摘要:
In today's Internet+ era, more and more e-learning platforms have appeared in the eyes of the public. The emergence of big data also points a development path for the learning platform. By analyzing the latest research progress and existing problems of many learning platforms, an online learning system with learning feedback is proposed. The system consists of a learning subsystem and a feedback subsystem. The learning subsystem is designed based on the basic needs of students. The feedback subsystem uses clustering algorithms and some calculation formulas to analyze student learning behaviors and display them in the summary report to the teacher. Teachers can adjust the teaching plan according to the summary report.
期刊:
2017 IEEE INTERNATIONAL CONFERENCE ON BIG DATA (BIG DATA),2017年:3882-3887 ISSN:2639-1589
通讯作者:
Hu, Xiaohua
作者机构:
[Jiang, Xingpeng; He, Tingting; Shen, Xianjun; Hu, Xiaohua; Gao, Li; Zhu, Xianchao] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.;[Shen, Xianjun; Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
通讯机构:
[Hu, Xiaohua] C;[Hu, Xiaohua] D;Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.;Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议名称:
IEEE International Conference on Big Data (IEEE Big Data)
会议时间:
DEC 11-14, 2017
会议地点:
Boston, MA
会议主办单位:
[Shen, Xianjun;Zhu, Xianchao;Jiang, Xingpeng;Gao, Li;He, Tingting;Hu, Xiaohua] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.^[Shen, Xianjun;Hu, Xiaohua] Drexel Univ, Coll Comp & Informat, Philadelphia, PA 19104 USA.
会议论文集名称:
IEEE International Conference on Big Data
摘要:
Known as phenotypic overlapping, some disease-related symptoms share a common pathological and physiological mechanism. Researchers attempt to visualize the phenotypic relationships between different human diseases from the perspective of machine learning, but traditional visualization methods may be subject to fundamental limitations of metric spaces. Multiple maps t-SNE regularization method, a probabilistic method for visualizing data points in multiple low-dimensional spaces has been proposed to address the limitation. However, the convergence speed is low when apply on the scale dataset. We use the RMSProp with Nesterov momentum method to learn the objective loss function. This method normalize the gradients by applying an exponential moving average of gradient magnitude for each iteration parameter and use Nesterov momentum to counterweigh too high velocities by "peeking ahead" actual objective values in the candidate search direction. This method convergent faster than the original method of convergence speed. Experiments results on several dataset shows that the proposed method outperforms the several version of mm-tSNE with or without regularization, as measured by the neighborhood preservation ratio and error rate. This suggests the modified mm-tSNE regularization can be applied directly in other domain including social, biological and microbiomic datasets.
摘要:
Theoretical soundness and technical feasibility of treating the problem of document ranking in IR as an inference problem in Bayesian Networks, was studied recently. A pilot framework was also proposed there. In this paper, we provide two implementations of the framework: BNBM25, the one based on BM25, and BNMATF, which is based on MATF, a recently proposed innovative ranking function. We empirically verify the effectiveness of these two implementations on several standard test collections. Positive, significant results are obtained. Potentials of this BN-based framework in addition to its verified effectiveness are also discussed. As a result of the study, we believe that the technique is promising, worthy of further analysis and application.
期刊:
2017 IEEE 24TH INTERNATIONAL CONFERENCE ON SOFTWARE ANALYSIS, EVOLUTION, AND REENGINEERING (SANER),2017年:272-282
通讯作者:
Liu, Jin;Yang, Zijiang
作者机构:
[Liu, Jin; Zhou, Pingyi] Wuhan Univ, Comp Sch, State Key Lab Software Engn, Wuhan, Peoples R China.;[Yang, Zijiang] Western Michigan Univ, Dept Comp Sci, Kalamazoo, MI 49008 USA.;[Zhou, Guangyou] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.
通讯机构:
[Liu, Jin; Yang, Zijiang] W;Wuhan Univ, Comp Sch, State Key Lab Software Engn, Wuhan, Peoples R China.;Western Michigan Univ, Dept Comp Sci, Kalamazoo, MI 49008 USA.
会议名称:
24th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)
会议时间:
FEB 20-24, 2017
会议地点:
Klagenfurt, AUSTRIA
会议主办单位:
[Zhou, Pingyi;Liu, Jin] Wuhan Univ, Comp Sch, State Key Lab Software Engn, Wuhan, Peoples R China.^[Yang, Zijiang] Western Michigan Univ, Dept Comp Sci, Kalamazoo, MI 49008 USA.^[Zhou, Guangyou] Cent China Normal Univ, Sch Comp, Wuhan, Peoples R China.
关键词:
Software Information Site;Tag Recomendation;Software Object;Multi-Classification
摘要:
Software developers can search, share and learn development experience, solutions, bug fixes and open source projects in software information sites such as StackOverflow and Freecode. Many software information sites rely on tags to classify their contents, i.e. software objects, in order to improve the performance and accuracy of various operations on the sites. The quality of tags thus has a significant impact on the usefulness of these sites. High quality tags are expected to be concise and can describe the most important features of the software objects. Unfortunately tagging is inherently an uncoordinated process. The choice of tags made by individual software developers is dependent not only on a developer's understanding of the software object but also on the developer's English skills and preferences. As a result, the number of different tags grows rapidly along with continuous addition of software objects. With thousands of different tags, many of which introduce noise, software objects become poorly classified. Such phenomenon affects negatively the speed and accuracy of developers' queries. In this paper, we propose a tool called TagMulRec to automatically recommend tags and classify software objects in evolving large-scale software information sites. Given a new software object, TagMulRec locates the software objects that are semantically similar to the new one and exploit their tags. We have evaluated TagMulRec on four software information sites, StackOverf low, AskUbuntu, AskDifferent and Freecode. According to our empirical study, TagMulRec is not only accurate but also scalable that can handle a large-scale software information site with millions of software objects and thousands of tags.
期刊:
Proceedings of SPIE - The International Society for Optical Engineering,2017年10225:1022510-null ISSN:0277-786X
通讯作者:
Jin, Cong
作者机构:
[Jin, Cong] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.;[Jin, Shu-Wei] Ecole Normale Super, 24 Rue Lhomond, F-75231 Paris 5, France.
通讯机构:
[Jin, Cong] C;Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.
会议名称:
8th International Conference on Graphic and Image Processing (ICGIP)
会议时间:
OCT 29-31, 2016
会议地点:
Tokyo, JAPAN
会议主办单位:
[Jin, Cong] Cent China Normal Univ, Sch Comp, Wuhan 430079, Peoples R China.^[Jin, Shu-Wei] Ecole Normale Super, 24 Rue Lhomond, F-75231 Paris 5, France.
摘要:
Multi-label image annotation (MIA) has been widely studied during recent years and many MIA schemes have been proposed. However, the most existing schemes are not satisfactory. In this paper, an improved multiple kernel learning (IMKL) method of support vector machine (SVM) is proposed to improve the classification accuracy of SVM, then a novel MIA scheme based on IMKL is presented, which uses the discriminant loss to control the number of top semantic labels, and the feature selection approach is also used for improving the performance of MIA. The experiment results show that proposed MIA scheme achieves higher the performance than the existing other MIA schemes, its performance is satisfactory for large image dataset.
摘要:
Emerging multimedia Multiview video systems consist of a dense deployment of multiple partial-overlapped wireless cameras, as well as some access points (Aps) and many wireless distributed relay nodes. Correlated views are captured by cameras followed being transmitted to destination by different Aps and networks links. Packet expiration of one camera flow may harm the whole task. To effectively integrate multiple viewpoints into a whole image, the correlated data rate and deadline of flows from multiple cameras are meaningful. There is a trade-off between data redundancy and time deadline among correlated multi-views subjecting to the constraints of limited buffer length. However, most researches in this field have not considered packet expiration suffering from varieties of delays after multipath. In this paper, we conduct this problem to optimally adjust multiple flows of viewpoints by exploiting spatial and temporal correlations among cameras to reduce delay variances. A global optimization algorithm based on joint rate-distortion and delay-distortion model is proposed. Simulation results show that quality of service for Multiview streaming can be improved by allocating suitable transmission rates among correlated cameras as well as appropriate playout deadline. The PSNR quality shows that better performance can be achieved compared with baseline policies.
作者机构:
[Yang Yan; Li Rong; Wang Sai] Cent China Normal Univ, Comp Sch, Wuhan 430079, Hubei, Peoples R China.
会议名称:
4th International Conference on Machinery, Materials and Computer (MACMC)
会议时间:
NOV 27-29, 2017
会议地点:
Xian, PEOPLES R CHINA
会议主办单位:
[Yang Yan;Wang Sai;Li Rong] Cent China Normal Univ, Comp Sch, Wuhan 430079, Hubei, Peoples R China.
会议论文集名称:
AER-Advances in Engineering Research
关键词:
service composition;optimization;cloud computing
摘要:
In cloud computing environment, service composition provides an effective way to implement a composite service. This paper investigates the issue of optimization of cloud service selection and composition in cloud environment. First, a cloud service filtrating and composition optimization index system is proposed, which can be used to characterize and differentiate services with similar functions and narrow the selection scope of candidate cloud services according to user requirements for subsequent composition. Then an optimization method is introduced for cloud service composition, which contains a service filtrating process based on evidential reasoning approach before the mathematical model is established and resolved. After that, the case study in a travel planning scenario is presented, which shows the proposed method can quickly reduce the solution space and improve the efficiency of service composition in cloud environment.
作者机构:
[Chen, Qiu-rui; Ou, Shi-rou; Zheng, Shi-jue; Xiao, Yao; Liu, Cong; Xu, Ya-jing] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
会议名称:
2017 2nd International Conference on Computational Modeling, Simulation and Applied Mathematics (CMSAM)
会议时间:
OCT 22-23, 2017
会议地点:
Beijing, PEOPLES R CHINA
会议主办单位:
[Xu, Ya-jing;Zheng, Shi-jue;Chen, Qiu-rui;Ou, Shi-rou;Liu, Cong;Xiao, Yao] Cent China Normal Univ, Sch Comp, Wuhan, Hubei, Peoples R China.
会议论文集名称:
DEStech Transactions on Computer Science and Engineering
关键词:
Virtual reality;Unity 3D;The belt and road;High-tech learning of Chinese words
摘要:
The convening of "The Belt and Road" summit makes the trade exchange between China and other countries more frequent. The language barrier becomes the greatest obstacle of popularizing China's high and new technology. The maturity of VR technology makes the ability of computer to create a real scene gradually improves, this passage introduces the design and implementation of a case about Chinese vocabulary learning based on mobile VR scene for people along "The Belt and Road" region. Using the related programming interfaces provided by Google VR SDK, this project program on the Unity 3D development platform. With the help of mobile terminals and low-cost VR devices, this project can make the people in "The Belt and Road" region learn high-tech Chinese vocabulary whenever and wherever possible and help them grasp the specific context of the use of specialized Chinese words quickly and efficiently.
摘要:
In this paper an algorithm of highlight extraction in soccer videos is proposed. Multimodal analysis of soccer field, moving objects, audio and caption is described. The highlight extraction model is built based on highlight levels. The experimental results show that our method based multimodal analysis is robust and efficient for video retrieval.
作者机构:
[Yang Yan; Yao Huaxiong; Wang Sai] Cent China Normal Univ, Comp Sch, Wuhan 430079, Hubei, Peoples R China.
会议名称:
4th International Conference on Machinery, Materials and Computer (MACMC)
会议时间:
NOV 27-29, 2017
会议地点:
Xian, PEOPLES R CHINA
会议主办单位:
[Yang Yan;Yao Huaxiong;Wang Sai] Cent China Normal Univ, Comp Sch, Wuhan 430079, Hubei, Peoples R China.
会议论文集名称:
AER-Advances in Engineering Research
关键词:
service composition;optimization;cloud service
摘要:
In this paper, we investigate the optimization problem of cloud service composition in cloud environment. First, the performance indexes for the optimization of cloud service composition is introduced. Then we propose an optimization method of cloud service composition, and establish a constrained multi-objective model for the optimization problem of cloud service composition which requires high reliability and low CPU and bandwidth occupancy. After that, a travel planning scenario is used to illustrate our approach to cloud service composition optimization. The case study shows the proposed method can effectively solve the problem of cloud service composition with high reliability and low resource consumption in cloud computing environment.