Abstract

Itelligent tutoring systems (ITS) can be improved by considering real time information from phsysiological signals. For example, performance could be predicted based on the user’s affective state. In this chapter a feature extraction approach is presented to try to predict when a user makes a mistake while interacting in a dynamic learning environment (DLE). Electroencephalogram (EEG) signals from participants were recorded and used as inputs in a random forest. Three approaches were followed: in the first one we used the affective states provided by a commercial headset, in the second approach we additionally considered the affective state rate of change and finally we used the 14 channels raw information generated by the EEG after applyinga Fast Fourier Transformation (FFT) to calculate the Power Spectral Density (PSD). Results show that random forest provides high accuracy in the three approaches that were followed. Further, key results show an extensive analysis of feature importance which helped identify the relevant affective states, bandwidths and sensors. Lessons learned can be incorporated into the desing of intelligent tutoring sytems.

Original languageEnglish (US)
Title of host publicationIntelligent Tutoring Systems
Subtitle of host publicationStructure, Applications and Challenges
PublisherNova Science Publishers, Inc.
Pages105-128
Number of pages24
ISBN (Electronic)9781634852111
ISBN (Print)9781634851671
StatePublished - Jan 1 2016

Fingerprint

Electroencephalography
Power spectral density
Feature extraction
Bandwidth
Sensors

Keywords

  • Affective computing
  • Affective states
  • BCI
  • Dynamic learning environments
  • Electroencephalogram (EEG)
  • Feature importance
  • Intelligent tutoring systems (ITS)
  • Physiological signals
  • Random forest

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Lujan-Moreno, G. A., Atkinson, R., & Runger, G. (2016). EEG-based user performance prediction using random forest in a dynamic learning environment. In Intelligent Tutoring Systems: Structure, Applications and Challenges (pp. 105-128). Nova Science Publishers, Inc..

EEG-based user performance prediction using random forest in a dynamic learning environment. / Lujan-Moreno, Gustavo A.; Atkinson, Robert; Runger, George.

Intelligent Tutoring Systems: Structure, Applications and Challenges. Nova Science Publishers, Inc., 2016. p. 105-128.

Research output: Chapter in Book/Report/Conference proceedingChapter

Lujan-Moreno, GA, Atkinson, R & Runger, G 2016, EEG-based user performance prediction using random forest in a dynamic learning environment. in Intelligent Tutoring Systems: Structure, Applications and Challenges. Nova Science Publishers, Inc., pp. 105-128.
Lujan-Moreno GA, Atkinson R, Runger G. EEG-based user performance prediction using random forest in a dynamic learning environment. In Intelligent Tutoring Systems: Structure, Applications and Challenges. Nova Science Publishers, Inc. 2016. p. 105-128
Lujan-Moreno, Gustavo A. ; Atkinson, Robert ; Runger, George. / EEG-based user performance prediction using random forest in a dynamic learning environment. Intelligent Tutoring Systems: Structure, Applications and Challenges. Nova Science Publishers, Inc., 2016. pp. 105-128
@inbook{82d4297edcd54d58956d5f61c1a2ad03,
title = "EEG-based user performance prediction using random forest in a dynamic learning environment",
abstract = "Itelligent tutoring systems (ITS) can be improved by considering real time information from phsysiological signals. For example, performance could be predicted based on the user’s affective state. In this chapter a feature extraction approach is presented to try to predict when a user makes a mistake while interacting in a dynamic learning environment (DLE). Electroencephalogram (EEG) signals from participants were recorded and used as inputs in a random forest. Three approaches were followed: in the first one we used the affective states provided by a commercial headset, in the second approach we additionally considered the affective state rate of change and finally we used the 14 channels raw information generated by the EEG after applyinga Fast Fourier Transformation (FFT) to calculate the Power Spectral Density (PSD). Results show that random forest provides high accuracy in the three approaches that were followed. Further, key results show an extensive analysis of feature importance which helped identify the relevant affective states, bandwidths and sensors. Lessons learned can be incorporated into the desing of intelligent tutoring sytems.",
keywords = "Affective computing, Affective states, BCI, Dynamic learning environments, Electroencephalogram (EEG), Feature importance, Intelligent tutoring systems (ITS), Physiological signals, Random forest",
author = "Lujan-Moreno, {Gustavo A.} and Robert Atkinson and George Runger",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
isbn = "9781634851671",
pages = "105--128",
booktitle = "Intelligent Tutoring Systems",
publisher = "Nova Science Publishers, Inc.",

}

TY - CHAP

T1 - EEG-based user performance prediction using random forest in a dynamic learning environment

AU - Lujan-Moreno, Gustavo A.

AU - Atkinson, Robert

AU - Runger, George

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Itelligent tutoring systems (ITS) can be improved by considering real time information from phsysiological signals. For example, performance could be predicted based on the user’s affective state. In this chapter a feature extraction approach is presented to try to predict when a user makes a mistake while interacting in a dynamic learning environment (DLE). Electroencephalogram (EEG) signals from participants were recorded and used as inputs in a random forest. Three approaches were followed: in the first one we used the affective states provided by a commercial headset, in the second approach we additionally considered the affective state rate of change and finally we used the 14 channels raw information generated by the EEG after applyinga Fast Fourier Transformation (FFT) to calculate the Power Spectral Density (PSD). Results show that random forest provides high accuracy in the three approaches that were followed. Further, key results show an extensive analysis of feature importance which helped identify the relevant affective states, bandwidths and sensors. Lessons learned can be incorporated into the desing of intelligent tutoring sytems.

AB - Itelligent tutoring systems (ITS) can be improved by considering real time information from phsysiological signals. For example, performance could be predicted based on the user’s affective state. In this chapter a feature extraction approach is presented to try to predict when a user makes a mistake while interacting in a dynamic learning environment (DLE). Electroencephalogram (EEG) signals from participants were recorded and used as inputs in a random forest. Three approaches were followed: in the first one we used the affective states provided by a commercial headset, in the second approach we additionally considered the affective state rate of change and finally we used the 14 channels raw information generated by the EEG after applyinga Fast Fourier Transformation (FFT) to calculate the Power Spectral Density (PSD). Results show that random forest provides high accuracy in the three approaches that were followed. Further, key results show an extensive analysis of feature importance which helped identify the relevant affective states, bandwidths and sensors. Lessons learned can be incorporated into the desing of intelligent tutoring sytems.

KW - Affective computing

KW - Affective states

KW - BCI

KW - Dynamic learning environments

KW - Electroencephalogram (EEG)

KW - Feature importance

KW - Intelligent tutoring systems (ITS)

KW - Physiological signals

KW - Random forest

UR - http://www.scopus.com/inward/record.url?scp=85034761920&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85034761920&partnerID=8YFLogxK

M3 - Chapter

AN - SCOPUS:85034761920

SN - 9781634851671

SP - 105

EP - 128

BT - Intelligent Tutoring Systems

PB - Nova Science Publishers, Inc.

ER -