Application of Advanced Petri Net in Personalized Learning

被引：1

作者：

Dai, Junyi ^{[1
]}

Su, Guiping ^{[1
]}

Sun, Yuan ^{[2
]}

Ye, Shiwei ^{[1
]}

Liao, Pan ^{[1
]}

Sun, Yi ^{[1
]}

机构：

[1] Univ Chinese Acad Sci, Beijing, Peoples R China

[2] Natl Inst Informat, Tokyo, Japan

来源：

2018 9TH INTERNATIONAL CONFERENCE ON E-EDUCATION, E-BUSINESS, E-MANAGEMENT AND E-LEARNING (IC4E 2018) | 2018年

关键词：

Personalized learning; Timed Petri Net; Fuzzy Petri Net; knowledge space; optimal learning path;

D O I：

10.1145/3183586.3183588

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

Personalized learning refers to efforts required to tailor pedagogical approaches in order to meet students' various individualized learning requirements. Learning objectives and instructional content may vary based on learner. Profiles, for example, in the selection of specific learning sequences and assessment methods. Thus, to address these issues, advanced Petri nets (consisting of timed Petri nets (TPNs) and fuzzy Petri nets (FPNs)) are applied to personalize learning. In the following ways. First, the knowledge space theory is used to pretreat several knowledge points. And then, a knowledge structure model based on TPNs is used to calculate students' optimal learning path. Finally, a learning process model based on FPNs is created to ensure that all learners master the specific learning objectives set out in the syllabus. The main advantages of this model are that it imposes a highly organized structure upon learning as well as reducing highly complex knowledge spaces to a set of more compact and easily managed knowledge points.

引用

页码：1 / 6

页数：6

共 17 条

[1]

Albano G., 2015, INT C INT NETWORKING, V11, P689

[2]

[Anonymous], 2015, 2015 LONG ISLAND SYS

[3]

Barkaoui K., 1995, Proceedings 1995 INRIA/IEEE Symposium on Emerging Technologies and Factory Automation. ETFA'95 (Cat. No.95TH8056), P499, DOI 10.1109/ETFA.1995.496690

[4] Diagnosability Analysis of Labeled Time Petri Net Systems [J].