Pub Date : 2022-01-06DOI: 10.1109/ICEIT54416.2022.9690744
Bo Liu
This paper first analyzes the problems existing in the teaching of data mining course for undergraduates, then puts forward the application-oriented teaching ideas, designs the teaching content modules and the corresponding practice modules. Starting from the current teaching situation, it explores the reform of data mining course in order to cultivate more excellent data mining talents.
{"title":"Exploration on the Application-Oriented Teaching Mode of Data Mining Course for Undergraduates","authors":"Bo Liu","doi":"10.1109/ICEIT54416.2022.9690744","DOIUrl":"https://doi.org/10.1109/ICEIT54416.2022.9690744","url":null,"abstract":"This paper first analyzes the problems existing in the teaching of data mining course for undergraduates, then puts forward the application-oriented teaching ideas, designs the teaching content modules and the corresponding practice modules. Starting from the current teaching situation, it explores the reform of data mining course in order to cultivate more excellent data mining talents.","PeriodicalId":285571,"journal":{"name":"2022 11th International Conference on Educational and Information Technology (ICEIT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133012823","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}
As the number of service clusters in the OpenStack Cloud Platform, the work-load in the data center also increase, leading to node failures and performance issues. Therefore, managers need to know how the OpenStack cloud platform is operating and storing. This function can be realized through the monitoring system, and the monitoring can improve the quality of cloud computing services and also help to identify faults within the system. The purpose of this paper is to provide a solution for the monitoring of cloud computing services, that allows users and managers to optimize computing resources based on the changing business requirements within the cloud computing system. First of all, the functions of the OpenStack cloud monitoring system are introduced to mainly include the functions of OpenStack data collection, data processing, analysis, display, and alarm notification. Secondly, the system is mainly composed of components such as OpenStack-exporter, Libvirt, Ceph-exporter and Grafana. Finally, the existing issues of the Open-Stack cloud platform monitoring system are discussed.
{"title":"An Microservices-Based OpenStack Monitoring System","authors":"Hongbin Wang, Xiaoxuan Zhang, Zhiqiang Ma, Lei-Yi Li, Jing Gao","doi":"10.1109/ICEIT54416.2022.9690713","DOIUrl":"https://doi.org/10.1109/ICEIT54416.2022.9690713","url":null,"abstract":"As the number of service clusters in the OpenStack Cloud Platform, the work-load in the data center also increase, leading to node failures and performance issues. Therefore, managers need to know how the OpenStack cloud platform is operating and storing. This function can be realized through the monitoring system, and the monitoring can improve the quality of cloud computing services and also help to identify faults within the system. The purpose of this paper is to provide a solution for the monitoring of cloud computing services, that allows users and managers to optimize computing resources based on the changing business requirements within the cloud computing system. First of all, the functions of the OpenStack cloud monitoring system are introduced to mainly include the functions of OpenStack data collection, data processing, analysis, display, and alarm notification. Secondly, the system is mainly composed of components such as OpenStack-exporter, Libvirt, Ceph-exporter and Grafana. Finally, the existing issues of the Open-Stack cloud platform monitoring system are discussed.","PeriodicalId":285571,"journal":{"name":"2022 11th International Conference on Educational and Information Technology (ICEIT)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115639281","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 : 2022-01-06DOI: 10.1109/ICEIT54416.2022.9690763
Y. Chen, Lichen Zhang, Hailong Ma, Longjiang Guo
Online learning platforms such as MOOCs have been widely applied, on which students can learn online courses anytime and anywhere, and can also be divided into groups to conduct a learning task. Through team collaboration, students' comprehensive abilities can be improved, including learning, organization, communication, teamwork ability, etc. Reasonable grouping is the basis and focus of efficient collaborative learning. The existing intelligent optimization algorithms used to solve the combinatorial optimization problem of student grouping still have the limitation of being easy to fall into the local optimum and blind search. In response to this problem, we study an efficient student grouping algorithm for online collaborative learning in this paper. Firstly, we integrate an immune strategy into the Genetic Algorithm to form a new algorithm called Immune Genetic Algorithm (IGA). Secondly, we design a fitness function according to the grouping goal of “Heterogeneity within a group, homogeneity between groups”. Finally, we evaluate the performances of the algorithms through experiments based on a real data set. The grouping results show that compared with the Genetic Algorithm, the proposed Immune Genetic Algorithm improves the search efficiency and stability, and can get grouping results with better fitness value.
{"title":"Online Collaborative Learning Grouping Method Based on Immune Genetic Algorithm","authors":"Y. Chen, Lichen Zhang, Hailong Ma, Longjiang Guo","doi":"10.1109/ICEIT54416.2022.9690763","DOIUrl":"https://doi.org/10.1109/ICEIT54416.2022.9690763","url":null,"abstract":"Online learning platforms such as MOOCs have been widely applied, on which students can learn online courses anytime and anywhere, and can also be divided into groups to conduct a learning task. Through team collaboration, students' comprehensive abilities can be improved, including learning, organization, communication, teamwork ability, etc. Reasonable grouping is the basis and focus of efficient collaborative learning. The existing intelligent optimization algorithms used to solve the combinatorial optimization problem of student grouping still have the limitation of being easy to fall into the local optimum and blind search. In response to this problem, we study an efficient student grouping algorithm for online collaborative learning in this paper. Firstly, we integrate an immune strategy into the Genetic Algorithm to form a new algorithm called Immune Genetic Algorithm (IGA). Secondly, we design a fitness function according to the grouping goal of “Heterogeneity within a group, homogeneity between groups”. Finally, we evaluate the performances of the algorithms through experiments based on a real data set. The grouping results show that compared with the Genetic Algorithm, the proposed Immune Genetic Algorithm improves the search efficiency and stability, and can get grouping results with better fitness value.","PeriodicalId":285571,"journal":{"name":"2022 11th International Conference on Educational and Information Technology (ICEIT)","volume":"95 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120999937","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 : 2022-01-06DOI: 10.1109/ICEIT54416.2022.9690630
Danqing Zhao, Yatao Li
Project-Based Learning and STEAM Education are widely favored by schools and teachers because both of them are student-centered learning models by allowing students to collaborate and explore around issues in order to promote the development of students' learning in the 21st century. However, in practical pedagogical applications, specific educational models and implementations are highly dependent on exceptional teachers with innovative abilities, especially in the cultivation of implicit higher-order thinking of students still lacking a better landing point. In the context of the current era of rapid development of information technology, the educational changes caused by the new development of smart education mean that more attention should be paid to the level of thinking and operational skills of students. As a result, the Problem-Based Learning for Computational Thinking Development Model for Primary and Secondary Schools (CTPBL), which is interdisciplinary, contextual, innovative, experiential and humanistic in nature, has emerged. As a new educational model, CTPBL helps integrate the advantages of existing Project-Based Learning and STEAM Education, crack the dilemma of teachers' choice of the inherent educational model, and realize the cultivation of students' information literacy and the improvement of their comprehensive ability. However, it still needs to be further explored, such as its operation mechanism, technology carrier, and teachers' roles.
{"title":"Research on the Educational Model of Computational Thinking Cultivation in Primary and Middle Schools Oriented to Production-Based Learning","authors":"Danqing Zhao, Yatao Li","doi":"10.1109/ICEIT54416.2022.9690630","DOIUrl":"https://doi.org/10.1109/ICEIT54416.2022.9690630","url":null,"abstract":"Project-Based Learning and STEAM Education are widely favored by schools and teachers because both of them are student-centered learning models by allowing students to collaborate and explore around issues in order to promote the development of students' learning in the 21st century. However, in practical pedagogical applications, specific educational models and implementations are highly dependent on exceptional teachers with innovative abilities, especially in the cultivation of implicit higher-order thinking of students still lacking a better landing point. In the context of the current era of rapid development of information technology, the educational changes caused by the new development of smart education mean that more attention should be paid to the level of thinking and operational skills of students. As a result, the Problem-Based Learning for Computational Thinking Development Model for Primary and Secondary Schools (CTPBL), which is interdisciplinary, contextual, innovative, experiential and humanistic in nature, has emerged. As a new educational model, CTPBL helps integrate the advantages of existing Project-Based Learning and STEAM Education, crack the dilemma of teachers' choice of the inherent educational model, and realize the cultivation of students' information literacy and the improvement of their comprehensive ability. However, it still needs to be further explored, such as its operation mechanism, technology carrier, and teachers' roles.","PeriodicalId":285571,"journal":{"name":"2022 11th International Conference on Educational and Information Technology (ICEIT)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120968433","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 : 2022-01-06DOI: 10.1109/ICEIT54416.2022.9690718
Zirui Fan, Jun Ruan
Crowd counting is a fundamental computer vision task and plays a critical role in video structure analysis and potential down-stream applications, e.g., accident forecasting and urban traffic analysis. The main challenges of crowd counting lie in the scale variation caused by disorderly distributed “person-camera” distances, as well as the interference of complex backgrounds. To address these issues, we propose a scale adaptive enhance network (SAENet) based on the encoder-decoder U-Net architecture. We employ Res2Net as the encoder backbone for extracting multi-scale head information to relieve the scale variation problem. The decoder consists of two branches, i.e., Attention Estimation Network (AENet) to provide attention maps and Density Estimation Network (DENet) to generate density maps. In order to fully leverage the complementary concepts between AENet and DENet, we craft to propose two modules to enhance feature transfer: i) a lightweight plug-and-play interactive attention module (IA-block) is deployed to multiple levels of the decoder to refine the feature map; ii) we propose a global scale adaptive fusion strategy (GSAFS) to adaptively model diverse scale cues to obtain the weighted density map. Extensive experiments show that the proposed method outperforms the existing competitive method and establishes the state-of-the-art results on ShanghaiTech Part A and B, and UCF-QNRF. Our model can achieve 53.56 and 5.95 MAE in ShanghaiTech Part A and B, with obtains performance improvement of 6.0 % and 13.13%, respectively.
{"title":"Scale Adaptive Enhance Network for Crowd Counting","authors":"Zirui Fan, Jun Ruan","doi":"10.1109/ICEIT54416.2022.9690718","DOIUrl":"https://doi.org/10.1109/ICEIT54416.2022.9690718","url":null,"abstract":"Crowd counting is a fundamental computer vision task and plays a critical role in video structure analysis and potential down-stream applications, e.g., accident forecasting and urban traffic analysis. The main challenges of crowd counting lie in the scale variation caused by disorderly distributed “person-camera” distances, as well as the interference of complex backgrounds. To address these issues, we propose a scale adaptive enhance network (SAENet) based on the encoder-decoder U-Net architecture. We employ Res2Net as the encoder backbone for extracting multi-scale head information to relieve the scale variation problem. The decoder consists of two branches, i.e., Attention Estimation Network (AENet) to provide attention maps and Density Estimation Network (DENet) to generate density maps. In order to fully leverage the complementary concepts between AENet and DENet, we craft to propose two modules to enhance feature transfer: i) a lightweight plug-and-play interactive attention module (IA-block) is deployed to multiple levels of the decoder to refine the feature map; ii) we propose a global scale adaptive fusion strategy (GSAFS) to adaptively model diverse scale cues to obtain the weighted density map. Extensive experiments show that the proposed method outperforms the existing competitive method and establishes the state-of-the-art results on ShanghaiTech Part A and B, and UCF-QNRF. Our model can achieve 53.56 and 5.95 MAE in ShanghaiTech Part A and B, with obtains performance improvement of 6.0 % and 13.13%, respectively.","PeriodicalId":285571,"journal":{"name":"2022 11th International Conference on Educational and Information Technology (ICEIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124359894","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 : 2022-01-06DOI: 10.1109/ICEIT54416.2022.9690733
S. Ubani, Rodney D. Nielsen
This paper reviews recently published works in the emerging field of Collaborative Intelligent Tutoring Systems (CITS). The paper first provides an overview of the fields of Intelligent Tutoring Systems, Computer-Supported Collaborative Learning, and Collaborative Intelligent Tutoring Systems. We systematically search online bibliographic databases, code their research objectives, qualitatively analyze their methodology, and group papers into 3 categories according to our findings. Then we evaluate the associated systems, highlighting their main features and impacts on student learning. Finally, we identify the gaps for possible future research.
{"title":"Review of Collaborative Intelligent Tutoring Systems (CITS) 2009-2021","authors":"S. Ubani, Rodney D. Nielsen","doi":"10.1109/ICEIT54416.2022.9690733","DOIUrl":"https://doi.org/10.1109/ICEIT54416.2022.9690733","url":null,"abstract":"This paper reviews recently published works in the emerging field of Collaborative Intelligent Tutoring Systems (CITS). The paper first provides an overview of the fields of Intelligent Tutoring Systems, Computer-Supported Collaborative Learning, and Collaborative Intelligent Tutoring Systems. We systematically search online bibliographic databases, code their research objectives, qualitatively analyze their methodology, and group papers into 3 categories according to our findings. Then we evaluate the associated systems, highlighting their main features and impacts on student learning. Finally, we identify the gaps for possible future research.","PeriodicalId":285571,"journal":{"name":"2022 11th International Conference on Educational and Information Technology (ICEIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129251235","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：