期刊：
Multimedia Tools and Applications,2017年76(17):18027-18045 ISSN：1380-7501
通讯作者：
Huang, Tao
作者机构：
[Zheng, Zhigao] Huazhong Univ Sci & Technol, Sch Comp & Technol, Wuhan 430079, Hubei, Peoples R China.;[Jeong, Hwa-Young] Kyung Hee Univ, Humanitas Coll, 1 Hoegi Dong, Seoul, South Korea.;[Shu, Jiangbo; Huang, Tao] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.
通讯机构：
[Huang, Tao] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.
关键词：
Kernel density estimation;Distributed;Data stream;Stream analysis;Exponential decay policy
摘要：
Multimedia networks hold the promise of facilitating large-scale, real-time data processing in complex environments. Their foreseeable applications will help protect and monitor military, environmental, safety-critical, or domestic infrastructures and resources. Cloud infrastructures promise to provide high performance and cost effective solutions to large scale data processing problems. This paper focused on the outlier detection over distributed data stream in real time, proposed kernel density estimation (KDE) based outlier detection algorithm KDEDisStrOut in Storm, firstly formalized the problem of outlier detection using the kernel density estimation technique and update the transported data incrementally between the child node and the coordinator node which reduces the communication cost. Then the paper adopted the exponential decay policy to keep pace with the transient and evolving natures of stream data and changed the weight of different data in the sliding window adaptively made the data analysis more reasonable. Theoretical analysis and experiments on Storm with synthetic and real data show that the KDEDisStrOut algorithm is efficient and effective compared with existing outlier detection algorithms, and more suitable for data streams.
作者机构：
[Kong, Deli; Cao, Taihe; Zhang, Zhaoli; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Liu, Hai] City Univ Hong Kong, Dept Mech & Biomed Engn, Kowloon, 83 Tat Chee Ave, Hong Kong, Peoples R China.
会议名称：
International Symposium on Educational Technology (ISET)
摘要：
Recently, blended learning has attracted more and more attention by the educational researchers. They often focus on how to combine blended learning with advanced technology to serve the teaching. In this paper, we proposed a novel learning pattern of "blended plus flipped". The pattern combined blended learning with flipped classroom, which integrated with offline learning, online learning, and study in class and out of class,. This achieves seamless integration of time and space. We test this idea using the course of "Educational Technology Research Method" and the experimental result demonstrates that blended learning pattern outperforms the traditional learning pattern. It is found that the time length of online learning and the active degree of the forum are the major factors affecting the blended learning pattern.
摘要：
Blended learning has caused comprehensive attention for domestic and foreign researchers with the rapid development of information technology and the theory of lifelong learning. In view of the inevitable shortcomings of traditional offline teaching and e-learning, an exploration of blended teaching pattern based on Hstar teaching platform and smart classroom is proposed which is a new education idea. In this paper, we select software engineering course and use Hstar teaching platform and smart classroom as the supporting environment, where students are allowed to choose the learning content according to their own plans and interests. Then we implement the blended formative evaluation method to evaluate learning effect and find that blended teaching pattern can break through the limitations of traditional education and e-learning. So we can forecast that blended learning will have a wide range of application and huge development potential in education.
摘要：
With the development of blended learning, it has been widely applied in teaching process. However, in the context of blended learning, tutor are not easy to acquire learning process of students and to make good use of learner' behaviors records. Therefore, they cannot timely receive feedback and effectively perform evaluation based on traditional indicators and method. To address this problem, this paper applies learning analytics and studies the learning behavior records in blended learning, i.e., integrating learning analytics to construct an evaluation mode through the evaluation theory, types, subject, and applies the mode to the specific teaching practice. This can provide guidance for tutors and help them make better effective and objective evaluation.
作者机构：
[Zhang, Zhaoli; Li, Zhifei; Chen, Yingying; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Hubei, Peoples R China.;[Liu, Hai] City Univ Hong Kong, Dept Mech & Biomed Engn, Kowloon, 83 Tat Chee Ave, Hong Kong, Peoples R China.
会议名称：
International Symposium on Educational Technology (ISET)
摘要：
Recently, the interactive learning environment has received more and more attention. In this paper, we introduce a cloud-terminal integration learning platform, which is developed by our group, and design a blended learning mode, which enables the platform to be used by the blended learning. Finally, we verify the effect of the platform using the course "Digital teaching system development".
摘要：
In recent years, most of the teaching service models in universities are linear in the exploration of big data in education, and people who use data are mainly researchers and policy makers, the process of data generation is static. Aiming at this problem, this paper proposes a data-driven feedback teaching service model. The model is characterized by: 1) the service mode is closed and nonlinearity; 2) the process of data generation is cyclic and dynamic; 3) the results of the data analysis are fed back to the participants in the teaching activities, intervening the process of generating data effectively. Finally, two examples are given to illustrate the effectiveness of the proposed model.
作者：
Yi, Baolin;Shen, Xiaoxuan*;Zhang, Zhaoli;Shu, Jiangbo;Liu, Hai
期刊：
PROCEEDINGS OF 2016 10TH INTERNATIONAL CONFERENCE ON SOFTWARE, KNOWLEDGE, INFORMATION MANAGEMENT & APPLICATIONS (SKIMA),2016年:298-303 ISSN：2373-082X
通讯作者：
Shen, Xiaoxuan
作者机构：
[Shen, Xiaoxuan; Zhang, Zhaoli; Yi, Baolin; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
通讯机构：
[Shen, Xiaoxuan] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
会议名称：
10th International Conference on Software, Knowledge, Information Management and Applications (SKIMA)
会议时间：
DEC 15-17, 2016
会议地点：
Chengdu, PEOPLES R CHINA
会议主办单位：
[Yi, Baolin;Shen, Xiaoxuan;Zhang, Zhaoli;Shu, Jiangbo;Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
会议论文集名称：
International Conference on Software Knowledge Information Management and Applications
关键词：
deep learning recommendation model;side information;Huber function;movie recommendation
摘要：
Automatic recommendation has become a popular research field: it allows the user to discover items that match their tastes. In this paper, we proposed an expanded autoencoder recommendation framework. The stacked autoencoders model is employed to extract the feature of input then reconstitution the input to do the recommendation. Then the side information of items and users is blended in the framework and the Huber function based regularization is used to improve the recommendation performance. The proposed recommendation framework is applied on the movie recommendation. Experimental results on a public database in terms of quantitative assessment show significant improvements over conventional methods.
期刊：
FIFTH INTERNATIONAL CONFERENCE ON EDUCATIONAL INNOVATION THROUGH TECHNOLOGY (EITT 2016),2016年:91-95
通讯作者：
Liu, Hai
作者机构：
[Li, Zhenhua; Cao, Taihe; Zhang, Zhaoli; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Liu, Hai] Cent China Normal Univ, Collaborat & Innovat Ctr Educ Technol, Wuhan 430079, Peoples R China.
通讯机构：
[Liu, Hai] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;Cent China Normal Univ, Collaborat & Innovat Ctr Educ Technol, Wuhan 430079, Peoples R China.
会议名称：
5th International Conference on Educational Innovation through Technology (EITT)
会议时间：
SEP 22-24, 2016
会议地点：
Tainan, TAIWAN
会议主办单位：
[Zhang, Zhaoli;Cao, Taihe;Liu, Hai;Shu, Jiangbo;Li, Zhenhua] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.^[Liu, Hai] Cent China Normal Univ, Collaborat & Innovat Ctr Educ Technol, Wuhan 430079, Peoples R China.
摘要：
In this paper, we present an infrared spectroscopy computer-assisted learning system (IRSCAL) using the computer as an interactive partner in problem solving activities. The software is designed to help the student with solving problems of their own choice, or those assigned by an instructor. It can be used as a tool to infrared spectroscopy learning, spectrum recognition training, optical data processing, and to give advice upon request without actually solving the problem itself. It includes an interactive interface, a spectrum simulator for graphical display of students' spectrum, a database which contains data on typical bands of chemical groups. A sample of fifty-five freshmen in college of chemistry in Central China Normal University completed a range of elementary school chemical problems.
摘要：
Automatic learning resources recommendation has become an increasingly relevant problem: it allows students to discover new learning resources that matches their tastes, and enables e-learning system to target their learning resources to the right students. In this paper, we propose an automatic learning resources recommendation algorithm based on convolutional neural network (CNN). The CNN can be used to predict the latent factors from the text information. To train the CNN, its input and output should be solved firstly. For its input, the language model is employed. For its output, we propose the latent factor model, which is regularized by L1-norm. Furthermore, the split Bregman iteration method is introduced to solve the model. The major novelty of the proposed recommendation algorithm is that a new CNN is constructed to make personalized recommendations. Experimental results on public database in terms of quantitative assessment show significant improvements over conventional methods. Especially, it can also work well when the existing recommendation algorithms suffer from the cold-start problem.
作者机构：
[Li, Zhenhua; Liu, Tingting; Cao, Taihe; Zhang, Zhaoli; Shu, Jiangbo] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.;[Li, Zhenhua] China West Normal Univ, Network Ctr, Nanchong 637000, Peoples R China.
会议名称：
5th International Conference on Educational Innovation through Technology (EITT)
会议时间：
SEP 22-24, 2016
会议地点：
Tainan, TAIWAN
会议主办单位：
[Li, Zhenhua;Zhang, Zhaoli;Liu, Tingting;Shu, Jiangbo;Cao, Taihe] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.^[Li, Zhenhua] China West Normal Univ, Network Ctr, Nanchong 637000, Peoples R China.
关键词：
Resource library;Reusable;Multi-granularity;Digital content service
摘要：
Construction of educational digital resources database is the core part of online education, and plays an important role in the development of education. In this paper, the construction of the digital resource library of Central China Normal University is introduced in detail from the technical point of view. At last, through the analysis of the survey results of the use of the resource library, this paper reveals the problems existing in the construction of the resource base.
摘要：
Passive millimeter wave imaging often suffers from issues such as low resolution, noise, and blurring. In this study, a blind image restoration method for the passive millimeter-wave images (PMMW) is proposed. The purpose of the proposed method is to simultaneously solve the point spread function (PSF) and restoration image. In this method, the data fidelity item is constructed based on Gaussian noise assuming, and the regularization item is constructed as the hyper-Laplace function parallel to x parallel to(0.6), which is fitted according to the high-resolution PMMW images. Moreover, a data-selected matrix is proposed to select the regions that are helpful for estimating the accurate PSF. The proposed method has been applied to simulated and real PMMW image experiments. Comparative results demonstrate that the proposed method significantly outperforms the state-of-the-art deblurring methods on both qualitative and quantitative assessments. The proposed method improves the resolution of the PMMW image and makes it more preferable for object recognition. (C) 2016 Elsevier Inc. All rights reserved.
摘要：
In this paper, we study the public elementary course "software engineering" which is based on the StarC platform. StarC is a teaching service platform developed by Central China Normal University. It is one part of national education cloud platform. This paper reports on the relationships between students' patterns of engagement and their course performance. The results indicate that students' participation is positively correlated with their final academic performance. So is students' effective learning time with their final performance. By using questionnaire, interview and results comparison, we found that the cloud classroom teaching is better than the traditional classroom teaching in the aspects of student's participation, satisfaction and learning gain.
作者机构：
[Wu, Liang; Zhang, Jianfeng; Wan, Beibei; Zhang, Zhaoli; Shu, Jiangbo; Liu, Hai] Cent China Normal Univ, Natl Engn Ctr E Learning, Wuhan, Peoples R China.
会议名称：
International Symposium on Educational Technology (ISET)
会议时间：
JUL 19-21, 2016
会议地点：
Peking Univ, Beijing, PEOPLES R CHINA
会议主办单位：
Peking Univ
关键词：
big data;blended learning;process evaluation
摘要：
With the development of information technology, the application of big data in the field of education has been deepened, and blended learning has been popularized in teaching process. In blended learning, teacher can't remember every student in the process of learning in all details, resulting in methods of emotional subjective evaluation can only be used on the evaluation process of teachers to students. Without doubt it cannot describe their real behavior performance objectively and fairly. In view of this problem, this paper studies personal big data of blended learning, through the establishment of a large data model of personal learning, and analysis of these data, so as to provide a basis for objective evaluation. According to the data of teaching in software engineering course as an example, through the analysis of classroom video of the teaching process, gets the expression and action of learners in class in usual, and sees it as a factor of reflection of seriousness degree of the students listening in class, and it can reflect the attitude of students in a sense. This experiment shows that learning process of big data have a relatively objective evaluation to students, it can also show students' behavior history, so as to spur students to improve these behaviors consciously.
摘要：
In view of the problem of the low efficiency in traditional classroom teaching due to the limitation in time and space, an exploration which combines real classroom with virtual classroom in hybrid learning was proposed. We chose the teaching of a software engineering course and used starC as the teaching support tool for analysis. In our study, the teaching process was divided into several teaching units, and each teaching unit was further divided into several activity units. The content was organized in the form of topicalities, where students are allowed to choose the learning content according to their study plans and preferences. Through the questionnaire survey which includes the indicators of participation and satisfaction among the students on both traditional learning and hybrid learning, it is found that the students on hybrid learning have higher participation and satisfaction than that on traditional learning. This indicated that hybrid learning could effectively improve teaching effectiveness.
作者机构：
[Liu, Tingting; Zhang, Zhaoli; Liu, Sanya; Shu, Jiangbo; Zhang, ZL; Liu, SY; Liu, Hai] Cent China Normal Univ, Natl Engn Res Ctr Learning, Wuhan 430079, Peoples R China.
会议名称：
IEEE Signal Processing and Signal Processing Education Workshop (SP/SPE)
会议时间：
AUG 09-12, 2015
会议地点：
Salt Lake, UT
会议主办单位：
[Liu, Hai;Zhang, Zhaoli;Liu, Sanya;Shu, Jiangbo;Liu, Tingting] Cent China Normal Univ, Natl Engn Res Ctr Learning, Wuhan 430079, Peoples R China.
关键词：
Optics data processing;Signal processing;Blind deconvolution;Infrared spectroscopy
摘要：
In this paper, we will propose a new framework which can estimate the desired signal and the instrument response function (IRF) simultaneously from the degraded spectral signal. Firstly, the spectral signal is considered as a distribution, thus, new entropy (called differential-entropy, DE) is defined to measure the distribution with a uniform distribution, which allows negative value existing. Moreover, the IRF is parametrically modeled as a Lorentzian function. Comparative results manifest that the proposed method outperforms the conventional methods on peak narrowing and noise suppression. The deconvolution IR spectrum is more convenient for extracting the spectral feature and interpreting the unknown chemical mixtures.
