Automated ai-based proctoring for online testing in e-learning system

Abstract

Based on the analysis of existing on the market algorithmic solutions for identity verification during knowledge control in electronic learning systems, the requirements for the target system were formed. The main algorithms and approaches to the detection and recognition of faces were considered, as a result of which an effective combination of algorithms was chosen. The system of photo fixation and identity verification during knowledge control in LMS ATutor was designed and implemented. Its effectiveness was verified on the basis of a sample of test passes during its work in the real conditions of the educational process. Conclusions were made regarding the feasibility of implementation.