摘要:
Knowledge graph embedding aims to learn the embedded representation of entities and relations in knowledge graphs which is very important for the subsequent link prediction task. However, two key issues are existed for learning knowledge graph embedding: 1) How to take full advantage of the deep learning algorithms to generate expressive embeddings? 2) How to solve the polysemy phenomenon caused by multi-relations knowledge graphs that entities and relations show different semantics after involving different predictions? In this article, to tackle the first problem, the multi-layer convolutional networks are adopted to generate features about entities and relations then used to predict candidate entity. Moreover, the representation power of the networks is strengthened by integrating an effective recalibration mechanism which can accentuate informative features selectively. To tackle the second problem, we propose to learn multiple specific interaction embeddings. Instead of directly learning one general embedding to preserve all information for each entity and relation, their interactions are captured to model the cross-semantic influence from relations to entities and from entities to relations. Compared to traditional embedding models, the proposed model can provide more generalization capabilities and effectively capture potential links between entities and relations. Experimental results have revealed that the proposed model achieves the state-of-the-art performance for general evaluation metrics on link prediction tasks. (c) 2020 Elsevier B.V. All rights reserved.
作者机构:
[Zhang, Zhaoli; Nie, Hanwen; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Xiong, Naixue] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.
通讯机构:
[Liu, Hai] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
期刊:
PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON COMPUTER SCIENCE AND APPLICATION ENGINEERING (CSAE2019),2019年:Pages 1–7
通讯作者:
Shu, Jiangbo
作者机构:
[Tan, Fengxia; Peng, Liyuan; Shu, Jiangbo; Hu, Qianqian; Ge, Xiong] Cent China Normal Univ, Natl Engn Ctr E Learning, Wuhan, Peoples R China.
通讯机构:
[Shu, Jiangbo] C;Cent China Normal Univ, Natl Engn Ctr E Learning, Wuhan, Peoples R China.
会议名称:
3rd International Conference on Computer Science and Application Engineering (CSAE)
会议时间:
OCT 22-24, 2019
会议地点:
Sanya, PEOPLES R CHINA
会议主办单位:
[Shu, Jiangbo;Peng, Liyuan;Hu, Qianqian;Tan, Fengxia;Ge, Xiong] Cent China Normal Univ, Natl Engn Ctr E Learning, Wuhan, Peoples R China.
关键词:
Education big data;Student personal big data;Behavior analysis;Correlation analysis
摘要:
With the continuous improvement of the information construction of colleges and universities, the daily life and learning behaviors of college students are recorded and stored by major business systems, and they are accumulated, which has initially formed a large-scale and multi-type student personal big data environment. This paper mainly classifies and summarizes the students' data from the three aspects of student basic information, campus learning and campus life. It focuses on the feature extraction and index mining of students' campus consumption, curriculum and performance data, and constructs the student's personal big data behavior analysis model. In-depth analysis and mining of student consumption behavior data to explore students' dietary rules and consumption level. Through data analysis, the following rules were found: 1)The total number of students eating at school decreases year by year, and the breakfast rate decreases year by year; 2) Freshmen are one hour ahead of the "peak period" of breakfast meals for the whole group;3) The students' academic scores are highly correlated with the meal rate, breakfast meal rate and eating consumption level, and are less correlated with variables such as window selection stability, etc. 4) The more regular the student's diet, the more stable the level of consumption, and the higher the level of learning effort, the better the student's academic performance.
摘要:
Automatic multimedia learning resources recommendation has become an increasingly relevant problem: it allows students to discover new learning resources that match their tastes, and enables the e-learning system to target the learning resources to the right students. In this paper, we propose a content-based recommendation algorithm based on convolutional neural network (CNN). The CNN can be used to predict the latent factors from the text information of the multimedia resources. To train the CNN, its input and output should first be solved. For its input, the language model is used. For its output, we propose the latent factor model, which is regularized by L (1)-norm. Furthermore, the split Bregman iteration method is introduced to solve the model. The major novelty of the proposed recommendation algorithm is that the text information is used directly to make the content-based recommendation without tagging. Experimental results on public databases in terms of quantitative assessment show significant improvements over conventional methods. In addition, the split Bregman iteration method which is introduced to solve the model can greatly improve the training efficiency.
期刊:
ICDEL '18: Proceedings of the 2018 International Conference on Distance Education and Learning,2018年:Pages 122–126
通讯作者:
Li, Yang(ly0104@mails.ccnu.edu.cn)
作者机构:
[Zhang, Zhaoli; Li, Yang; Liu, Hai; Shu, Jiangbo] National Engineering Research Center for E-Learning, Science Hall, Central China Normal University, 152 Luoyu Road, Wuhan, Hubei, China
会议名称:
2018 International Conference on Distance Education and Learning, ICDEL 2018
摘要:
Recently, blending learning has attracted more and more researchers attention in the field of teaching and learning. However, there are many troubles in making it clear as teaching model is suitable for specific knowledge points and there are no fixed implementing pattern. In this paper, we propose a new teaching strategy for blending learning, and divide all the knowledge into five categories, such as declarative knowledge, concept knowledge, rule knowledge, basic skill knowledge, and problem solving knowledge. Furthermore, we analyze the characteristics of each category and predict which teaching model is suitable for a specific category. Then we have carried out the proposed teaching strategy on the geography course in senior high school. Experimental results demonstrate that the proposed strategy has the great significance in educational theory and practical application.
作者机构:
[Zhang, Zhaoli; Li, Zhifei; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Ctr E Learning, Wuhan, Hubei, Peoples R China.
会议名称:
International Symposium on Educational Technology (ISET)
会议时间:
JUN 27-29, 2017
会议地点:
City Univ Hong Kong, Hong Kong, HONG KONG
会议主办单位:
City Univ Hong Kong
关键词:
interactive visualization;junior middle school chemistry;applied research
摘要:
With the development of interactive visualization technology, it is an excellent choice to apply it to the field of education. In this paper, we first briefly introduce interactive visualization and design principles. Then, we select participants from junior high school in Wuhan (N=55) and use a between-subjects design with participants assigned randomly to one of two instructional conditions: interactive chemistry experiment platform (ICEP) and PowerPoint. The results show that the students who use the ICEP have better performance in learning and applying knowledge compared with traditional teaching. Finally, we propose the research direction of interactive visualization in education field and hope to provide a reference for the teachers and students to carry out research.
作者机构:
[Ru, Qianqian; Wang, Xu; Wang, Li; Liu, Rai; Zhang, Zhaoli; Zhi, Min; Shu, Jiangbo] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
会议名称:
2nd IEEE International Conference on Cloud Computing and Big Data Analysis (ICCCBDA)
会议时间:
APR 28-30, 2017
会议地点:
Chengdu, PEOPLES R CHINA
会议主办单位:
[Shu, Jiangbo;Wang, Xu;Wang, Li;Zhang, Zhaoli;Liu, Rai;Ru, Qianqian;Zhi, Min] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
关键词:
education big data;open service;model
摘要:
With the gradual improvement of the level of educational information, the idea of education big data has gone deep into people's minds. More and more teaching staff and researchers have the consciousness of the data needs, and expect to do the data mining and learning analysis of education big data. However, the most realistic and basic problem they have in the process of carrying out research is that there is no good data support or a convenient way to get data. Aiming at the problem, this article puts forward an education big data open service model, and builds the education big data open service platform based on the model. The platform has tried to run on the Central China Normal University and provides some data service for all the teachers and students in school. The data acquisition trouble is solved perfectly for teaching staff and researchers.
作者机构:
[Zhang, Zhaoli; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Li, Zhifei] Cent China Normal Univ, Collaborat & Innovat Ctr Educ Technol, Wuhan 430079, Hubei, Peoples R China.
会议名称:
International Conference on Advanced Technologies Enhancing Education (ICAT2E)
会议时间:
MAR 18-20, 2017
会议地点:
Qingdao, PEOPLES R CHINA
会议主办单位:
[Zhang, Zhaoli;Liu, Hai;Shu, Jiangbo] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.^[Li, Zhifei] Cent China Normal Univ, Collaborat & Innovat Ctr Educ Technol, Wuhan 430079, Hubei, Peoples R China.
会议论文集名称:
Advances in Social Science Education and Humanities Research
关键词:
Knowledge visualization;Double-Whiteboard;Teaching research
摘要:
Knowledge visualization plays an increasingly important role in the field of educational communication. However, most researches follow with interest a specific subject knowledge. Accordingly, we present the knowledge visualization by using different visualization tools based on the knowledge classification. And we present information in text and visualization by Double-Whiteboard. Then we selected two Physics classes as subjects in a middle school to reveal the impact of KV compared to traditional teaching. The result shows that this teaching method can effectively improve the teaching effects.
摘要:
Due to the influence of psychology and cognitive science, personalized learning has gradually drawn the attention of many researchers. The purpose of this paper is to research an acceptable personalized learning method for learners. In this paper, we perform a study by literature review from four aspects. Firstly, we construct learner model based on learner's learning style and cognitive ability. Then, we introduce the process of personalized learning in online learning environment. Moreover, we propose the way of information presentation by knowledge visualization, and pose corresponding intervention strategies for different learning stages. Finally, we conduct experiments, and prove that the personalized learning method is more effective than the conventional learning method.
作者机构:
[Zhang, Xingfang; Li, Zhenhua; Cao, Taihe; Zhang, Zhaoli; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Li, Zhenhua] China West Normal Univ, Network Ctr, Nanchong 637009, Peoples R China.
会议名称:
International Conference on Advanced Technologies Enhancing Education (ICAT2E)
会议时间:
MAR 18-20, 2017
会议地点:
Qingdao, PEOPLES R CHINA
会议主办单位:
[Shu, Jiangbo;Cao, Taihe;Zhang, Xingfang;Zhang, Zhaoli;Liu, Hai;Li, Zhenhua] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.^[Li, Zhenhua] China West Normal Univ, Network Ctr, Nanchong 637009, Peoples R China.
会议论文集名称:
Advances in Social Science Education and Humanities Research
摘要:
With the rapid development of information technology, blended learning as a worldwide hot topic in the field of education has attracted domestic and foreign researchers' attention including academic organizations, practitioners and education managers. In view of the shortage of the low efficiency in traditional offline learning due to the limitation of time and space, a novel application which contains offline learning and online learning was proposed. In our study, we selected the teaching of software engineering course and used starC as the supporting tool. Through analyzing learning behavior we found that students have higher learning enthusiasm and participation on blended learning than that on traditional offline learning. We can foresee that blended learning has a broad application prospect and huge development potential in the education.