6] Zhang M L. A k-nearest neighbor based multi-instance multi-label learning algorithm. In: Proceedings of the 22nd International Conference on Tools with Artificial Intelligence (ICTAI'10), Arras, 2010. 207--212. Google Scholar

[7] Liu B, Chen-Chuan-Chang K. Editorial. SIGKDD Explor Newsl, 2004, 6: 1-4 CrossRef Google Scholar

[8] Wang J, Zucker J D. Solving the multiple-instance problem: a lazy learning approach. In: Proceedings of the 17th International Conference on Machine Learning, Stanford, 2000. 1119--1126. Google Scholar

[9] Zhou Z H. Machine Learning. Beijing: Tsinghua University Press, 2016. 29--35. Google Scholar

  • Figure 1

    (Color online) Multi-instance multi-label representation for pre-course student performance prediction. Each instance represents information about one of the student's previous courses, e.g., Periods: 64 (hours), Theory-teaching period (Theory-P): 32 (hours), Experiment period (Exp-P): 32 (hours), Credit: 4, Course nature: 1 (1 compulsory or 0 optional), Examination form: 1 (1 close-book or 0 open-book), Score: 80.

Copyright 2020 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备17057255号       京公网安备11010102003388号