Distance learning system adaptation based on statistical processing of the results of users activities

DOI: 10.34759/trd-2019-109-21


Naumov A. V.*, Martyushova Y. G.**

Moscow Aviation Institute (National Research University), 4, Volokolamskoe shosse, Moscow, А-80, GSP-3, 125993, Russia

*e-mail: naumovav@mail.ru
**e-mail: ma1554@mail.ru


The article regards the of statistical analysis tools of the distant learning systems (DLS) operation analysis aimed at adapting user’s individual tasks forming process to create his individual training trajectory and control of a compromise of answers. Probabilistic model of the time consumed by a user for the responses to the task is taken as a basis for the user responses compromizing algorithm. The Van der Linden model with log-normal response time distribution is used herewith. The left-hand confidence interval is formed with its aid, and in case, if the user’s response goes beyond its boundaries, a signal to the system administratof is generated on possible compromizing of the response. A certain set of system administrator actions exists herewith based on the signal occurrence, namely the task substitution, tutors’ face-to-face cpnversation with the user, etc. The DLS user individual trajectory forming algorithm is built based on the Rush Model of the probability of right response of the user to the task. The model parameters are the level of the task complexity and the level of the user’s abilities, which are assessed by the maximum likelihood method. User’s individual trajecroty is formed stage-by-stage. Individual task fo the user is formed for each course section by integer programming problem solving method, which parameters are the total complexity level selected by the administrator, and evaluation vector of tasks complexity, obatained based on the Rush model. Individual learning trajectory correcion is performed by limitations in the integer progamming problem, controlling the total complexity of the task, and by user ranking method by the user progress categories with the Rush model.

Depending on the category that the user enters, the administrator selects a specific level of total block of tasks complexity for the individual training trajectory generation task. The proposed algorithms for the individual training trajectory forming of the DLS user and compromizing his answers are implemented in the mathematical support functioning package of the MAI DLS CLASS.NET.


electronic education system, statistical analysis, feedback of control, coprometry of answers


  1. Naumov A.V., Sai Kkhin Aung Tint. Trudy MAI, 2011, no. 42, URL: http://trudymai.ru/eng/published.php?ID=24321

  2. Kibzun A.I., Martyushova Ya.G., Mkhitaryan G.A, Naumov A.V., Rybalko A.A. Sovremennye informatsionnye tekhnologii i IT-obrazovanie, 2016, vol. 12, no. 3, Ch. 2, pp. 68 – 74.

  3. Rasch G. Probabilistic models for some intelligence and attainment tests, Chicago, The University of Chicago Press, 1980, 199 p.

  4. Wim J. van der Linden. A Lognormal Model for Response Times on Test Items, Journal of Educational and Behavioral Statistics, 2006, vol. 31, no. 2, pp. 181–204.

  5. Naumov A.V., Rybalko A.A. Trudy MAI, 2017, no. 97, URL: http://trudymai.ru/eng/published.php?ID=87356

  6. Sologub G.B. Trudy MAI, 2010, no. 38, URL: http://www.mai.ru/eng/science/trudy/

  7. Naumov A.V., Dzhumurat A.S., Inozemtsev A.O. Vestnik komp’yuternykh i informatsionnykh tekhnologii, 2014, no. 10, pp. 36 – 40.

  8. Naumov A.V., Mkhitaryan G.A. Avtomatika i telemekhanika, 2016, no. 9, pp. 124–135.

  9. Kibzun A.I., Panarin S.I. Avtomatika i telemekhanika, 2012, no. 6, pp. 119–139.

  10. Kibzun A.I., Inozemtsev A.O. Avtomatika i telemekhanika, 2014, no. 4, pp. 20–37.

  11. Naumov A.V., Inozemtsev A.O. Vestnik komp’yuternykh i informatsionnykh tekhnologii, 2013, no. 6, pp. 46 – 51.

  12. Kibzun A.I., Zharkov E.A. Vestnik komp’yuternykh i informatsionnykh tekhnologii, 2017, no. 7, pp. 52 – 58.

  13. Naumov A.V., Mkhitaryan G.A., Cherygova E.E. Vestnik komp’yuternykh i informatsionnykh tekhnologii, 2019, no. 2, pp. 37 – 46.

  14. Bosov A.V., Mkhitaryan G.A., Naumov A.V., Sapunova A.P. Informatika i ee primenenie, 2019, vol. 13, no. 4, pp. 12 – 18.

  15. Kibzun A.I., Zharkov E.A. Avtomatika i telemekhanika, 2017, no. 12, pp. 84–99.

  16. Kibzun A.I., Panarin S.I. Avtomatika i telemekhanika, 2012, no. 6, pp. 119–139.

  17. Kibzun A.I., Panarin S.I. Vestnik komp’yuternykh i informatsionnykh tekhnologii, 2010, no. 12, pp. 40 – 49.

  18. Panarin S.I. Trudy MAI, 2011, no. 44, URL: http://trudymai.ru/published.php?ID=25191

  19. Volkov S.S. Trudy MAI, 2019, no. 104, URL: http://trudymai.ru/eng/published.php?ID=102198


mai.ru — informational site MAI

Copyright © 2000-2021 by MAI