Cluster Keyboard Handwriting

摘要

The methods to control the user’s identity during learning in a distance educational environment are explored in the article. In this regard, there is a problem of replacing a registered user with an unscrupulous one.To prevent unauthorized replacement of a registered user, it is proposed to use his keyboard handwriting, which can be formed during user registration in the system. Cluster keyboard handwriting containing information on the data input characteristics of all keyboard symbols is formed to control the user during operation.It is proposed, depending on the length of time the user presses the keys, to calculate the corresponding mean values and standard deviations. Further, the letters are combined into clusters according to the proximity of the obtained statistical characteristics. For clustering, the Kohonen network is used. Preliminary, the mean values and standard deviations are normalized to the interval [0;1]. The formed clusters store the sets of symbols included in them and their statistical characteristics.This method of forming keyboard handwriting makes it possible to verify the user during the entire time he is in the learning environment. The system stores information about the duration of pressing all the keys on the keyboard. Therefore, the decision on the compliance of a user who is in the system with an authorized user is made depending on the correspondence of the current characteristics of the handwriting with the available characteristics.The experimental data that were used to form the cluster keyboard handwriting are presented in the article.