Article

Article title PREDICTION OF RESIDUAL KNOWLEDGE OF STUDENTS IN CERTAIN DISCIPLINES BY NEURAL NETWORKS
Authors O.I. Fedyaev
Section SECTION III. METHODS OF ADAPTATION AND NEURAL NETWORK ALGORITHMS
Month, Year 07, 2016 @en
Index UDC
DOI DOI 10.18522/2311-3103-2016-7-122136
Abstract The scientific work is devoted to the development of a neural network model of the learning process for students agent system modeling of the labor market. This model simulates the transfer of skills and knowledge, depending on the personal characteristics of students. The system will allow the simulation to analyze the process of training young professionals and to predict their future employment prospects. The aim of this work is to develop a model based on a neural network capable of functionally describe the dependence of students receive professional knowledge and skills of the factors affecting the completeness of this knowledge. The main function of the learning process of students as the system is to transfer knowledge and develop professional skills of the future experts to solve specific production problems. The learning process is difficult to formalize, and therefore can not be described by conventional mathematical methods. In addition, participants in the learning process geographically distant from each other, are heterogeneous in structure and activity of intelligent by nature. These features cause the feasibility of the theory of intelligent agents to the development of a simulation model for the analysis of the training process. Have been developed methods for determining the mental and psycho-physiological characteristics of the student. These techniques combine to form a system that determines a mental portrait of a student. The developed model of the learning process should form the output residual knowledge of the student on a separate discipline, with whom he comes into the labor market. Residual knowledge depend on the mentality of students and other factors. This relationship is difficult to formalize. In such cases it is advisable to use a neural network that will identify an existing connection through her training. Forecast residual knowledge on one particular discipline taken for one student is carried out in two stages. In the first phase is predicted on the basis of the examination score mentality of the student. In the second stage, based on the projected estimates formed averaged residual set of knowledge and skills corresponding to this assessment. Each of these steps can not be formalized mathematically, so the two will be used by the neural network. The first neural network will be trained on the basis of mental portrait of a group of students and the examination sheet. The second neural network - based on the evaluation criteria and curriculum discipline, which contains a list of knowledge and skills. As a medium of artificial neural networks modeling package was used Neural Network Toolbox, which is included in the standard package MATLAB. Preliminary results of a study on software models showed the correctness of the proposed ideas for solving the problem. On the basis of this model will be developed artificial learning software agents, which together will simulate the dynamics of the processes of training a group of students and their employment. The novelty of the work lies in a new approach to the description of the neural network is difficult to formalize the process of vocational training of young professionals, based on a simulation of the transfer of skills and knowledge, depending on the personal characteristics of students. It includes the construction of a mental portrait of the student and the development of neural learning algorithm of the two stages of the neural model that predicts residual knowledge and skills of student in certain disciplines. Prediction competencies enables to further evaluate the relevance of each student in the labor market.

Download PDF

Keywords Training model; professional knowledge; the mentality of the student; neural network.
References 1. Tel'nov Yu.F., Danilov A.V., Kazakov V.A. Primenenie mnogoagentnoy tekhnologii dlya resheniya obrazovatel'nykh zadach v informatsionno-obrazovatel'nom prostranstve [The application of multi-agent technology for solving educational challenges in the information educational environment], Inzhiniring predpriyatiy i upravlenie znaniyami: Sb. nauch. tr. 18-y nauchno-prakticheskoy konferentsii (IPi UZ-2015, 21-24 aprelya 2015 g., Moskva, MESI) [Engineering enterprises and knowledge management: SB. scientific. Tr. 18-th scientific-practical conference (IAS UZ-2015 21-24 April 2015, Moscow, MESI)]. Moscow: MESI, 2015, pp. 451-457.
2. Fedyaev O.I. Mnogoagentnaya model' protsessa obucheniya studentov na kafedral'nom urovne [A multi-agent model of the learning process of students at Cathedral level], Naukovі pratsі Donets'kogo natsіonal'nogo tekhnіchnogo unіversitetu. Serіya "Problemi modelyuvannya ta avtomatizatsії proektuvannya dinamіchnikh sistem" [Scientific works of Donetsk national technical University. Series "Problems of modeling and design automation of dynamic systems]. Issue 5 (116). Donets'k: DonNTU, 2006, pp. 105-116.
3. Trembach V.M. Intellektual'naya obuchayushchaya sistema s adaptatsiey individual'noy traektorii obucheniya [Intelligent tutoring system adaptation individual learning paths], Trudy 15-y Natsional'noy konferentsii po iskusstvennomu intellektu s mezhdunarodnym uchastiem (KII-2016) (3-9 oktyabrya 2016 g., Smolensk, Rossiya): Trudy konferentsii [Proceedings of the 15th National conference on artificial intelligence with international participation (KII-2016) (3-9 July, 2016, Smolensk, Russia): Proceedings of the conference]. Vol. 3. Smolensk: Izd-vo Universum, 2016, pp. 203-211.
4. Fedyaev O.I., Lukina Yu.Yu., Stropalov A.S. Analiz i prognozirovanie protsessa trudoustroystva molodykh spetsialistov s pomoshch'yu mul'tiagentnoy imitatsionnoy modeli [Analysis and forecasting of the process of employment of young specialists with multi-agent simulation model], Trudy konferentsii IAI-2013, KPI [The conference proceedings of IAS-2013, CRPD]. Kiev, 2013, pp. 47-53.
5. Mutovkina N.Yu., Palyukh B.V., Klyushin A.Yu. Nechetkaya otsenka konkurentosposobnosti vypusknikov vysshikh uchebnykh zavedeniy [Fuzzy evaluation of the competitiveness of graduates of higher education institutions], Trudy 15-y Natsional'noy konferentsii po is-kusstvennomu intellektu s mezhdunarodnym uchastiem (KII-2016) (3-9 oktyabrya 2016 g., Smolensk, Rossiya) [Proceedings of the 15th National conference on artificial intelligence with international participation (KII-2016) (3-9 July, 2016, Smolensk, Russia)]. Vol. 3. Smolensk: Izd-vo Universum, 2016, pp. 123-130.
6. Fedyaev O.I., Zhabskaya T.E. Proektirovanie virtual'noy kafedry universiteta na osnove mnogomodel'nogo agentno-orientirovannogo podkhoda [The virtual design Department of the University on the basis of the multi-model agent-oriented approach], Iskusstvennyy intellect [Artificial intelligence], 2010, No. 3, pp. 679-686.
7. Zhabska Tetiana, Fedyaev Oleg. The development of agent-based intellectual e-learning envi-ronment, Proceedings of the IADIS International conference Intelligent systems and agents 2011 Rome, Italy July 24-26, 2011, pp. 143-147.
8. Zakirova E.I. Upravlenie obrazovatel'nymi sistemami s ispol'zovaniem mul'tiagentnykh tekhnologiy [Management of educational systems using multi-agent technology], Nauka i obrazovanie [Science and education], 2013, No. 9, pp. 373-390.
9. Yankovskaya A.E., Shurygin Yu.A., Yamshanov A.V., Krivdyuk N.M. Opredelenie urovnya usvoennykh znaniy po obuchayushchemu kursu, predstavlennomu semanticheskoy set'yu [Determination of the level of acquired knowledge on the learning rate represented by semantic network], Trudy 5-y konferentsii "Otkrytye semanticheskie tekhnologii proektirovaniya intellektual'nykh sistem" (OSTIS-2015) (19-21 fevralya 2015, Minsk) [Proceedings of 5th conference "Open semantic technology of intelligent systems" (OSTIS-2015) (19-21 Feb 2015]. Minsk.: BGUIR, 2015, pp. 331-338.
10. Sherkunov V.V. Ontologicheskiy podkhod k analizu kompetentsiy vypusknikov vuzov [Onto-logical approach to the analysis of competencies of graduates of universities], Trudy 5-y kon-ferentsii "Otkrytye semanticheskie tekhnologii proektirovaniya intellektual'nykh sistem" (OSTIS-2015) (19-21 fevralya 2015, Minsk) [Ontological approach to the analysis of competencies of graduates of universities]. Minsk: BGUIR, 2015, pp. 351-356.
11. Vlasov A.A., Nekhaev I.N. Intellektual'naya sistema adaptivnogo testirovaniya urovnya usvoeniya znaniy [The intellectual system of adaptive testing level of learning], Dvenadtsataya natsional'naya konferentsiya po iskusstvennomu intellektu s mezhdunarodnym uchastiem «KII-2010» (20–24 sentyabrya 2010 g., g. Tver', Rossiya): Trudy konferentsii [Twelfth national conference on artificial intelligence with international participation "KII-2010" (20-24 September 2010, Tver, Russia): Proceedings of the conference]. Vol. 3. Moscow: Fizmatlit, 2010, pp. 257-263.
12. Danilov A.N., Lobov N.V., Stolbov V.Yu., Stolbova I.D. Kompetentnostnaya model' vypusknika: opyt proektirovaniya [Competence model of a graduate: the design experience], Vysshee obrazovanie segodnya [Higher Education Today], 2013, No. 6, pp. 25-33.
13. Gitman M.B., Danilov A.N., Stolbov V.Yu. Ob odnom podkhode k kontrolyu urovnya sformi-rovannosti bazovykh kompetentsiy vypusknikov vuza [About one approach to monitoring the level of formation of basic competences of the graduates of the University], Vysshee obra-zovanie v Rossii [Higher Education in Russia], 2012, No. 4, pp. 13-18.
14. Il'in E.P. Psikhologiya tvorchestva, kreativnosti, odarennosti [The psychology of creativity, creativity, talent]. St. Petersburg: Piter, 2004, 537 p.
15. Ayzenk G. Novye testy IQ [New IQ tests]. Moscow: Izd-vo "ESKMO", 2003, 189 p.
16. Deyneka A.V. i dr. Sovremennye tendentsii v upravlenii personalom: ucheb. Posobie [Modern trends in personnel management: textbook]. Moscow: Izd-vo "Akademiya estestvoznaniya", 2009, 294 p.
17. Kruglov V.V. i dr. Nechetka logika i iskusstvennye neyronnye seti [Fuzzy logic and artificial neural networks]. Moscow: Fizmatlit, 2001, 224 p.
18. Kol'tsov Yu.V. Dobrovol'skaya N.Yu. Neyrosetevye modeli v adaptivnom komp'yuternom obuchenii [Neural network model in adaptive computer training], Educational Technology & Society [Educational Technology & Society], 2002, No. 5 (2). Available at: http://ifets.ieee.org/russian/periodical/V_52_2002EE.html.
19. D'yachenko S.A. Ispol'zovanie neyronnykh setey pri izuchenii protsessa prisposoblyaemosti studenchestva k vuzovskomu obucheniyu [The use of neural networks in the study of the pro-cess of adaptation of students to University learning], Neyrosetevye tekhnologii i ikh primenenie: Sbornik trudov mezhdunarodnoy nauchnoy konferentsii «Neyrosetevye tekhnologii i ikh primenenie 2002-2003» [Neural network technology and their application: proceedings of the international scientific conference "Neural network technology and their application 2002-2003"]. Kramatorsk: DGMA, 2003, pp. 67-70.
20. D'yakonov V. i dr. Matematicheskie pakety rasshireniya MATLAB. Spetsial'nyy spravochnik [Mathematical expansion packs MATLAB. A special Handbook]. St. Petersburg: Piter, 2001, 268 p.
21. Ivashkin Yu.A. Agentnye tekhnologii i mul'tiagentnoe modelirovanie: ucheb. Posobie [Agent technologies and multi-agent modeling: a tutorial]. Moscow: MFTI, 2013, 268 p.

Comments are closed.