作者:
Wang, Zhifeng;Yan, Wenxing;Zeng, Chunyan;Tian, Yuan;Dong, Shi
期刊:
International Journal of Intelligent Systems,2023年2023 ISSN:0884-8173
作者机构:
[Dong, Shi; Tian, Yuan; Wang, Zhifeng; Yan, Wenxing] Cent China Normal Univ, Fac Artificial Intelligence Educ, Sch Educ Informat Technol, Wuhan 430079, Peoples R China.;[Zeng, Chunyan] Hubei Univ Technol, Hubei Key Lab High efficiency Utilizat Solar Energ, Wuhan 430068, Peoples R China.
摘要:
Intelligent learning diagnosis is a critical engine of intelligent tutoring systems, which aims to estimate learners' current knowledge mastery status and predict their future learning performance. The significant challenge with traditional learning diagnosis methods is the inability to balance diagnostic accuracy and interpretability. Although the existing psychometric-based learning diagnosis methods provide some domain interpretation through cognitive parameters, they have insufficient modeling capability with a shallow structure for large-scale learning data. While the deep learning-based learning diagnosis methods have improved the accuracy of learning performance prediction, their inherent black-box properties lead to a lack of interpretability, making their results untrustworthy for educational applications. To settle the abovementioned problem, the proposed unified interpretable intelligent learning diagnosis framework, which benefits from the powerful representation learning ability of deep learning and the interpretability of psychometrics, achieves a better performance of learning prediction and provides interpretability from three aspects: cognitive parameters, learner-resource response network, and weights of self-attention mechanism. Within the proposed framework, this paper presents a two-channel learning diagnosis mechanism LDM-ID as well as a three-channel learning diagnosis mechanism LDM-HMI. Experiments on two real-world datasets and a simulation dataset show that our method has higher accuracy in predicting learners' performances compared with the state-of-the-art models and can provide valuable educational interpretability for applications such as precise learning resource recommendation and personalized learning tutoring in intelligent tutoring systems.
摘要:
This study assesses the predictive capabilities of the CMA-GD model for wind speed prediction in two wind farms located in Hubei Province, China. The observed wind speeds at the height of 70m in wind turbines of two wind farms in Suizhou serve as the actual observation data for comparison and testing. At the same time, the wind speed predicted by the EC model is also included for comparative analysis. The results indicate that the CMA-GD model performs better than the EC model in Wind Farm A. The CMA-GD model exhibits a monthly average correlation coefficient of 0.56, root mean square error of 2.72 m s-1, and average absolute error of 2.11 m s-1. In contrast, the EC model shows a monthly average correlation coefficient of 0.51, root mean square error of 2.83 m s-1, and average absolute error of 2.21 m s-1. Conversely, in Wind Farm B, the EC model outperforms the CMA-GD model. The CMA-GD model achieves a monthly average correlation coefficient of 0.55, root mean square error of 2.61 m s-1, and average absolute error of 2.13 m s-1. By contrast, the EC model displays a monthly average correlation coefficient of 0.63, root mean square error of 2.04 m s-1, and average absolute error of 1.67 m s-1.
作者机构:
[Zhao, Yulin; Liu, Kai; Zhao, YL; Li, Junke] Suqian Univ, Sch Informat Engn, Suqian 223800, Jiangsu, Peoples R China.;[Zhao, Yulin] Cent China Normal Univ, Sch Educ Informat Technol, Wuhan 430079, Peoples R China.;[Li, Junke] Jiangsu Prov Engn Res Ctr Smart Poultry Farming &, Suqian 223800, Jiangsu, Peoples R China.;[Liu, Kai] Qiannan Normal Univ Nationalities, Sch Comp & Informat, Duyun 558000, Peoples R China.
通讯机构:
[Liu, K ; Zhao, YL; Li, JK] S;Suqian Univ, Sch Informat Engn, Suqian 223800, Jiangsu, Peoples R China.
关键词:
High school mathematics;Subject attention;Literature research;Relationship modeling;Short-term forecasting
摘要:
The exploration of the correlation between subject network attention and literature research in China can aid in comprehending the development trend of Chinese scientific and technological journals. Currently, many scholars have done a lot of research based on the network media index, but the relationship between the discipline attention represented by it and literature research has not been fully verified. This paper used CNKI and Baidu Index as data sources to establish a RAPF experimental framework based on relationship analysis and prediction, and selected high school mathematics subjects in China for effective demonstration. First, RAPF extracted core keywords using text tools and word frequency statistics. Second, it constructed a relationship model between subject attention and literature research based on Spearman and LOOCV. Finally, it made predictions through time series and regression analysis. The results showed a correlation between subject attention and literature research, and the model fit R(2) was 0.774, with a relative error of less than 2%. Short-term predictions found that some keywords received less online attention, and 2022-2024 may be the crucial development period for mathematical education research, with an annual literature research volume of approximately 380 articles. This paper summarized the mathematical subject themes centered on content, culture, literacy, and integration, and also provided a reference for the development of the subject through experimental prediction. In the next two years, China's mathematics literature research still needs to delve deeper, broaden its breadth, enhance its height, and ensure a steady improvement in the quality and quantity of literature research.
期刊:
Journal of Research on Technology in Education,2023年55(2):344-368 ISSN:1539-1523
通讯作者:
Zhang, Yi
作者机构:
[Li, Xing] Jianghan Univ, Sch Educ, Media Technol, Wuhan, Hubei, Peoples R China.;[Xie, Kui] Ohio State Univ, Dept Educ Studies, Educ Psychol & Learning Technol, Columbus, OH 43210 USA.;[Vongkulluksn, Vanessa] Ohio State Univ, Columbus, OH 43210 USA.;[Stein, David] Ohio State Univ, Workforce Dev & Educ, Columbus, OH 43210 USA.;[Zhang, Yi; Xie, Kui] Cent China Normal Univ, Sch Educ Informat Technol, Educ Technol, Wuhan, Hubei, Peoples R China.
通讯机构:
[Zhang, Yi] C;Cent China Normal Univ, Sch Educ Informat Technol, Dept Educ Technol, Bldg 9,152 Luoyu Rd, Wuhan 430079, Hubei, Peoples R China.
关键词:
Elementary education;teaching;learning strategies;21st century abilities;pedagogical issues;interdisciplinary projects
摘要:
Computational Thinking (CT) is regarded as a crucial competency for all children in the 21(st) century. There are misconceptions about CT which confounds CT skills with programming skills. However, CT skills and programming skills are not the same. CT is a broader skillset of cognitive thinking that is integral to complex problem solving. Teaching and assessing CT should not only focus on computer programming. In this project, a new design-based learning (DBL) approach was proposed to improve elementary school students' CT. This approach not only included programming skills, but also integrated CT practices with authentic real-life contexts. Corresponding to recent conceptions of CT, we also assessed CT in a more comprehensive manner. A quasi-experiment study was carried out to assess how the intervention was associated with students' self-perceived CT skills using both quantitative and qualitative methods. In the treatment group, twenty-three fourth graders engaged in three curriculum units to create artifacts that solve specific real-world problems using LabPlus electronic kits and Scratch programming software. The control group took a traditional computer science class. Results revealed that students' self-perceived CT skills increased to a greater extent in the treatment group compared to the control group. In addition, we observed and interviewed three student cases in the treatment group to understand the potential learning effects of our new DBL approach. This study contributes to research in CT instruction, its application in STEM education in particular, and how it can be used in elementary level education in general.
期刊:
ETR&D-EDUCATIONAL TECHNOLOGY RESEARCH AND DEVELOPMENT,2022年70(3):849-880 ISSN:1042-1629
通讯作者:
Hung, C.-Y.;Zhang, Y.
作者机构:
[Wang, Jue] Huzhou Univ, Sch Teacher Educ, Huzhou, Zhejiang, Peoples R China.;[Zhang, Yi; Hung, Cheng-Yu] Cent China Normal Univ, Fac Artificial Inteligence Educ, Sch Educ Informat Technol, Wuhan, Hubei, Peoples R China.;[Wang, Qiyun] Nanyang Technol Univ, Natl Inst Educ, Singapore, Singapore.;[Zheng, Ying] Yichun Univ, Sch Foreign Languages, Yichun, Jiangxi, Peoples R China.
通讯机构:
[Yi Zhang; Cheng-Yu Hung] S;School of Educational Information Technology, Faculty of Artificial Inteligence in Education, Central China Normal University, Wuhan, People’s Republic of China<&wdkj&>School of Educational Information Technology, Faculty of Artificial Inteligence in Education, Central China Normal University, Wuhan, People’s Republic of China
关键词:
Non-programming;Plugged learning;Mathematics;Computational thinking (CT);Design-based implementation research (DBIR);Problem-solving
作者机构:
[Yang, Zongkai; Liu, Sannyuya; Liu, Zhi; Peng, Xian] Cent China Normal Univ, Natl Engn Lab Educ Big Data, Wuhan, Peoples R China.;[Yang, Zongkai; Liu, Sannyuya; Mu, Rui] Cent China Normal Univ, Natl Engn Res Ctr E Learning, Wuhan, Peoples R China.;[Chen, Jia] Cent China Normal Univ, Sch Educ Informat Technol, Wuhan, Peoples R China.
通讯机构:
[Xian Peng] N;National Engineering Laboratory for Educational Big Data, Central China Normal University, Wuhan, People’s Republic of China
作者:
Mingzhang Zuo;Lixiang Gao;Wei Wang;Shuang Wang;Heng Luo
期刊:
International Journal of Innovation and Learning,2022年31(3):404-422https://doi.org/10.1504/IJIL.2022.122072 ISSN:1471-8197
通讯作者:
Luo, H.
作者机构:
1. School of Educational Information Technology, Central China Normal University, Wuhan, China;2. School of Educational Information Technology, Central China Normal University, Wuhan, China;3. Hangcheng Elementary and Middle School, Shenzhen, China;4. School of Educational Information Technology, Central China Normal University, Wuhan, China;5. School of Educational Information Technology, Central China Normal University, Wuhan, China
通讯机构:
School of Educational Information Technology, Central China Normal University, Wuhan, China
期刊:
Signal, Image and Video Processing,2022年16(1):47-54 ISSN:1863-1703
通讯作者:
Zhifeng Wang
作者机构:
[Zhao, Nan; Wu, Minghu; Ye, Jiaxiang; Zeng, Chunyan] Hubei Univ Technol, Hubei Key Lab High Efficiency Utilizat Solar Ener, Wuhan 430068, Peoples R China.;[Wang, Zhifeng] Cent China Normal Univ, Hubei Res Ctr Educ Informationizat, Sch Educ Informat Technol, Wuhan 430079, Peoples R China.
通讯机构:
[Zhifeng Wang] S;School of Educational Information Technology/Hubei Research Center for Educational Informationization, Central China Normal University, Wuhan, China
摘要:
Most deep learning-based compressed sensing (DCS) algorithms adopt a single neural network for signal reconstruction and fail to jointly consider the influences of the sampling operation for reconstruction. In this paper, we propose a unified framework, which jointly considers the sampling and reconstruction process for image compressive sensing based on well-designed cascade neural networks. Two sub-networks, which are the sampling sub-network and the reconstruction sub-network, are included in the proposed framework. In the sampling sub-network, an adaptive fully connected layer instead of the traditional random matrix is used to mimic the sampling operator. In the reconstruction sub-network, a cascade network combining stacked denoising autoencoder (SDA) and convolutional neural network (CNN) is designed to reconstruct signals. The SDA is used to solve the signal mapping problem, and the signals are initially reconstructed. Furthermore, CNN is used to fully recover the structure and texture features of the image to obtain better reconstruction performance. Extensive experiments show that this framework outperforms many other state-of-the-art methods, especially at low sampling rates.