This paper proposes a speedup convolutional neural network (CNN)-based deblurring framework (SpeedDeblur) for reconstructed blurry videos. First, we extract the coding information and the reconstructed video from the compressed data. Second, a CNN-based algorithm is used for deblurring the first reconstructed frame.
In this game, I applied A* Algorithm to make the bot more intelligent.
Blue bot: freedom to move and shoot bullets
Yellow bot: find a way to chase and attack player
Red bot: find a way to attack the main house
Bomber: appear and drop bombs randomly
In this thesis, we developed an application to identify persons in surveillance cameras, using video surveillance cameras from a building as input. The target is finding a person with information, such as a photo of a person's face or personal attribute information. We designed a framework that utilizes facial features and person identification information to find persons in CCTV cameras. The goals of this thesis are as follows: first, to learn related techniques such as face detection, matching algorithms, person detection, classification of a person's descriptive information, object grouping, and so on; second, to develop a system with the function of searching people in surveillance cameras; and finally, to evaluate the application's search efficiency when combining related techniques.
In the current complicated COVID epidemic, many educational institutions have applied online teaching. Monitoring and analyzing students' academic performance in the online environment is essential. Thus, we developed this web-based application to help administrators and teachers capture students' learning performance. Then lecturers can improve more appropriate teaching methods.
This paper proposes a speedup convolutional neural network (CNN)-based deblurring framework (SpeedDeblur) for reconstructed blurry videos. First, we extract the coding information and the reconstructed video from the compressed data. Second, a CNN-based algorithm is used for deblurring the first reconstructed frame.
Online learning is growing in various forms, including full-online, hybrid, hy-flex, blended, synchronous, and asynchronous.
Assessing students’ engagement without having real contact between teachers and students is becoming a challenge for the
teachers.
In higher education, learning analytics is trending for transforming teaching behavior, uncovering information on
the human learning process, understanding factors for smart
learning environments, and addressing artificial intelligence issues
in education.
TAs learning analytics is getting maturity, higher educational institutions worldwide are becoming more interested in
practicing learning analytics. Over the last decade, learning management systems (LMSs) such as Moodle, Canvas, Blackboard,
Sakai were the primary sources for interaction data.