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.
作者机构:
[吕磊; 贾钊逸; 栾银森] School of Information Science and Engineering, Henan University of Technology, Zhengzhou;450001, China;[吴珂] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan;430079, China;[吕磊; 贾钊逸; 栾银森] 450001, 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.
关键词:
Smart security;Person re-identification;Surveillance video analysis;Deep metric learning;Similarity probability
摘要:
Surveillance video analysis plays a vital role in the daily operations of smart cities, which increasingly relies on person re-identification technology to sustain smart security applications. However, research challenges of re-identification remain especially in terms of recognizing the different appearances of the same person in a harsh real-world environment: (1) the adaptability of the selected features to the dynamic environment cannot be guaranteed, and (2) existing methods rooted from metric learning aim to find a single metric function, and they lack the ability to measure the different appearances of the same person. To address these problems, this study proposes a multiple deep metric learning method empowered by the functionality of person similarity probability measurement. The proposed method exploits multiple stacked auto-encoder networks and classification networks to quantify pedestrians' similarity relations. The stacked auto-encoder networks directly recognize persons from surveillance images at the pixel level. The classification networks are equipped with the Softmax regression models and produce multiple similarity probabilities to characterize different appearances belonging to the same person. An Adaboost-like model is designed to fuse the probabilities corresponding to multiple metrics, which ensures a high accuracy of recognition. Experimental results on two public datasets (VIPeR and CUHK-01) indicate that the proposed method outperforms existing algorithms by 2%-10% at rank 1. Based on the similarity probabilities learned by the proposed model, the algorithm for matching the person pair can achieve a time complexity as low as O(n), which can be deployed at a large scale on the distributed intelligent surveillance network, with each node maintaining limited computing capabilities. (C) 2017 Elsevier Inc. All rights reserved.
作者机构:
[Zhang, Wei; Yi, Baolin; Qin, Shiming] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Tian, Peng] Cent China Normal Univ, Coll Publ Adm, Wuhan, Hubei, Peoples R China.
通讯机构:
[Tian, Peng] C;Cent China Normal Univ, Coll Publ Adm, Wuhan, Hubei, Peoples R China.
作者机构:
[Zhang, Kai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Zhang, Kai] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan, Hubei, Peoples R China.;[Zhang, Kai] Univ Regina, Dept Comp Sci, Regina, SK, Canada.
通讯机构:
[Zhang, Kai] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
期刊:
PROCEEDINGS OF 2019 THE 4TH INTERNATIONAL CONFERENCE ON DISTANCE EDUCATION AND LEARNING (ICDEL 2019),2019年:147-152
通讯作者:
Guo, Dongpo
作者机构:
[Li, Qing; Guo, Dongpo; Liu, Sanya; Chai, Huanyou] Cent China Normal Univ, Natl Engn Ctr E Learning, Wuhan 430079, Peoples R China.
通讯机构:
[Guo, Dongpo] C;Cent China Normal Univ, Natl Engn Ctr E Learning, Wuhan 430079, Peoples R China.
会议名称:
4th International Conference on Distance Education and Learning (ICDEL)
会议时间:
MAY 24-27, 2019
会议地点:
Shanghai, PEOPLES R CHINA
会议主办单位:
[Guo, Dongpo;Li, Qing;Liu, Sanya;Chai, Huanyou] Cent China Normal Univ, Natl Engn Ctr E Learning, Wuhan 430079, Peoples R China.
关键词:
Digital education service;Crowdfunding and Crowdsourcing;Ecology model;Block chain
摘要:
Crowdfunding and crowdsourcing in digital education service has become an important content in educational informatization. Different personalized demands from learners for digital education service are increasing day by day, which leads to the asymmetry between supply and demand. This paper aims to solve the asymmetry of supply and demand in education sector under the SISC ecology model based on value chain theory, and also to elaborate the ecology environment in digital education service, as well as the subject and content of crowdfunding and crowdsourcing. Block chain is the protection mechanism for the rights of subject, which improves the development of personalized education. Empirical study and qualitative analysis are used to fulfill the effectiveness of SISC ecology model of CFCS in DES. A case of "Parallel" successfully recommends 10 resources that suitable for the students, which proves the feasibility of the SISC ecology model so as to improve the motivations of CFCS subjects and student' satisfaction. This paper also supports future research by developing a framework for crowdfunding and crowdsourcing in digital education service.
作者机构:
[Li, Guangqiang; Huo, Yanzhu; Huang, Ao] Wuhan Univ Sci & Technol, State Key Lab Refractories & Met, Wuhan 430081, Hubei, Peoples R China.;[Yang, Juan] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.
通讯机构:
[Yang, Juan] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.
关键词:
big data;data mining;electrical conductivity;oxide melts
摘要:
Electrical conductivity is one of the most basic physical(-)chemical properties of oxide-based melts and plays an important role in the materials and metallurgical industries. Especially with the metallurgical melt, molten slag, existing research studies related to slag conductivity mainly used traditional experimental measurement approaches. Meanwhile, the idea of data-driven decision making has been widely used in many fields instead of expert experience. Therefore, this study proposed an innovative approach based on big data mining methods to investigate the computational simulation and prediction of electrical conductivity. Specific mechanisms are discussed to explain the findings of our proposed approach. Experimental results show slag conductivity can be predicted through constructing predictive models, and the Gradient Boosting Decision Tree (GBDT) model is the best prediction model with 90% accuracy and more than 88% sensitivity. The robustness result of the GBDT model demonstrates the reliability of prediction outcomes. It is concluded that the conductivity of slag systems is mainly affected by TiO(2), FeO, SiO(2), and CaO. TiO(2) and FeO are positively correlated with conductivity, while SiO(2) and CaO have negative correlations with conductivity.
作者机构:
[Liu, Tingting; Chen, Zengzhao; Liu, Hai; Zhang, Zhaoli; Chen, Yingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Liu, Tingting] Carnegie Mellon Univ, Sch Comp Sci, 5000 Forbes Ave, Pittsburgh, PA 15213 USA.;[Liu, Hai] City Univ Hong Kong, Dept Mech Engn, Hong Kong, Peoples R China.
会议名称:
2nd International Conference on Advances in Image Processing (ICAIP) / 2nd International Conference on Software Engineering and Development (ICSED
会议时间:
JUN 16-18, 2018
会议地点:
Chengdu, PEOPLES R CHINA
会议主办单位:
[Liu, Tingting;Chen, Zengzhao;Liu, Hai;Zhang, Zhaoli;Chen, Yingying] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.^[Liu, Tingting] Carnegie Mellon Univ, Sch Comp Sci, 5000 Forbes Ave, Pittsburgh, PA 15213 USA.^[Liu, Hai] City Univ Hong Kong, Dept Mech Engn, Hong Kong, Peoples R China.
期刊:
Lecture Notes in Computer Science,2018年10749:314-325 ISSN:0302-9743
通讯作者:
He, Bin
作者机构:
[Yu, Xinguo; He, Bin; Jian, Pengpeng; Xia, Meng] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Zhao, Gang] Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Hubei, Peoples R China.
通讯机构:
[He, Bin] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
会议名称:
8th Pacific-Rim Symposium on Image and Video Technology (PSIVT)
会议时间:
NOV 20-24, 2017
会议地点:
Wuhan, PEOPLES R CHINA
会议主办单位:
[Yu, Xinguo;Jian, Pengpeng;He, Bin;Xia, Meng] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.^[Zhao, Gang] Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Hubei, Peoples R China.
摘要:
This paper presents an algorithm for understanding problems from circuit schematics in exercise problems in physics at secondary school. This paper models the problem understanding as a problem of extracting a set of relations that can be used to solve problems with enough information. The challenges lie in not only analyzing the circuit schematics but also extracting the proper relations for a given exercise problem. To face these challenges a novel approach is proposed to detect circuit nodes with their current flows to extract the current equations for nodes. And the other novel approach is proposed to extract voltage equations of independent loops. The proposed approach was tested with a dataset collected from the text books and the exam papers for the students at secondary schools. Experimental results show that the effect of recognition and analysis we designed delivers promising result, and our approach can be adapted to more complex electrical circuit analysis.
作者机构:
[张坤; 刘乐元; 罗珍珍; 陈靓影] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, 430079, China;[张坤; 陈靓影; 刘乐元] Innovative Center for Educational Technology, Wuhan, 430079, China
通讯机构:
National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
关键词:
笑脸检测;条件随机森林;头部姿态估计;K-Means聚类
摘要:
为减少非约束环境下头部姿态多样性对笑脸检测带来的不利影响,提出一种基于条件随机森林(Conditional random forests, CRF)的笑脸检测方法. 首先,以头部姿态作为隐含条件划分数据空间,构建基于条件随机森林的笑脸分类器;其次,以K-Means聚类方法确定条件随机森林分类器的分类边界;最后,分别从嘴巴区域和眉眼区域采集图像子块训练两组条件随机森林构成层级式结构进行笑脸检测.本文的笑脸检测方法在GENKI-4K、LFW和自备课堂场景(CCNU-Classroom)数据集上分别取得了91.14 %, 90.73 %和85.17 %的正确率,优于现有基于支持向量机、AdaBoost和随机森林的笑脸检测方法.
作者机构:
[Liu, Tingting; Zhang, Zhaoli; Liu, Sanya; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Liu, Tingting; Liu, Hai] City Univ Hong Kong, Dept Mech Engn, 83 Tat Chee Ave, Kowloon, Hong Kong, Peoples R China.;[Liu, Tingting] Univ Pittsburgh, Sch Educ, Pittsburgh, PA 15260 USA.
通讯机构:
[Liu, Hai] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;City Univ Hong Kong, Dept Mech Engn, 83 Tat Chee Ave, Kowloon, Hong Kong, Peoples R China.
期刊:
Proceedings of 2017 6th International Conference on Computer Science and Network Technology, ICCSNT 2017,2018年2018-January:157-160
通讯作者:
Zan, Hui(zxydhh@163.com)
作者机构:
[Luo, Zhuoran; Yu, Peng; Zhao, Gang; Lu, Shuai] School of Educational Information Technology, Central China Normal University, Wuhan, 430079, China;[Zan, Hui] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, 430079, China;[Zhao, Dasheng] Wuhan Maritime Communication Research Institute, Wuhan, 430079, China
通讯机构:
National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China
摘要:
Extracting algebraic relations from a given circuit image is still a challenge task due to the complex topology of considered circuit. This paper presents an approach for extracting algebraic relations from circuit images through producing a set of atomic topologies from the complex topology of a given circuit. In which, algebraic relations, in form of a set of equations involving voltage, current and resistance relations from atomic topologies that is obtained by an iteratively operation of transforming a complex series/parallel connection into a series of atomic connection topology breaking down and shrinking. The extracted algebraic relations can be used to solve the exercise problem described by the circuit. Experimental results on 20 exercise problems show that the proposed algorithm can obtain a complete set of algebraic relations that can be used to solve the given problem. Further experiments conducted on a dataset of 200 scanned circuit images from the text books and exam papers demonstrate the proposed algorithm is the robustness and effectiveness.
作者机构:
[Hao, Yixue] National Engineering Research Center for E-learning, Central China Normal University, No. 152, Luoyu road, Hongshan district, Wuhan city, Hubei province, China;[Liu, Qingtang; Zhai, Huiqing] School of Educational Information Technology, Central China Normal University, No. 152, Luoyu road, Hongshan district, Wuhan city, Hubei province, China
会议名称:
2018 International Conference on Distance Education and Learning, ICDEL 2018