Figure - available from: Distributed and Parallel Databases
This content is subject to copyright. Terms and conditions apply.
Source publication
The Internet deconstructs and reshapes the traditional classroom organization, the status of teachers, the authority of teaching materials and the role of students. Online Ideological and political education with the help of the Internet has become an inevitable trend of Ideological and political education. Mobile edge computing solves the high del...
Citations
... A combination of technologies was used to create an effective model. The suggested framework is verified against various state-of-the-art methods (Saad, 2018;Su, 2021). The cloud-based system was used to share computational resources for ANN to reduce redundant computation. ...
One of the most important features of the Amazon Web Services (AWS) cloud is that the program can be run and accessed from any location. You can access and monitor the result of the program from any location, saving many images and allowing for faster computation. This work proposes a face detection classification model based on AWS cloud aiming to classify the faces into two classes: a non-permission class, and a permission class, by training the real data set collected from our cameras. The proposed Convolutional Neural Network (CNN) cloud-based system was used to share computational resources for Artificial Neural Networks (ANN) to reduce redundant computation. The test system uses Internet of Things (IoT) services through our cameras system to capture the images and upload them to the Amazon Simple Storage Service (AWS S3) cloud. Then two detectors were running, Haar cascade and multitask cascaded convolutional neural networks (MTCNN), at the Amazon Elastic Compute (AWS EC2) cloud, after that the output results of these two detectors are compared using accuracy and execution time. Then the classified non-permission images are uploaded to the AWS S3 cloud. The validation accuracy of the offline augmentation face detection classification model reached 98.81%, and the loss and mean square error were decreased to 0.0176 and 0.0064, respectively. The execution time of all AWS cloud systems for one image when using Haar cascade and MTCNN detectors reached three and seven seconds, respectively.
... In recent years, the development of VR technology has received considerable attention, and with the further popularization of 5G networks, online teaching has emerged as one of the most popular teaching methods besides school teaching [16,17]. Based on this feature and the needs of the current teaching content, we attempt to develop and explore the course mode and resources and apply 5G+ VR technology to the English teaching scenario. ...
Situational teaching has become an important issue in the current development of new teaching modes. The development of the fifth generation (5G) and virtual reality (VR) technologies provide powerful support for reforming the new teaching method. The smart education application scenario implemented by the immersive 5G+ VR smart classroom renders situational English teaching more efficient. Therefore, in this study, we design and analyze a new teaching scenario based on 5G+ VR technology for situational English teaching. First, we design the overall framework of teaching around teaching goals, learner characteristics, teaching resources, and teaching evaluation. We divide the virtual classroom into three different teaching processes: before, during, and after class. Second, we form a virtual classroom teaching system, which includes a cloud system, communication equipment, and a VR classroom applet. Finally, we design the interaction scheme between teachers and students in situational English teaching. The experimental results demonstrate that our method improves teaching effectiveness, which has significant implications for English teaching.
Since entering the information age, educational informatization reform has become the inevitable trend of the development of colleges and universities. The traditional education management methods, especially the classroom attendance methods, not only need to rely on a large number of manpower for data collection and analysis but also cannot dynamically monitor students’ attendance and low efficiency. The development of Internet of things technology provides technical support for the informatization reform of education management in colleges and universities and makes the classroom attendance management in colleges and universities have a new development direction. In this study, a college smart classroom attendance management system based on RFID technology and face recognition technology is constructed under the architecture of the Internet of things, and the corresponding simulation experiments are carried out. The experimental results show that the smart classroom attendance management system based on RFID technology can accurately identify the absence and substitution of students and has the advantages of fast response and low cost. However, its recognition is easily affected by obstructions, which requires students to place identification cards uniformly. The smart classroom attendance management system based on face recognition technology can accurately record and identify the situation of students entering and leaving the classroom and identify the situations of being late and leaving early, absenteeism, and substitute classes. The experimental results are basically consistent with the sample results, and the error rate is low. However, the system is easily affected by environmental light, students’ sitting posture, expression, and other factors, so it cannot be recognized. Generally speaking, both can meet the needs of classroom attendance in colleges and universities and have high accuracy and efficiency.
