Sustainable Construction of Higher Education MOOCs Using CNN Feature Extraction

Sustainable Construction of Higher Education MOOCs Using CNN Feature Extraction

Yongyan Zhao (Harbin University, China) and Jian Li (Harbin University, China)
DOI: 10.4018/IJWLTT.357695
Article PDF Download
Open access articles are freely available for download

Abstract

The attention time of students studying in MOOC (Massive Open Online Courses) classroom was analyzed to optimize and further improve their performance. On this basis, a student class model based on convolutional neural networks (CNN) feature extraction was proposed. Through Pr (Adobe Premiere) technology, students' class videos were processed by framing, and relevant features were extracted based on changes in students' eye movement trajectories. Then, 10 class videos of ten different experimenters were selected for comparative experiments. After comparing the results, it was found that the test scores of the experimental personnel using MOOC model for assisted learning were significantly different from those before using MOOC model. The final test scores of the students using MOOC model for learning increased to 5-10 points, which had a certain positive impact on the learning results. In the context of sustainable development of higher education, the construction and application of the MOOC model require more favorable promotion and practice.
Article Preview
Top

Introduction

In this information age, pursuing sustainable development has become a long-term strategy. The sustainable development of universities includes the construction of environmental, economic, industrial, and ideological education, teaching staff, and other areas (Chang & Liu, 2020; Pasha, 2022). Additionally, with numerous universities in major cities, sustainable development is an essential task and a crucial development strategy for these institutions. It is an effective means for high-quality schools to maximize their social responsibility. Massive open online courses (MOOCs) use information technology to drive innovation in educational concepts, having a profound impact on higher education. Higher education focuses on cultivating students’ technical skills. In terms of jointly building and sharing high-quality and scarce resources, MOOCs have established a flexible, diverse, and heuristic curriculum system. This allows them to provide services to a broader audience, promoting educational fairness and accessibility, which is significant (Omkar & Fassou, 2023; Zheng et al., 2023).

In modern society, people’s lifestyles are changing, and educational models are evolving as well. Today, MOOCs, as a new teaching method, are widely used worldwide, and university MOOCs have become an essential tool for students. García-Peñalvo et al. (2018) conducted in-depth research on the composition of second-generation MOOCs, aiming to provide a new model without the need for complex technologies, allowing people to better understand the essence of MOOCs. This model integrated the social characteristics of connective MOOCs, the organization of extended MOOCs, and personalized learning. Its feasibility was verified through case analysis and participant feedback. Yousef and Sumner (2021) conducted a meta-analysis of over 200 MOOC studies, reflecting on the past decade of MOOC research. They highlighted major achievements and research directions, identifying areas for further exploration. Zulkifli et al. (2020) used descriptive and inferential statistics to analyze MOOC usage. Their results showed that while students were motivated and willing to use MOOCs, the greatest barrier was the need for additional online searches. University students’ emotional experiences with MOOCs also led to corresponding behaviors. Therefore, this article focuses on the experiences of university users as a starting point.

With the continuous development of society, the economy, education, and other areas, the market demand for MOOCs is constantly evolving and presenting new characteristics. Therefore, providing suitable supplementary tools for MOOCs is particularly important. In MOOCs, image recognition can effectively enhance students’ interest. Zhao et al. (2022) used image data collected by robots and deep learning methods to recognize students’ facial expressions, assessing their attention and fatigue levels. Their findings showed that patrol robots can supervise students’ focus in daily teaching, helping improve teaching quality. The robots also assist in timely reminders, enhancing students’ attention and improving classroom learning effectiveness.

Li et al. (2022) proposed an image feature extraction method using intelligent hardware and computer technology, significantly improving the accuracy of tracking and identification, allowing for precise recognition of movement trajectory. This approach, combined with new behavior recognition methods, not only improves the accuracy of teaching video recognition but also speeds up recognition, making it easier to capture students’ behavioral changes. The behavior recognition algorithm is fast and efficient. Bai et al. (2020) applied multiple feature fusion to integrate detailed shallow features with deep layers of rich semantic information, resulting in an improved model for detecting students’ classroom performance. Their findings indicated that the model, using faster region-convolutional neural network (R-CNN) with multi-feature fusion, demonstrated high precision in detecting student behaviors in the classroom, showing promise for enhancing teaching quality. However, existing research primarily focuses on college students’ behavior, with limited attention to emotional factors. Therefore, this article aims to extract and analyze students’ emotional levels to better understand their psychological status and improve academic performance.

Complete Article List

Search this Journal:
Reset
Volume 20: 1 Issue (2025)
Volume 19: 1 Issue (2024)
Volume 18: 2 Issues (2023)
Volume 17: 8 Issues (2022)
Volume 16: 6 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing