Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085494
Ping Zhong, Hugang Gu, Pengfeng Li, Min Xiao, Xiaofeng Du
More and more personal information is stored in the smart phone, especially including the photos and pictures. It is important to manage these numbers of rapid growth photos in smart phone. In this paper, we develop an intelligent photo management system used for android phone, namely i-Memory. The key function mainly includes the basic function of classify based on time and location, the advanced function of quickly searching and intelligent classification based on face recognition. The core technology of face recognition consists of three steps: face detection, face comparison and face searching. Experiment shows that the i-Memory works well and is efficient for mobile photo management.
{"title":"i-Memory: An intelligence Android-based photo management system","authors":"Ping Zhong, Hugang Gu, Pengfeng Li, Min Xiao, Xiaofeng Du","doi":"10.1109/ICCSE.2017.8085494","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085494","url":null,"abstract":"More and more personal information is stored in the smart phone, especially including the photos and pictures. It is important to manage these numbers of rapid growth photos in smart phone. In this paper, we develop an intelligent photo management system used for android phone, namely i-Memory. The key function mainly includes the basic function of classify based on time and location, the advanced function of quickly searching and intelligent classification based on face recognition. The core technology of face recognition consists of three steps: face detection, face comparison and face searching. Experiment shows that the i-Memory works well and is efficient for mobile photo management.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126517616","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085556
Lin Mingyu, Ju Jianping, Zhu Yi, Zhan Cuili
Big data as a current hotspot technology, has obvious impact on the professional curriculum in colleges and universities, it is an inevitable trend that it prompts the curriculum reform in colleges and universities. This paper expounds the problems of the database curriculum of computer major faced in big data era, and explores the teaching reform of database curriculum of computer major from two aspects of theory teaching and experimental teaching.
{"title":"Research on the teaching reform of database curriculum major in computer in big data era","authors":"Lin Mingyu, Ju Jianping, Zhu Yi, Zhan Cuili","doi":"10.1109/ICCSE.2017.8085556","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085556","url":null,"abstract":"Big data as a current hotspot technology, has obvious impact on the professional curriculum in colleges and universities, it is an inevitable trend that it prompts the curriculum reform in colleges and universities. This paper expounds the problems of the database curriculum of computer major faced in big data era, and explores the teaching reform of database curriculum of computer major from two aspects of theory teaching and experimental teaching.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126462255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085515
Da Huo, Yufeng Chen, Fengxia Li, Zhengchao Lei
We proposed a novel method of feature extraction for multi-modal images called modality-convolution. It extracts both the intra- and inter-modality information. Whats more, it completes the data fusion at pixel-level so that the complementarity of information contained in multi-modal data is fully utilized. Based on the modality-convolution, we describe a modality-CNN for multi-modal gesture recognition. For extracting the features in RGB-D images, the modality-CNN is adopted in the gesture recognition framework. The framework use DBN to present the skeleton data. Then, the probability obtained by the two networks are fused and put into the HMM to carry out dynamic gestures classification. We use the Jaccar Index to calculate the accuracy of gesture recognition. A comparative experiment on ChaLearn LAP 2014 gesture datasets shows that the modality-convolution is able to extract the inter- and intra-modality information effectively, which is helpful to improve the accuracy.
我们提出了一种新的多模态图像特征提取方法，称为模态卷积。它同时提取模态内和模态间的信息。并在像素级完成数据融合，充分利用多模态数据所含信息的互补性。在模态卷积的基础上，提出了一种用于多模态手势识别的模态cnn。为了提取RGB-D图像中的特征，在手势识别框架中采用了模态- cnn。该框架使用DBN来表示骨架数据。然后，将两个网络得到的概率融合到HMM中进行动态手势分类。我们使用Jaccar指数来计算手势识别的准确性。在ChaLearn LAP 2014手势数据集上的对比实验表明，模态卷积能够有效地提取模态间和模态内信息，有助于提高识别精度。
{"title":"Modality-convolutions: Multi-modal gesture recognition based on convolutional neural network","authors":"Da Huo, Yufeng Chen, Fengxia Li, Zhengchao Lei","doi":"10.1109/ICCSE.2017.8085515","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085515","url":null,"abstract":"We proposed a novel method of feature extraction for multi-modal images called modality-convolution. It extracts both the intra- and inter-modality information. Whats more, it completes the data fusion at pixel-level so that the complementarity of information contained in multi-modal data is fully utilized. Based on the modality-convolution, we describe a modality-CNN for multi-modal gesture recognition. For extracting the features in RGB-D images, the modality-CNN is adopted in the gesture recognition framework. The framework use DBN to present the skeleton data. Then, the probability obtained by the two networks are fused and put into the HMM to carry out dynamic gestures classification. We use the Jaccar Index to calculate the accuracy of gesture recognition. A comparative experiment on ChaLearn LAP 2014 gesture datasets shows that the modality-convolution is able to extract the inter- and intra-modality information effectively, which is helpful to improve the accuracy.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125729993","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085583
Bowei Hong, Zhiqiang Wei, Yongquan Yang
High dropout rate of MOOC is criticized while a dramatically increasing number of learners are appealed to these online learning platforms. Various works have been done on analysis and prediction of dropout. Machine learning techniques are widely applied to this field. However, a single classifier may not always perform reliable for predictions. In this work, we study dropout prediction for MOOC. A technique is proposed to predict dropouts using learning activity information of learners. We applied a two-layer cascading classifier with a combination of three different machine learning classifiers — Random Forest (RF), Support Vector Machine (SVM), and MultiNomial Logistic Regression (MLR) for prediction. Experimental results indicate that the technique is promising in predicting dropouts with achieving 97% precision.
{"title":"Discovering learning behavior patterns to predict dropout in MOOC","authors":"Bowei Hong, Zhiqiang Wei, Yongquan Yang","doi":"10.1109/ICCSE.2017.8085583","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085583","url":null,"abstract":"High dropout rate of MOOC is criticized while a dramatically increasing number of learners are appealed to these online learning platforms. Various works have been done on analysis and prediction of dropout. Machine learning techniques are widely applied to this field. However, a single classifier may not always perform reliable for predictions. In this work, we study dropout prediction for MOOC. A technique is proposed to predict dropouts using learning activity information of learners. We applied a two-layer cascading classifier with a combination of three different machine learning classifiers — Random Forest (RF), Support Vector Machine (SVM), and MultiNomial Logistic Regression (MLR) for prediction. Experimental results indicate that the technique is promising in predicting dropouts with achieving 97% precision.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126556020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085601
Jiading Guo, Xingyu Xiao, P. Pan, Xiaotong Luo
Using machines to save manpower has always been the core concept of technological development. For some time, the process of replacing the brain has made great progress in the development of decision-making, such as identification, and has made a wide range of applications. The self-driving car as the representative of the intelligent robot has become a hot topic. Based on the scene of the use of small indoor service robots, this paper puts forward a kind of application scheme based on the combination of global visual localization and robot vision localization, and designs a set of management system suitable for catering service, so as to promote the further development of robot application.
{"title":"A design of multi-vision localization and navigation service robot system","authors":"Jiading Guo, Xingyu Xiao, P. Pan, Xiaotong Luo","doi":"10.1109/ICCSE.2017.8085601","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085601","url":null,"abstract":"Using machines to save manpower has always been the core concept of technological development. For some time, the process of replacing the brain has made great progress in the development of decision-making, such as identification, and has made a wide range of applications. The self-driving car as the representative of the intelligent robot has become a hot topic. Based on the scene of the use of small indoor service robots, this paper puts forward a kind of application scheme based on the combination of global visual localization and robot vision localization, and designs a set of management system suitable for catering service, so as to promote the further development of robot application.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128454304","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085464
M. Takada, M. Miyao, Fumiya Kinoshita, A. Sugiura, Kazuhiro Fujikake, H. Takada
The technology provides an enhanced visual experience with realistic scene portrayal, but is known to cause motion sickness when stereoscopic video clips of rotating or blurred images are viewed. Viewers complain of symptoms such as eye fatigue, nausea, and dizziness. The underlying cause of these symptoms has not been identified; therefore, an investigation to determine the mechanism for the motion sickness is necessary. Compared to the baseline test, the concentration of oxygenated hemoglobin in the occipital lobe increased significantly during a viewing for both background cases. The result is consistent with both visual recognition methods. Furthermore, for both background cases, the concentration in the upper occipital lobe significantly increased during peripheral viewing versus visual pursuit. Peripheral viewing might enhance the activity in the dorsal stream, which could serve as an indication to the mechanism causing 3D sickness.
{"title":"Changes in brain blood flow during stereoscopic video clips","authors":"M. Takada, M. Miyao, Fumiya Kinoshita, A. Sugiura, Kazuhiro Fujikake, H. Takada","doi":"10.1109/ICCSE.2017.8085464","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085464","url":null,"abstract":"The technology provides an enhanced visual experience with realistic scene portrayal, but is known to cause motion sickness when stereoscopic video clips of rotating or blurred images are viewed. Viewers complain of symptoms such as eye fatigue, nausea, and dizziness. The underlying cause of these symptoms has not been identified; therefore, an investigation to determine the mechanism for the motion sickness is necessary. Compared to the baseline test, the concentration of oxygenated hemoglobin in the occipital lobe increased significantly during a viewing for both background cases. The result is consistent with both visual recognition methods. Furthermore, for both background cases, the concentration in the upper occipital lobe significantly increased during peripheral viewing versus visual pursuit. Peripheral viewing might enhance the activity in the dorsal stream, which could serve as an indication to the mechanism causing 3D sickness.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130629959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085553
Dongdong Zhang, Lisheng Wang, Yuchen Guo
Digital Logic course and Computer Composition Principle course are important professional basic courses of computer major. In the traditional teaching mode, the experiments of these two hardware courses are mainly implemented to validate the theoretical knowledge by plugging wires in different experiment boxes, which leads to a lack of computer system design and development capability of computer major students. In this paper, we will present the integrated experiment design of these two courses of Tongji University, based on Xilinx Nexy4 development board for computer system capability training.
{"title":"Integrated experiment design of digital logic course and computer composition principle course","authors":"Dongdong Zhang, Lisheng Wang, Yuchen Guo","doi":"10.1109/ICCSE.2017.8085553","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085553","url":null,"abstract":"Digital Logic course and Computer Composition Principle course are important professional basic courses of computer major. In the traditional teaching mode, the experiments of these two hardware courses are mainly implemented to validate the theoretical knowledge by plugging wires in different experiment boxes, which leads to a lack of computer system design and development capability of computer major students. In this paper, we will present the integrated experiment design of these two courses of Tongji University, based on Xilinx Nexy4 development board for computer system capability training.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130553359","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085461
Yuyang Sun, Qingzhong Li
One difficulty of teaching in mathematics is to present abstract mathematical concepts or laws to students in a simple visual way to promote students' understanding and mastery. Traditionally mathematical teachers tried to explain abstract mathematical concepts and formulas by means of some simple teaching tools and some mathematical models presented by some mathematical software, such as Matlab, Mathematica, etc. As an integrated modern discipline, 3D printing has become more and more important in scientific research and technological developments. This paper intends to explore the close relationship between mathematics teaching and 3D printing technology, and propose a comprehensive programme of mathematical education based on the introduction of 3D printer manufacture, mathematical formula, 3D printing models, logo adding to 3D models, and 3D outcomes. This scenario can well solve the problem of visualization of abstract mathematical concepts. Teachers can easily explain complex mathematical expressions by the visual 3D tools. Students' learning interests of mathematics can be stimulated and their understanding abilities of space and graphics can be greatly enhanced by means of the real practice of mathematical 3D printing.
{"title":"The application of 3D printing in mathematics education","authors":"Yuyang Sun, Qingzhong Li","doi":"10.1109/ICCSE.2017.8085461","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085461","url":null,"abstract":"One difficulty of teaching in mathematics is to present abstract mathematical concepts or laws to students in a simple visual way to promote students' understanding and mastery. Traditionally mathematical teachers tried to explain abstract mathematical concepts and formulas by means of some simple teaching tools and some mathematical models presented by some mathematical software, such as Matlab, Mathematica, etc. As an integrated modern discipline, 3D printing has become more and more important in scientific research and technological developments. This paper intends to explore the close relationship between mathematics teaching and 3D printing technology, and propose a comprehensive programme of mathematical education based on the introduction of 3D printer manufacture, mathematical formula, 3D printing models, logo adding to 3D models, and 3D outcomes. This scenario can well solve the problem of visualization of abstract mathematical concepts. Teachers can easily explain complex mathematical expressions by the visual 3D tools. Students' learning interests of mathematics can be stimulated and their understanding abilities of space and graphics can be greatly enhanced by means of the real practice of mathematical 3D printing.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"261 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133716578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085554
Chen-zhi Guan
This paper puts forward a new flipped laboratory mode for the computer network experimental course. In this mode the experiment process is reformed and the experiment course is extended to outside of lab. Different experiment activities are designed according to different experiment categories. The paper presents that what constitute the framework of the mode, how the experiment activities of the mode are designed and the future research direction.
{"title":"Design of computer network experimental course in flipped laboratory mode","authors":"Chen-zhi Guan","doi":"10.1109/ICCSE.2017.8085554","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085554","url":null,"abstract":"This paper puts forward a new flipped laboratory mode for the computer network experimental course. In this mode the experiment process is reformed and the experiment course is extended to outside of lab. Different experiment activities are designed according to different experiment categories. The paper presents that what constitute the framework of the mode, how the experiment activities of the mode are designed and the future research direction.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129496898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2017-08-01DOI: 10.1109/ICCSE.2017.8085512
Kunhui Lin, Yangbin Pan, Xiaoli Wang, Mengsang Wu, Shiyu Su
In the GIS applications, massive mark point display has become a very important problem. Especially for the application in vehicle networking, high-load vehicle position moving increases the difficulty of the display problem. Many existing efforts have been taken on proposing aggregation algorithms for map mark points. However, all these works suffer from efficiency and scalability problems when we employ them to the application in the vehicle networking. In order to solve the problem of high efficiency map display of high load vehicle location data, this paper proposes the dynamic aggregation algorithm based on the administrative unit and the dynamic aggregation algorithm for K-means service mark point based on the administrative unit. Experimental results show that these two algorithms can make the location data of the vehicle highly efficient display on the map, and can achieve smooth interaction and friendly user experience.
{"title":"Effective dynamic algorithms for massive mark point aggregation display","authors":"Kunhui Lin, Yangbin Pan, Xiaoli Wang, Mengsang Wu, Shiyu Su","doi":"10.1109/ICCSE.2017.8085512","DOIUrl":"https://doi.org/10.1109/ICCSE.2017.8085512","url":null,"abstract":"In the GIS applications, massive mark point display has become a very important problem. Especially for the application in vehicle networking, high-load vehicle position moving increases the difficulty of the display problem. Many existing efforts have been taken on proposing aggregation algorithms for map mark points. However, all these works suffer from efficiency and scalability problems when we employ them to the application in the vehicle networking. In order to solve the problem of high efficiency map display of high load vehicle location data, this paper proposes the dynamic aggregation algorithm based on the administrative unit and the dynamic aggregation algorithm for K-means service mark point based on the administrative unit. Experimental results show that these two algorithms can make the location data of the vehicle highly efficient display on the map, and can achieve smooth interaction and friendly user experience.","PeriodicalId":256055,"journal":{"name":"2017 12th International Conference on Computer Science and Education (ICCSE)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130945102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：