期刊：
Expert Systems with Applications,2020年158:113519 ISSN：0957-4174
通讯作者：
Su, Zhu;Liu, Sannyuya
作者机构：
[Yang, Zongkai; Liu, Sannyuya; Su, Zhu; Liu, SYY; Liu, Zhi; Ke, Wenxiang; Zhao, Liang] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.;[Yang, Zongkai; Liu, Sannyuya] Cent China Noma Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
通讯机构：
[Su, Z; Liu, SYY] C;Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan 430079, Peoples R China.
关键词：
Evolution feature;Behavior character;Friendship network;Percolation theory
摘要：
Analyzing and mining students' behaviors and interactions from big data is an essential part of education data mining. Based on the data of campus smart cards, which include not only static demographic information but also dynamic behavioral data from more than 30000 anonymous students, in this paper, the evolution features of friendship and the relations between behavior characters and student interactions are investigated. On the one hand, four different evolving friendship networks are constructed by means of the friend ties proposed in this paper, which are extracted from monthly consumption records. In addition, the features of the giant connected components (GCCs) of friendship networks are analyzed via social network analysis (SNA) and percolation theory. On the other hand, two high-level behavior characters, orderliness and diligence, are adopted to analyze their associations with student interactions. Our experiment/empirical results indicate that the sizes of friendship networks have declined with time growth and both the small-world effect and power-law degree distribution are found in friendship networks. Second, the results of the assortativity coefficient of both orderliness and diligence verify that there are strong peer effects among students. Finally, the percolation analysis of orderliness on friendship networks shows that a phase transition exists, which is enlightening in that swarm intelligence can be realized by intervening the key students near the transition point. (C)2020 Elsevier Ltd. All rights reserved.
期刊：
2018 SEVENTH INTERNATIONAL CONFERENCE OF EDUCATIONAL INNOVATION THROUGH TECHNOLOGY (EITT 2018),2018年:210-213 ISSN：2168-944X
通讯作者：
Kang, Lingyun
作者机构：
[Liu, Sannyuya; Li, Qing; Liu, Zhi; Kang, Lingyun; Su, Zhu] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
通讯机构：
[Kang, Lingyun] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
会议名称：
7th International Conference of Educational Innovation through Technology (EITT)
会议时间：
DEC 11-14, 2018
会议地点：
Massey Univ, Sch Humanities, Auckland, NEW ZEALAND
会议主办单位：
Massey Univ, Sch Humanities
会议论文集名称：
Proceedings of the International Conference of Educational Innovation through Technology
关键词：
social network analysis;sentiment density;learning outcomes
摘要：
With the explosion of learning data in online educational platforms, many educators and researchers have developed a keen interest in learning analytics, in which social network analysis (SNA) and sentiment analysis are the two critical methods for exploring collective learning processes. In this study, we extracted textual data from the discussion forum of a "contract law" course in a university learning platform. We examined the differences in distributions of males and females in the overall sociogram. As well, through calculating learners' social characteristics and sentiment densities across a semester, we explored the relationship among social characteristics, sentiments and learning outcomes. The experimental results showed that females tended to be more active than males in forum interactions, and high-performing learners participated more actively in interactions than did low-performing learners. Moreover, there was a strong positive correlation between confusion and learning outcomes. As well, the learners who were involved actively in discussions were more likely to express the confused sentiment.
期刊：
Journal of Physics: Conference Series,2018年1113(1):012021 ISSN：1742-6588
通讯作者：
Su, Zhu(suz@mail.ccnu.edu.cn)
作者机构：
[Jianwen Sun; Lingyun Kang; Zhu Su; Sannyuya Liu; Zhi Liu] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China;[Jianwen Sun; Zhu Su; Sannyuya Liu; Zhi Liu] National Engineering Laboratory for Technology of Big Data Applications in Education, Central China Normal University, Wuhan, China
通讯机构：
National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
作者机构：
[Sun, Jianwen; Liu, Sannyuya; Liu, Zhi; Kang, Lingyun; Su, Zhu] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Rudian, Sylvio] Humboldt Univ, Dept Comp Sci, Weizenbaum Inst Networked Soc, Berlin, Germany.
会议名称：
International Joint Conference on Information, Media and Engineering (ICIME)
会议时间：
DEC 12-14, 2018
会议地点：
Osaka Univ, Int Joint Lab Knowledge & Media Dynam Educ Fields, Osaka, JAPAN
会议主办单位：
Osaka Univ, Int Joint Lab Knowledge & Media Dynam Educ Fields
关键词：
social network analysis;emotion density;network structure
摘要：
In recent years, a growing number of educational researchers are keen to utilize social network analysis (SNA) and emotion detection for exploring collective learning states. Students' emotions and interaction characteristics before the exam typically suggest some significant traces of learning states. In this study, data from the discussion forum of "Chinese legal history" course in a university learning platform was used to investigate evolutionary trends of students' network characteristics and emotion densities (EDs) in the last four weeks before the final exam, as well as visualized the distribution of the high-EDs (including positivity, negativity and confusion) students in the weekly network. Empirical analyses suggested that, as the exam approaches, learners' network structure and emotional densities are constantly changing. After experiencing a smooth change in the first two weeks, the average degree centrality reached a peak in the third week, and confusion emotional density far exceeded positive and negative emotional density in the last week, which may help in identifying the potential academic losers and providing timely interventions.
期刊：
Communications in Computer and Information Science,2016年662:119-130 ISSN：1865-0929
通讯作者：
Chen, Jingying
作者机构：
[Liu, Leyuan; Luo, Zhenzhen; Su, Zhiming; Liu, Yuanyuan; Chen, Jingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.
通讯机构：
[Chen, Jingying] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.
会议名称：
第七届全国模式识别学术会议(The 7th Chinese Conference on Pattern Recognition,CCPR2016)
会议时间：
2016-11-03
会议地点：
成都
会议论文集名称：
第七届全国模式识别学术会议(The 7th Chinese Conference on Pattern Recognition,CCPR2016)论文集
关键词：
Smile recognition;Conditional random forest;Interest detection;Head poses
摘要：
“Interest”is a critical bridge between cognitive and effective issues in learning. Student’s interest has great impact on learning performance. Hence, it’s necessary to detect student’s interest and make them more engaged in the learning process for productive learning. Student’s interest can be detected based on the facial expression recognition, e.g., smile recognition. However, various head poses, different illumination, occlusion and low image resolution make smile recognition difficult. In this paper, a conditional random forest based approach is proposed to recognize spontaneous smile in natural environment. First, image patches are extracted within the eye and mouth regions instead of the whole face to improve the robustness and efficiency. Then, the conditional random forests based approach is presented to learn the relations between image patches and the smile/non-smile features conditional to head poses. Furthermore, a K-means based voting method is introduced to improve the discrimination capability of the approach. Experiments have been carried out with different spontaneous facial expression databases. The encouraging results suggest a strong potential for interest detection in natural environment.
作者机构：
[Liu, Leyuan; Luo, Zhenzhen; Su, Zhiming; Luo, Nan; Zhang, Kun; Liu, Yuanyuan; Chen, Jingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Liu, Yuanyuan] Wenhua Coll, Wuhan, Peoples R China.
通讯机构：
[Chen, Jingying] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
关键词：
Database systems;Decision trees;Forestry;Image resolution;Textures;Attention estimations;Geometric feature;Head Pose Estimation;Human Machine Interface;Probabilistic models;Unconstrained environments;Weighted voting;Weighted voting methods;Random forests;accuracy;Article;classification;classification algorithm;Dirichlet tree distribution enhanced random forest;facies;image analysis;intermethod comparison;mathematical analysis;mathematical model;noise;prediction;priority journal;probability;random forest
摘要：
Head pose estimation (HPE) is important in human-machine interfaces. However, various illumination, occlusion, low image resolution and wide scene make the estimation task difficult. Hence, a Dirichlet-tree distribution enhanced Random Forests approach (D-RF) is proposed in this paper to estimate head pose efficiently and robustly in unconstrained environment. First, positive/negative facial patch is classified to eliminate influence of noise and occlusion. Then, the D-RF is proposed to estimate the head pose in a coarse-to-fine way using more powerful combined texture and geometric features of the classified positive patches. Furthermore, multiple probabilistic models have been learned in the leaves of the D-RF and a composite weighted voting method is introduced to improve the discrimination capability of the approach. Experiments have been done on three standard databases including two public databases and our lab database with head pose spanning from -90 to 90 in vertical and horizontal directions under various conditions, the average accuracy rate reaches 76.2% with 25 classes. The proposed approach has also been evaluated with the low resolution database collected from an overhead camera in a classroom, the average accuracy rate reaches 80.5% with 15 classes. The encouraging results suggest a strong potential for head pose and attention estimation in unconstrained environment. Head pose estimation (HPE) is important in human-machine interfaces. However, various illumination, occlusion, low image resolution and wide scene make the estimation task difficult. Hence, a Dirichlet-tree distribution enhanced Random Forests approach (D-RF) is proposed in this paper to estimate head pose efficiently and robustly in unconstrained environment. First, positive/negative facial patch is classified to eliminate influence of noise and occlusion. Then, the D-RF is proposed to estimate the head pose in a coarse-to-fine way using more powerful combined texture and geometric features of the classified positive patches. Furthermore, multiple probabilistic models have been learned in the leaves of the D-RF and a composite weighted voting method is introduced to improve the discrimination capability of the approach. Experiments have been done on three standard databases including two public databases and our lab database with head pose spanning from -90 to 90 in vertical and horizontal directions under various conditions, the average accuracy rate reaches 76.2% with 25 classes. The proposed approach has also been evaluated with the low resolution database collected from an overhead camera in a classroom, the average accuracy rate reaches 80.5% with 15 classes. The encouraging results suggest a strong potential for head pose and attention estimation in unconstrained environment.
期刊：
International Journal of Pattern Recognition and Artificial Intelligence,2015年29(8):1556011 ISSN：0218-0014
通讯作者：
Chen, Jingying
作者机构：
[Shan, Cunjie; Cai, Pei; Su, Zhiming; Liu, Yuanyuan; Chen, Jingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;Wenhua Coll, CICET, Wuhan, Peoples R China.
通讯机构：
[Chen, Jingying] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
关键词：
D-RF;unconstrained face analysis;hierarchical regression;head pose estimation;facial feature detection
摘要：
Head pose and facial feature detection are important for face analysis. However, many studies reported good results in constrained environment, the performance could be decreased due to the high variations in facial appearance, poses, illumination, occlusion, expression and make-up. In this paper, we propose a hierarchical regression approach, Dirichlet-tree enhanced random forests (D-RF) for face analysis in unconstrained environment. D-RF introduces Dirichlet-tree probabilistic model into regression RF framework in the hierarchical way to achieve the efficiency and robustness. To eliminate noise influence of unconstrained environment, facial patches extracted from face area are classified as positive or negative facial patches, only positive facial patches are used for face analysis. The proposed hierarchical D-RF works in two iterative procedures. First, coarse head pose is estimated to constrain the facial features detection, then the head pose is updated based on the estimated facial features. Second, the facial feature localization is refined based on the updated head pose. In order to further improve the efficiency and robustness, multiple probabilitic models are learned in leaves of the D-RF, i.e. the patch's classification, the head pose probabilities, the locations of facial points and face deformation models (FDM). Moreover, our algorithm takes a composite weight voting method, where each patch extracted from the image can directly cast a vote for the head pose or each of the facial features. Extensive experiments have been done with different publicly available databases. The experimental results demonstrate that the proposed approach is robust and efficient for head pose and facial feature detection.
