作者:
Kadhim, Dheyaa Jasim*;Yu, Xinguo(余新国);Jabbar, Saba Qasim;Li, Yu;Luo, Wenxing
期刊:
Lecture Notes in Computer Science,2018年10749:150-161 ISSN:0302-9743
通讯作者:
Kadhim, Dheyaa Jasim
作者机构:
[Yu, Xinguo; Kadhim, Dheyaa Jasim] CCNU, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Li, Yu; Jabbar, Saba Qasim] Huazhong Univ Sci & Technol, Wuhan, Hubei, Peoples R China.;[Luo, Wenxing] GuiZhou Vocat Technol Coll Elect & Informat, Kaili, Peoples R China.
通讯机构:
[Kadhim, Dheyaa Jasim] C;CCNU, 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:
[Kadhim, Dheyaa Jasim;Yu, Xinguo] CCNU, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.^[Jabbar, Saba Qasim;Li, Yu] Huazhong Univ Sci & Technol, Wuhan, Hubei, Peoples R China.^[Luo, Wenxing] GuiZhou Vocat Technol Coll Elect & Informat, Kaili, Peoples R China.
会议论文集名称:
Lecture Notes in Computer Science
关键词:
Cloud computing;Live video streaming;QoE management;DASH
摘要:
Live video streaming process consumes very large data storage and takes very long time, so it requires big data storage and computing infrastructures for implementation. Accordingly, the use of cloud computing is becoming a common practice solution for streaming service providers. This work proposes a new scheme to manage the quality of experience (QoE) for live video streaming viewers, aimed directly at cloud computing environments. This scheme proposes to make optimal usage of cloud computing resources and quality services to meet the quality of experience (QoE) requirements of the live video streaming viewers without considering another cost to the video service provider. We examine the user’s quality of experience using dynamic adaptive streaming HTTP (DASH) technique. Then, we present and derive three important performance indicators which effect on viewer’s QoE namely: startup delay, deadline time (time nulling including null duration and number of null time), and bit rate level variations. The simulation results show that the tested indication parameters do not need to access the service providers in order to manage QoE of viewers neither do not need to insert them into the video streaming client software to determine the user experience in live video streaming. So, we believe that our proposed scheme and the performance indicators that studied in our work can serve as useful and light-weight tools for live video streaming service provider to monitor and control their quality of services.
作者:
Yu, Xinguo(余新国);Lyu, Xiaopan*;Xiang, Lei;Leong, Hon Wai
期刊:
Lecture Notes in Computer Science,2018年10736:457-466 ISSN:0302-9743
通讯作者:
Lyu, Xiaopan
作者机构:
[Yu, Xinguo; Lyu, Xiaopan; Xiang, Lei] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Leong, Hon Wai] Natl Univ Singapore, Dept Comp Sci, Singapore, Singapore.
通讯机构:
[Lyu, Xiaopan] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
会议名称:
18th Pacific-Rim Conference on Multimedia (PCM)
会议时间:
SEP 28-29, 2017
会议地点:
Harbin, PEOPLES R CHINA
会议主办单位:
[Yu, Xinguo;Lyu, Xiaopan;Xiang, Lei] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.^[Leong, Hon Wai] Natl Univ Singapore, Dept Comp Sci, Singapore, Singapore.
摘要:
This paper presents an algorithm for reading two digital video clocks of broadcast basketball videos by using context-aware pixel periodicity method and deep learning technique. Reading two digital video clocks is a very challenge problem as a difficulty special case of reading video text. The first challenge task is the clock digit localization. The existing pixel periodicity is a very good method for localizing second-digit place if a single clock is in video, but it is not applicable to localizing two second-digit places. This paper proposes a context-aware pixel periodicity method to identify the second-pixels of each clock based on the domain knowledge of digital video clocks. The second challenge task is clock-digit recognition. For this task, the CNN-based procedures are proposed to recognize clock digits. The experimental results show that the proposed algorithm can achieve 100% of accuracy in both localization and recognition for two clocks at very low computational cost by using very short input clips.
作者机构:
[Yu, Xinguo; Su, Yao; Sun, Chao] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
通讯机构:
[Yu, Xinguo] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, 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:
[Sun, Chao;Su, Yao;Yu, Xinguo] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.
会议论文集名称:
Lecture Notes in Computer Science
摘要:
Hypergeometric distribution is one of the most important mathematical models in probabilistic subjects, and also an integral part of the intelligent tutoring system based on automatic machine solving. In this paper, we propose a set of solutions to automatically solve the Hypergeometric distribution problems. Our method combines the syntactic and semantic information of the subject, establishes the matching rule between the topic narration and the type template, and implement the problem solving by establishing the solution formula corresponding to the topic, as well as extracting and complementing the corresponding problem data. Experiments conducted on a dataset which collected from the Internet and College Entrance Examination questions over the years demonstrate the feasibility of our method.
期刊:
Lecture Notes in Computer Science,2018年10799:396-409 ISSN:0302-9743
通讯作者:
Sun, Huihui
作者机构:
[Yu, Xinguo; Sun, Huihui; Sun, Chao] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Sun, Huihui] Huaibei Normal Univ, Comp Sci Sch, Huaibei, Peoples R China.
通讯机构:
[Sun, Huihui] C;[Sun, Huihui] H;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;Huaibei Normal Univ, Comp Sci Sch, Huaibei, 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:
[Sun, Huihui;Yu, Xinguo;Sun, Chao] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.^[Sun, Huihui] Huaibei Normal Univ, Comp Sci Sch, Huaibei, Peoples R China.
会议论文集名称:
Lecture Notes in Computer Science
关键词:
Structural line analysis;3D indoor reconstruction;Plucker line
期刊:
International Journal of Innovative Computing, Information and Control,2018年14(1):83-98 ISSN:1349-4198
作者机构:
[Yu, Xinguo; Gan, Wenbin] National Engineering Research Center for E-Learning, Central China Normal University, No. 152, Luoyu Road, Wuhan, 430079, China
期刊:
Lecture Notes in Computer Science,2018年10749:366-381 ISSN:0302-9743
通讯作者:
Gan, Wenbin
作者机构:
[Yu, Xinguo; Gan, Wenbin; He, Bin; Wang, Mingshu; Sun, Chao] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
通讯机构:
[Gan, Wenbin] 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:
[Gan, Wenbin;Yu, Xinguo;Sun, Chao;He, Bin;Wang, Mingshu] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
会议论文集名称:
Lecture Notes in Computer Science
关键词:
Plane geometry problem understanding;Geometric relation extraction;S-2 model;Visually presentation;Textual information extraction;Visual information extraction
摘要:
Speech interaction is a prominent interaction technology in educational robot, and educational robot with speech interaction can have a more harmonic and natural way of interaction. In some specific application scenarios such as education, the performance of speech recognition is not satisfactory due to the wide range of vocabularies and poor network. This paper trains the language model with professional vocabulary in the specific subject and establishes the corresponding phonetic dictionary in speech recognition based on Sphinx, and combines with speech synthesis based on Ekho to implement the speech interaction of educational robot in the offline state, and designs the relevant application of speech interaction about the teaching scenario of Chinese ancient poetry. The experiment demonstrates that the system designed and implemented can meet the demand of practical application of speech interaction in specific subject, and achieve the purpose of enhancing the student's learning experience and improving the learning effect.
摘要:
The development of a guide robot with explanatory features has always been a subject of concern. Based on NAO, a guide robot with Chinese and English voice recognition and expression is implemented, which enables visitors to interact with the robot in the exhibition hall. This paper designs interaction scheme, using the exhibition hall of the project team as experimental environment, focusing on how to make robots provide explanation service, especially on understanding the questions from visitors and the emotional expression of answers to visitors. This paper uses existing speech recognition methods and designs the explanation content and the dialog form, which allows the robot to recognize the questions from visitors, and combine speech representation with robot body movements so that the robot can express emotions to a certain extent. Finally, this paper verified the robot in the plane exhibition hall specializing in foreign propaganda, and the robot is able to perform their daily work on explanation, and greatly enhance the interactive experience of visitors.
摘要:
This paper presents a multimodal approach to predict affective dimensions, that makes full use of features from audio. video. Electrodermal Activity (EDA) and Electrocardiogram (ECG) using three regression techniques such as support vector regression (SVR). partial least squares regression (PLS), and a deep bidirectional long short-term memory recurrent neural network (DBLSTM-RNN) regression. Each of the three regression techniques performs multimodal affective dimension prediction followed by a fusion of different models on features of four modalities using a support vector regression. A support vector regression is also applied for a final fusion of the three regression systems. Experiments show that our proposed approach obtains promising results on the AVEC 2015 benchmark dataset for prediction of multimodal affective dimensions. For the development set, the concordance correlation coefficient (CCC) achieves results of 0.856 for arousal and 0.720 for valence, which increases 3.88 % and 4.66 % of the top-performer of AVEC 2015 in arousal and valence, respectively.
期刊:
2017 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC 2017),2017年:1368-1372 ISSN:2309-9402
通讯作者:
Ding, Wan
作者机构:
[Yu, Xinguo; Ding, Wan] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.;[Huang, Dong-Yan] Inst Infocomm Res, Human Language Technol Dept, Singapore, Singapore.;[Chen, Zhuo; Lin, Weisi] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore.
通讯机构:
[Ding, Wan] C;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.
会议名称:
9th Annual Summit and Conference of the Asia-Pacific-Signal-and-Information-Processing-Association (APSIPA ASC)
会议时间:
DEC 12-15, 2017
会议地点:
Kuala Lumpur, MALAYSIA
会议主办单位:
[Ding, Wan;Yu, Xinguo] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.^[Huang, Dong-Yan] Inst Infocomm Res, Human Language Technol Dept, Singapore, Singapore.^[Chen, Zhuo;Lin, Weisi] Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore, Singapore.
会议论文集名称:
Asia-Pacific Signal and Information Processing Association Annual Summit and Conference
摘要:
Positive samples of facial actions are much fewer than negative samples in natural conditions. The highly imbalanced class-distributions may cause very slow rate of convergence of error when using neural networks for facial action recognition. Traditional methods tackle this class-imbalance problem by changing data distributions, which is challenging for preventing the loss of useful information. In this paper we tackle this problem by using very deep (>10 layers) architectures to increase the chance that network training has acceptable rate of convergence using highly imbalanced data sets. Experimental results on EmotioNet Challenge data set show that the error rates of very deep covolutional networks converge to 40% after 90 epochs while shallower networks only converge to 60%. The results also show that very deep network outperforms shallower network by 0.2 on accuracy score. The proposed neural networks won the first place of the first track in the automatic detection of action units (AUs) of EmotioNet Challenge.
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.;[Chen, Zhanwen; Meng, Hao] Cent China Normal Univ, Wollongong Joint Inst, Wuhan, Hubei, Peoples R China.
会议名称:
2nd International Conference on Robotics and Automation Engineering (ICRAE)
会议时间:
DEC 29-31, 2017
会议地点:
Shanghai, PEOPLES R CHINA
会议主办单位:
[He, Bin;Xia, Meng;Yu, Xinguo;Jian, Pengpeng] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Hubei, Peoples R China.^[Meng, Hao;Chen, Zhanwen] Cent China Normal Univ, Wollongong Joint Inst, Wuhan, Hubei, Peoples R China.
摘要:
The educational robotics is a novel technology for preschooler's companion and can be used for lower level education. This paper presents an AI-based robot system for achieving educational aims, such as metacognition tutoring and geometrical thinking training, with characteristics of contextual teaching by mining knowledge from the real world directly. For metacognition tutoring in our system, objects in real world are detected and a set of learning materials associated with the objects is presented for learners. For example, when a cat is detected, the robot will teach learners to pronounce the "Cat" in different languages, and more knowledge about cat will be pushed to the learners. For geometrical thinking training, an automatic questioning-and-answering section is employed to engage the learner to think, which is carried by a voice interaction between learners and robots. In our experiment, a set of specific object images are captured to validate the feasibility and efficiency of the proposed system. Our study indicated that the proposed system succeeded in captivating the children and parents in maximizing the children's desire to explore.
关键词:
Iterated Local Search;Packing;Tabu Search;Variable Neighborhood Descent
摘要:
This paper presents an Iterated Tabu Search and Variable Neighborhood Descent (ITS-VND) algorithm for packing unequal circles into a circular container (PUCC). The algorithm adapts the Tabu Search procedure of Iterated Tabu Search algorithms and proposes a Tabu Search and Variable Neighborhood Descent (TS-VND) procedure. We observe there are strong complementarities between the small circles and the large vacant places, and propose the insert neighborhood to match up the small circles with the large vacant places. Although the insert neighborhood is inefficient and time-consuming, it is an important supplement to the classic swap neighborhood as it could arrange the small circles properly. Predicated on these features, we employ the insert neighborhood only at chosen local minima of the swap neighborhood that shows promise for an improvement. The traditional Tabu Search procedure is then transformed into a hybrid procedure composed of two alternative parts, namely Variable Neighborhood Descent and Tabu Search respectively. Besides this reformed procedure, ITS-VND also incorporates other new features, such as an adaptive evaluation function, a novel method for accelerating the neighborhood exploration, and the "collision accidents" criterion for evaluating how intensively the area near the current solution has been explored. The computational results on three well established benchmark sets show that the proposed algorithm not only has a good discovery capability but also can provide good results within a reasonable time. For a total of 84 benchmark instances, the proposed algorithm improves the best-known results on 23 instances, matches 60, and only misses one.
期刊:
Lecture Notes in Computer Science,2016年9431 ISSN:0302-9743
作者机构:
[Brä unl, Thomas] The University of Western Australia Crawley, Perth, WA, Australia;[McCane, Brendan] University of Otago, Dunedin, New Zealand;Centro de Investigació,n en Matematicas A.C, Guanajuato, Mexico;Central China Normal University, Wuhan, Hubei, China
摘要:
The extraction of implicit quantity relations is one of critical steps of building the machine solver for solving arithmetic word problems. Extracting implicit quantity relations is a challenge research problem as partial problem of natural language understanding, which has no mature solution method. To address this challenge, the existing work in the extraction of quantity relations mainly relies on creating problem solving framework and extracting system of linear equations. However, these existing methods can solve the relatively simple problems due to they have no methods to extract implicit quality relations. This paper proposes a novel method for extracting implicit quantity relations, which is achieved by the process of Chinese phrase parse, classification and instantiation method of required general implicit quantity relations with semantic models. A set of experiments were conducted to classify the arithmetic word problems, and an example was taken to illustrate the proposed method of identifying general implicit quantity relations. The experimental results demonstrate that the proposed method is effective in extracting implicit quantity relations.
期刊:
Multimedia Tools and Applications,2016年75(17):10357-10381 ISSN:1380-7501
通讯作者:
Cheng, Jun
作者机构:
[Yu, Xinguo; Song, Wu; Cheng, Jun] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Cheng, Jun] Hubei Polytech Univ, Comp Sch, Huangshi, Peoples R China.;[Wu, Shiqian] Wuhan Univ Sci & Technol, Coll Machinery & Automat, Wuhan, Peoples R China.;[Song, Wu] Hunan Univ Arts & Sci, Changde, Peoples R China.
通讯机构:
[Cheng, Jun] C;[Cheng, Jun] H;Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;Hubei Polytech Univ, Comp Sch, Huangshi, Peoples R China.
关键词:
Video panorama surveillance;Timestamp localization;Timestamp removal;Timestamp plantation;PTZ motion;Color correction
摘要:
This paper presents a framework to automatically replant timestamps for panorama video surveillance. The system mainly comprises six modules: 1) timestamp localization; 2) image registration; 3) timestamp pixel recovery; 4) color correction; 5) timestamp recognition; and 6) panorama video generation. The proposed framework first develops a method to localize the timestamp by employing the method of locating digital video clocks. Then, a fast and novel method is developed to recover the pixels covered by timestamps. The proposed method has fast speed because a fast image translation estimation procedure is introduced based on the PTZ camera motion estimation and global histogram-based image matching. Moreover, a hybrid color correction method by combining region matching with the gamma correction and the linear correction is presented. To plant timestamps accurately, a timestamp recognition procedure is developed by adopting the time recognition method for digit video clocks. Experimental results show that the proposed approach can accurately remove timestamps in real time, the recovered frames are visually consistent with the real scene, and the performance of color correction for panorama video is visually acceptable.
作者:
Cheng, Jun;Yu, Xinguo(余新国);Liao, Shengbin;Zhao, Gang
期刊:
ACM International Conference Proceeding Series,2015年2015-August:244-247
作者机构:
[Yu, Xinguo; Liao, Shengbin; Zhao, Gang] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China;Computer School, Hubei Polytechnic University, Huangshi, China;[Cheng, Jun] National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China<&wdkj&>Computer School, Hubei Polytechnic University, Huangshi, China
会议名称:
7th International Conference on Internet Multimedia Computing and Service, ICIMCS 2015
作者机构:
[Yu, Xinguo; Wu, Shuang] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
会议名称:
2015 International Conference of Educational Innovation Through Technology - (EITT)
会议时间:
OCT 16-18, 2015
会议地点:
Wuhan, PEOPLES R CHINA
会议主办单位:
[Yu, Xinguo;Wu, Shuang] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan 430079, Peoples R China.
关键词:
big data;data mining;educational technology;personalized recommendation;performance prediction
摘要:
The availability of big data sets on the different learning modes has stimulated the applications of big data technology in education. This article is to introduce relevant application examples of education data mining to show how big data in education help to solve education issues. Firstly it lists the groups of target users and participants involved in education data mining, and the objectives to use data information of each group. It then goes on to illustrate the groups and their objectives further by given examples and finally conclude how big data help to solve education issues through reaching the objective of each group. The examples show that for students big data can generate personalized activities and offer academic advising, for teachers big data can reveal students' characteristics and predict future performance and offer assistance, for educational organizations big data can make scientific decisions.