Software-Defined Infrastructure for Decentralized Data Lifecycle Governance: Principled Design and Open Challenges

Huang, Gang; Luo, Chaoran; Wu, Kaidong; Ma, Yun; Zhang, Ying; Liu, Xuanze

doi:10.1109/icdcs.2019.00166

Cited by 64 publications

(21 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the above research results, research hypothesis 3 was formulated, i.e., that there would be no significant difference between the two groups in relation to action skills learning. In the above research on free grouping, it was found that the results are not yet stable (although free grouping has been evaluated in many fields) (Huang et al, 2006(Huang et al, , 2015(Huang et al, , 2019b.…”

Section: No Difference Between Free Grouping and Other Grouping Methodsmentioning

confidence: 99%

The Efficiency of Cooperative Learning in Physical Education on the Learning of Action Skills and Learning Motivation

Yang

Chen

et al. 2021

Front. Psychol.

View full text Add to dashboard Cite

This paper proposes a cooperative learning method for use in physical education, involving two different grouping methods: S-type heterogeneous grouping and “free” grouping. Cooperative learning was found to enhance the effectiveness of basketball skills learning and learning motivation. A comparison was made of the differences between action skills grouping (the control group) and “free” grouping (the experimental group). The ARCS Motivation Scale and Basketball Action Skills Test were used to measure results, and SPSS statistical analysis software was used for relevant statistical processing (with α set to.05). The results showed that overall skills, dribbling and passing among the action skills groups and “free” groupings significantly improved, but results for shooting were not significant; motivation levels for the two grouping methods significantly improved overall, and no significant differences in learning motivation and learning effectiveness were found between the different grouping methods. It is clear that teachers should first establish a good relationship between and with students, and free grouping methods can be used to good effect. Teachers using cooperative learning should intervene in a timely manner and choose suitable grouping methods according to the teaching goals.

show abstract

Section: No Difference Between Free Grouping and Other Grouping Methodsmentioning

confidence: 99%

The Efficiency of Cooperative Learning in Physical Education on the Learning of Action Skills and Learning Motivation

Yang

Chen

et al. 2021

Front. Psychol.

View full text Add to dashboard Cite

show abstract

“…Through the questionnaire survey, this study has in-depth understanding of the importance ranking and obtained research results, which can be used as a reference for future digital content development and individual recommendation service directions. This first explains the research structure, the content of the expert questionnaire designed by the dimensions and evaluation criteria, then states the sampling and research tools of the research objects and their implementation methods, and finally explains the data processing and analysis of the questionnaire (Liu et al, 2014;Kandlhofer et al, 2016;Huang et al, 2019b).…”

Section: Methodsmentioning

confidence: 99%

Using Artificial Intelligence-Based Collaborative Teaching in Media Learning

Liu

2021

Front. Psychol.

View full text Add to dashboard Cite

With the advent of the 5G era, humans must not only learn the knowledge and skills of cross-border integration but must also get to grips with the breadth and efficiency of artificial intelligence (AI) technology in order to jointly overcome current difficulties and create a happy and beautiful life. In this article, we use the example of an elementary school to discuss the decision-making factors that influence teachers when choosing AI technology, where the digital content of schools is imported into artificial intelligence-based collaborative teaching. After discussing the relevant literature, this study will introduce the concept of digital media education, and then compare the development and application of smart technology and human-computer collaborative teaching methods, describing three key aspects and factors that influence elementary school teachers’ choice of AI technology. There are 12 evaluation criteria in total. After the completion of expert questionnaires and data analysis, it was found that the main factors affecting teachers’ choice of AI technology are “collaborative tasks,” “functional characteristics,” and “modeling characteristics.” In terms of evaluation criteria, the four most important aspects were found to be “learning assistance,” “security,” “teaching observation,” and “record review.” The results of this research analysis will help provide a reference for digital content development and individual recommendation services. In future work, this study can further discuss teaching innovations in digital media education, aimed at improving the quality and effectiveness of teaching and learning.

show abstract

“…With the continuous progress of information technology, the rapid development and popularization of the Internet, the popularity of software-defined infrastructure all over the world [33], the number of users on the news media has increased sharply and people are able to acquire information conveniently from the cyber space such as Web. The recommend methods can be roughly divided into two categoriestraditional methods and deep learning methods.…”

Section: Related Workmentioning

confidence: 99%

DEN-DQL: Quick Convergent Deep Q-Learning with Double Exploration Networks for News Recommendation

Song

Zhang

Shi

et al. 2021

2021 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Due to the dynamic characteristics of news and user preferences, personalized recommendation is a challenging problem. Traditional recommendation methods simply focus on current reward, which just recommend items to maximize the number of current clicks. And this may reduce users' interest in similar items. Although the news recommendation framework based on deep reinforcement learning preciously proposed (i.e, DRL, based on deep Q-learning) has the advantages of focusing on future total rewards and dynamic interactive recommendation, it has two issues. First, its exploration method is slow to converge, which may bring new users a bad experience. Second, it is hard to train on off-line data set because the reward is difficult to be determined. In order to address the aforementioned issues, we propose a framework named DEN-DQL for news recommendation based on deep Q-learning with double exploration networks. Also, we develop a new method to calculate rewards and use an off-line data set to simulate the online news clicking environment to train DEN-DQL. Then, the well trained DEN-DQL is tested in the online environment of the same data set, which demonstrates at least 10% improvement of the proposed DEN-DQL.

show abstract

Software-Defined Infrastructure for Decentralized Data Lifecycle Governance: Principled Design and Open Challenges

Cited by 64 publications

References 13 publications

The Efficiency of Cooperative Learning in Physical Education on the Learning of Action Skills and Learning Motivation

The Efficiency of Cooperative Learning in Physical Education on the Learning of Action Skills and Learning Motivation

Using Artificial Intelligence-Based Collaborative Teaching in Media Learning

DEN-DQL: Quick Convergent Deep Q-Learning with Double Exploration Networks for News Recommendation

Contact Info

Product

Resources

About