Abstract
In this technological world demanding latest updations in the domain knowledge, it is no surprise that e-learning has become a more viable option to a range of people from beginners to get knowledged and the experts to get updated in a particular domain. Nevertheless, the evolution of e-learning systems is yet to provide full adaptability to the e-learners due to several weaknesses in the systems. Normally, e-learners have varying degrees of progress in their respective learning methodology. Over a period of time, this affects the e-learners performance while providing the same course to all e-learner. Hence, there is a need to create the adaptive e-learning environment to offer the appropriate e-learning contents to all the e-learners. This proposed work puts forth a fuzzy-based novel, intelligent and adaptive e-learning context for a programming language and offers appropriate domain contents to the e-learners which shall update the e-learners better than the previous works. The dependency relation among the concepts in the programming language is provided using fuzzy cognitive map which in turn paves the way for the development of the existing e-learning system. The fuzzy sets and the fuzzy rules represent the e-learners knowledge level and help in providing appropriate recommendations for the previous and subsequent related concepts in a fuzzy cognitive map. Evaluations of the proposed intelligent e-learning system provide promising results in the precise categorization of e-learners and to find their true knowledge.
Similar content being viewed by others
References
Khamis M (2011) IDEAL: an intelligent distributed experience-based adaptive learning model. J Arts Humanit 20(1)
Akbulut Y, Cardak CS (2012) Adaptive educational hypermedia accommodating learning styles: a content analysis of publications from 2000 to 2011. Comput Educ 58:835–842
Zadeh LA (1996) Fuzzy logic = computing with words. IEEE Trans Fuzzy Syst 4:103–111
Mendel JM (2001) Uncertain rule-based fuzzy logic systems: introduction and new directions. Prentice-Hall, Upper Saddle River
Castillo O, Melin P (2008) Type-2 fuzzy logic theory and applications. Springer, Berlin
Cara AB, Wagner C, Hagras H, Pomares HC, Rojas I (2013) Multiobjective optimization and comparison of nonsingleton type-1 and singleton interval type-2 fuzzy logic systems. IEEE Trans Fuzzy Syst 21:459–476
Chrysafiadi K, Virvou M (2012) Using fuzzy cognitive maps for the domain knowledge representation of an adaptive e-learning system. In: Proceedings of the 10th joint conference on knowledge—based software engineering, Rhodes
Schneider M, Shnaider E, Kandel A, Chew G (1995) Constructing fuzzy cognitive maps. In: Proceedings of 1995 IEEE international conference on fuzzy systems, pp 2281–2288
Salmeron JL, Vidal R, Mena A (2012) Ranking fuzzy cognitive map based scenarios with TOPSIS. Expert Syst Appl 39:2443–2450
Kumar A (2005) Rule-based adaptive problem generation in programming tutors and its evaluation. In: Proceedings of 12th international conference on artificial intelligence in education, Amsterdam, pp 35–43
Aguilar J (2005) A survey about fuzzy cognitive maps papers (invited paper). Int J Comput Cognit 3:27–33
Tsiriga V, Virvou M (2003) Evaluation of an intelligent web-based language tutor. In: Proceedings of 7th international conference on knowledge-based intelligent information & engineering systems, University of Oxford, pp 275–281
Kavčič A (2004) Fuzzy user modeling for adaptation in educational hypermedia. IEEE Trans Syst Man Cybern Part C Appl Rev 34:439–449
Alves P, Amaral L, Pires J (2008) Case-based reasoning approach to adaptive web-based educational systems. In: Proceedings of eighth IEEE international conference on advanced learning technologies (ICALT ‘08), Santander, pp 260–261
Xin X, Law R, Chen W, Tang L (2016) Forecasting tourism demand by extracting fuzzy Takagi–Sugeno rules from trained SVMs. CAAI Trans Intell Technol 1:30–42
Bhattacharya S, Roy S, Chowdhury S (2018) A Neural Network-based intelligent cognitive state recognizer for confidence-based e-learning system. Neural Comput Appl 29:205–219
Acampora G, Gaeta M, Loia V (2011) Hierarchical optimization of personalized experiences for e-Learning systems through evolutionary models. Neural Comput Appl 20:641–657
Wang Z, Xie L, Ting L (2016) Research Progress of artificial psycology and artificial emotion in china. CAAI Trans Intell Technol 1:355–365
Jegatha Deborah L, Sathiyaseelan R, Audithan S, Vijiayakumar P (2015) Fuzzy logic-based learning style prediction in e-learning using web interface information. Springer Sadhana Indian Acad Sci 40:379–394
Chrysafiadi K, Virvou M (2015) Fuzzy Logic for adaptive instruction for e-learning environment for computer programming. IEEE Trans Fuzzy Syst 23:164–177
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix
Appendix
- Rule1:
-
If α (βi) = Unknown and α (βj) = Learned, then α (βj) = Unknown
µUn (βj) = µUn (βi) * µγ (βi, βj)
- Rule2:
-
If α (βi) = Unknown and α (βj) = Known, then α (βj) = Unknown
µUn (βj) = µUn (βi) * µγ (βi, βj)
- Rule3:
-
If α (βi) = Unknown and α (βj) = Insufficiently known, then α (βj) = Unknown
µUn (βj) = µUn (βi) * µγ (βi, βj)
- Rule4:
-
If α (βi) = Insufficiently known and α (βj) = learned, then α (βj) = Insufficiently known
µInk (βj) = µInk (βi) * µγ (βi, βj)
- Rule5:
-
If α (βi) = Insufficiently known and α (βj) = Known, then α (βj) = Insufficiently known
µInk (βj) = µInk (βi) * µγ (βi, βj)
- Rule6:
-
If α (βi) = Insufficiently known and α (βj) = Unknown, then α (βj) = Insufficiently known
µInk (βj) = µInk (βi) * µγ (βi, βj)
- Rule7:
-
If α (βi) = Known and α (βj) = Learned, then α (βj) = Known
µK (βj) = µK (βi) * µγ (βi, βj)
- Rule8:
-
If α (βi) = Known and α (βj) = Insufficiently known, then α (βj) = Known
µK (βj) = µK (βi) * µγ (βi, βj)
- Rule9:
-
If α (βi) = Known and α (βj) = Unknown, then α (βj) = Known
µK (βj) = µK (βi) * µγ (βi, βj)
- Rule10:
-
If α (βi) = Learned and α (βj) = Known, then α (βj) = Learned
µL (βj) = µL (βi) * µγ (βi, βj)
- Rule11:
-
If α (βi) = Learned and α (βj) = Insufficiently known, then α (βj) = Learned
µL (βj) = µL (βi) * µγ (βi, βj)
- Rule12:
-
If α (βi) = Learned and α (βj) = Unknown, then α (βj) = Learned
µL (βj) = µL (βi) * µγ (βi, βj)
- Rule13:
-
If α (βi) = Assimilated and α (βj) = Known, then α (βj) = Assimilated
µA (βj) = µA (βi) * µγ (βi, βj)
- Rule14:
-
If α (βi) = Assimilated and α (βj) = Unknown, then α (βj) = Assimilated
µA (βj) = µA (βi) * µγ (βi, βj)
- Rule15:
-
If α (βi) = Assimilated and α (βj) = Learned, then α (βj) = Assimilated
µA (βj) = µA (βi) * µγ (βi, βj)
- Rule16:
-
If α (βi) = Assimilated and α (βj) = Insufficiently known, then α (βj) = Assimilated
µA (βj) = µA (βi) * µγ (βi, βj)
- Rule17:
-
If α (βi) = learned and α (βj) = unknown, then α (βi) = Unknown
µUn = µUn (βi) * µγ (βj, βi)
- Rule18:
-
If α (βi) = Assimilated and α (βj) = Unknown, then α (βi) = Unknown
µUn = µUn (βi) * µγ (βj, βi)
- Rule19:
-
If α (βi) = Learned and α (βj) = Insufficiently known, then α (βi) = Insufficiently known
µInk (Ci) = µInk (βi) * µγ (βj, βi)
- Rule20:
-
If α (βi) = Assimilated and α (βj) = Insufficiently known, then α (βi) = Insufficiently known
µInk (Ci) = µInk (βi) * µγ (βj, βi)
- Rule21:
-
If α (βi) = Learned and α (βj) = Known, then α (βi) = Known
µK (Ci) = µK (βi) * µγ (βj, βi)
- Rule22:
-
If α (βi) = Assimilated and α (βj) = Known, then α (βi) = Known
µK (βi) = µK (βi) * µγ (βj, βi)
- Rule23:
-
If α (βi) = Learned and α (βj) = Learned, then α (βi) = Learned
µL (βi) = µL (βi) * µγ (βj, βi)
- Rule24:
-
If α (βi) = Assimilated and α (βj) = Learned, then α (βi) = Learned
µL (βi) = µL (βi) * µγ (βj, βi)
- Rule25:
-
If α (βi) = Learned and α (βj) = Assimilated, then α (βi) = Assimilated
µA (βi) = µA (βi) * µγ (βj, βi)
- Rule26:
-
If α (βi) = Assimilated and α (βj) = Assimilated, then α (βi) = Assimilated
µA (βi) = µA (βi) * µγ (βj, βi)
Rights and permissions
About this article
Cite this article
Karthika, R., Jegatha Deborah, L. & Vijayakumar, P. Intelligent e-learning system based on fuzzy logic. Neural Comput & Applic 32, 7661–7670 (2020). https://doi.org/10.1007/s00521-019-04087-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-019-04087-y