An adaptive strategy to help students in e-Learning systems using competency-based ontology and agents

Bremgartner, Vitor; Netto, José Francisco de Magalhães

doi:10.1109/isda.2011.6121785

Cited by 7 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The goal is to apply visual perception in the teaching-learning process. Bremgartner and de Magalhaes Netto (2011) disabilities to suggest activities or utilizes a pedagogical model that is adequate to the specific necessities of students with disabilities or learning difficulties.…”

Section: Related Workmentioning

confidence: 99%

Kamachiy – Mayistru: adaptive module to support teaching to people with learning difficulties

Lancheros-Cuesta

Carrillo-Ramos

Pavlich-Mariscal

2015

International Journal of Web Information Systems

View full text Add to dashboard Cite

Purpose – The purpose of this paper is to propose Kamachiy-Mayistru (KM), an adaptive module to support teaching to people with learning difficulties. In Colombia, learning disabilities and difficulties are frequent in the integration classroom. Proper learning can be achieved as long as teaching strategies and didactic tools are the most adequate to the specific student characteristics and follow the suggestions given by experts for each learning difficulty. This module assists the teacher to prepare a course taking into account the disability profile, the student profile and pedagogical model suggestions. In this way, the student can learn utilizing the format and didactic tools more appropriate to their specific necessities. Design/methodology/approach – The design and implementation of the KM comprises the following phases: identify the most important student, teacher, difficulties and course parameters to take into account in the adaptation process; design the data model that supports activity adaptation, based on student characteristics and difficulties; implement the platform; and validate the approach through a case study of teachers and their students with difficulties. Findings – The application of KM in the case study indicated the effectiveness of KM to assist teachers in organizing course activities for students with and without disabilities or difficulties. Research limitations/implications – KM addresses specific student difficulties: attention, memory and languages. KM does not address severe cognitive disabilities. Regarding the validation, it is recommended to pursue new case studies to further demonstrate the effectiveness of the approach in a broader population. Practical implications – The main approach in KM is to suggest activities or pedagogical strategies to teachers to best support learning in students with difficulties or disabilities. The core of KM is an algorithm, called “Adapt Course”, that takes as input student and disability profiles, the course contents and the pedagogical model and creates course structures that are specially tailored to each student. Social implications – This model recommends teachers different activities, based on the specific student difficulties, to create personalized courses. It is able to address specific educational issues that are associated with learning difficulties and disabilities, such as educational integration, through content organization and personalized information display, which are based on the inherent characteristics of each student in the classroom. Originality/value – It is based on a conceptual model that provides the essential architecture to design and implement virtual learning environments for students with learning difficulties or disabilities.

show abstract

Section: Related Workmentioning

confidence: 99%

Kamachiy – Mayistru: adaptive module to support teaching to people with learning difficulties

Lancheros-Cuesta

Carrillo-Ramos

Pavlich-Mariscal

2015

International Journal of Web Information Systems

View full text Add to dashboard Cite

show abstract

“…One of them is adaptation to provide services that convey the information to students, according to their particular characteristics and necessities (Bailey et al, 2002). Content adaptation utilizes parameters, such as user preferences (Bailey et al, 2002;Minsky, 1974), goals, knowledge, among other data stored in a user model (Bremgartner and de Magalhaes Netto, 2011), focusing in enriching services and displaying only the information that is accord to those characteristics (Lancheros-Cuesta et al, 2014).…”

Section: Introductionmentioning

confidence: 99%

Evaluation of content adaptation

Lancheros-Cuesta

Carrillo-Ramos

Lancheros-Cuesta³

2019

IJWIS

View full text Add to dashboard Cite

Purpose Students have learning difficulties, mainly in processes that involve attention and interpretation of written or spoken language. Technological tools allow to create computational platforms with adaptation aspects depending on the student’s characteristics. It is also important to highlight the progress of the measurement of cognitive processes such as attention through NeuroSky’s MindWave EEG sensors. This paper aims to present the results of analyzing attention levels of children with learning difficulties, based on the acquired brain waves. As a final result, an adaptive computational system that displays educational activities regarding educational profiles of children is obtained. Design/methodology/approach The Kamachiy–Idukay platform was chosen to make the validation. The platform generates the educational activities according to the students’ profile. The validation phases were identification of the test environment, the first environment required a scenario that involved students with learning difficulties, to verify the functionality of the system, when analyzing cases of the students with learning difficulties; identification of two validation criteria, type of educational activity and attention difficulties of the students; and analysis of the brain signal when children interact with the educational content. Findings The adaptation of contents that include music and animations generate higher levels of attention in students with difficulty. The analysis of signals from the NeuroSky sensor to determine the attentional levels in children allowed a generation of content adapted to the characteristics of the difficulty in each child. Research limitations/implications For the validation, it was necessary at the beginning of the activity to determine the stability of the signal emitted by the NeuroSky sensor. Two cases were studied in children with difficulty and their measure of attention versus adaptive contents. Practical implications A k-means algorithm was used to establish the attention levels of the children. Social implications Children with learning difficulties have different learning styles, which implies an adaptation of content that generates an attentional process according to their characteristics. Originality/value Evaluation content adaptation taking into account the signal brain sensor NeuroSky for learning process. The signal brain of the student when interacting with the activities is include in the student profile.

show abstract

Improving collaborative learning by personalization in Virtual Learning Environments using agents and competency-based ontology

Bremgartner

Netto

2012

2012 Frontiers in Education Conference Proceedings

View full text Add to dashboard Cite

An adaptive strategy to help students in e-Learning systems using competency-based ontology and agents

Cited by 7 publications

References 7 publications

Kamachiy – Mayistru: adaptive module to support teaching to people with learning difficulties

Kamachiy – Mayistru: adaptive module to support teaching to people with learning difficulties

Evaluation of content adaptation

Improving collaborative learning by personalization in Virtual Learning Environments using agents and competency-based ontology

Contact Info

Product

Resources

About