Use of neural networks for adaptive e-learning: A preliminary study

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61988987%3A17310%2F17%3AA1801QY3" target="_blank" >RIV/61988987:17310/17:A1801QY3 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Use of neural networks for adaptive e-learning: A preliminary study

Popis výsledku v původním jazyce

Neural Computing, e.g. Artificial Neural Networks, is one of the most interesting and rapidly growing areas of research, attracting researchers from a wide variety of scientific disciplines. Starting from the basics, Neural Computing covers all the major approaches, putting each in perspective in terms of their capabilities, advantages, and disadvantages. Their use primarily focuses on predicting future behaviour of the given area, e.g. stock market. Adaptive system is able to react to changes from the outside aiming at minimizing the deviation from the required values that characterise the required state or behaviour of the system. Current adaptive systems take advantage of the use of expert systems. Unlike expert systems that use a predefined knowledge base of rules, neural networks learn from a set of examples thus creating their own unique configuration. The aim of this paper is to consider the use of neural networks in an existing e-learning system featuring adaptive characteristics based on a fuzzy expert system. Neural networks are used as a classifier, which generates personal study plans of students and are able to replace the previously used expert system. Nowadays, the experimental study of the whole proposed classifier is in a testing phase. Neural networks should then replace the fuzzy expert system with the goal to outperform it and to provide more accurate and suitable outputs. The final structure of the system should be simplified as the tool in the form of a series of neural networks. The proposed system should act as the only mediator between the tutor and the student in the process of creating a personalised study plan.

Název v anglickém jazyce

Use of neural networks for adaptive e-learning: A preliminary study

Popis výsledku anglicky

Neural Computing, e.g. Artificial Neural Networks, is one of the most interesting and rapidly growing areas of research, attracting researchers from a wide variety of scientific disciplines. Starting from the basics, Neural Computing covers all the major approaches, putting each in perspective in terms of their capabilities, advantages, and disadvantages. Their use primarily focuses on predicting future behaviour of the given area, e.g. stock market. Adaptive system is able to react to changes from the outside aiming at minimizing the deviation from the required values that characterise the required state or behaviour of the system. Current adaptive systems take advantage of the use of expert systems. Unlike expert systems that use a predefined knowledge base of rules, neural networks learn from a set of examples thus creating their own unique configuration. The aim of this paper is to consider the use of neural networks in an existing e-learning system featuring adaptive characteristics based on a fuzzy expert system. Neural networks are used as a classifier, which generates personal study plans of students and are able to replace the previously used expert system. Nowadays, the experimental study of the whole proposed classifier is in a testing phase. Neural networks should then replace the fuzzy expert system with the goal to outperform it and to provide more accurate and suitable outputs. The final structure of the system should be simplified as the tool in the form of a series of neural networks. The proposed system should act as the only mediator between the tutor and the student in the process of creating a personalised study plan.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of the European Conference on e-Learning, ECEL

ISBN

978-191121859-3

ISSN

2048-8637

e-ISSN

—

Počet stran výsledku

7

Strana od-do

78-84

Název nakladatele

Academic Conferences Limited

Místo vydání

UK

Místo konání akce

Porto; Portugal

Datum konání akce

27. 10. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000457842600011