The issue related to the risk of identity impersonation, where one person can be replaced by another in online exam surveillance systems, poses challenges. This study focuses on the effectiveness of detecting attempts...The issue related to the risk of identity impersonation, where one person can be replaced by another in online exam surveillance systems, poses challenges. This study focuses on the effectiveness of detecting attempts of identity impersonation through face substitution during online exams, with the aim of ensuring the integrity of assessments. The goal is to develop facial recognition algorithms capable of precisely detecting these impersonations, training them on a tailored database rather than biased generic data. An original database of student faces has been created. An algorithm leveraging advanced deep learning techniques such as depthwise separable convolution has been developed and evaluated on this database. We achieved very high levels of precision, reaching an accuracy rate of 98% in face detection and recognition.展开更多
Little research has been conducted on Oral English course exams for tertiary-level English major students in China. Issues found in recent surveys of teachers and students of Oral English classes at four universities ...Little research has been conducted on Oral English course exams for tertiary-level English major students in China. Issues found in recent surveys of teachers and students of Oral English classes at four universities suggest that the Oral English course exam needs a theoretical model to ensure its reliability and validity and hence to better lead students' learning of spoken English. Applying language testing theories and using ethnographic methodologies, this paper attempts to propose such a model through discussing the problematic issues in current practice in Oral English course exams and defining the targeted oral English abilities to be examined.展开更多
文摘The issue related to the risk of identity impersonation, where one person can be replaced by another in online exam surveillance systems, poses challenges. This study focuses on the effectiveness of detecting attempts of identity impersonation through face substitution during online exams, with the aim of ensuring the integrity of assessments. The goal is to develop facial recognition algorithms capable of precisely detecting these impersonations, training them on a tailored database rather than biased generic data. An original database of student faces has been created. An algorithm leveraging advanced deep learning techniques such as depthwise separable convolution has been developed and evaluated on this database. We achieved very high levels of precision, reaching an accuracy rate of 98% in face detection and recognition.
文摘Little research has been conducted on Oral English course exams for tertiary-level English major students in China. Issues found in recent surveys of teachers and students of Oral English classes at four universities suggest that the Oral English course exam needs a theoretical model to ensure its reliability and validity and hence to better lead students' learning of spoken English. Applying language testing theories and using ethnographic methodologies, this paper attempts to propose such a model through discussing the problematic issues in current practice in Oral English course exams and defining the targeted oral English abilities to be examined.
