文章基本信息

标题：Advances in Contextual Action Recognition: Automatic Cheating Detection Using Machine Learning Techniques
本地全文：下载
作者：Fairouz Hussein ; Ayat Al-Ahmad ; Subhieh El-Salhi 等
期刊名称：Data
印刷版ISSN：2306-5729
出版年度：2022
卷号：7
期号：9
页码：1-13
DOI：10.3390/data7090122
语种：English
出版社：MDPI Publishing
摘要：Teaching and exam proctoring represent key pillars of the education system. Humanproctoring, which involves visually monitoring examinees throughout exams, is an important partof assessing the academic process. The capacity to proctor examinations is a critical componentof educational scalability. However, such approaches are time-consuming and expensive. In thispaper, we present a new framework for the learning and classification of cheating video sequences.This kind of study aids in the early detection of students’ cheating. Furthermore, we introduce anew dataset, “actions of student cheating in paper-based exams”. The dataset consists of suspiciousactions in an exam environment. Five classes of cheating were performed by eight different actors.Each pair of subjects conducted five distinct cheating activities. To evaluate the performance ofthe proposed framework, we conducted experiments on action recognition tasks at the frame levelusing five types of well-known features. The findings from the experiments on the framework wereimpressive and substantial.
关键词：action recognition;machine learning;cheating;computer vision;feature extraction;videosurveillance