Applying the Douglas–Peucker Algorithm in Online Authentication of Remote Work Tools for Specialist Training in 10.00.00 “Information Security” Integrated Group of Specialties

With educational systems shifting to distance learning and the trend towards remote work growing, an urgent need has arisen to develop reliable biometric identification and authentication technologies to verify employees working remotely. Such technologies can provide a high degree of protection and usability, making their development and optimization extremely important. The issue is that accuracy and efficiency of mouse gesture recognition systems need to be improved without any specialized devices used and in the shortest possible time. This requires efficient preprocessing of such gestures to simplify their trajectories while preserving their key features. The Douglas–Peucker algorithm is proposed to be used for preliminary processing of mouse gesture trajectory data. This algorithm allows significantly reducing the number of points in the trajectories, simplifying them while preserving the principal shape of the gestures. The data with simplified trajectories are then used to train neural networks. The experimental part of the work showed that, when applied, the Douglas–Peucker algorithm allows for a 60% reduction in the number of points on the trajectories, increasing the gesture recognition accuracy from 70 to 82%. Such data simplification contributes to speeding up the neural networks' training process and improving their operational efficiency. The study confirmed the efficiency of using the Douglas–Peucker algorithm for preliminary data processing in mouse gesture recognition problems. The results can be applied to develop more intuitive and adaptive user interfaces. In addition, directions for further research, including optimization of the algorithm’s parameters for different types of gestures and exploring the possibility of combining it with other machine learning methods, are proposed.