Framework for Electroencephalography-based Evaluation of User Experience
summary
A software-and-EEG pipeline extracts spectral, ERP and spatial features to estimate workload, attention and error recognition; calibration uses an n-back task (producing high classification accuracy) and transfers to a 3D maze that produces four validated workload levels (confirmed by NASA-TLX). Applying the classifier to game sessions yields a continuous workload index that rises with difficulty and separates keyboard from touchscreen control (touchscreen shows higher workload). Hardware ranges from g.tec rigs to an OpenBCI-based headset.
AI-written summary · about
chapters (15)
- 0:00Introduction to EEG framework
- 1:04Evaluating new interfaces
- 2:30Physiological signals in UX
- 3:54EEG signal processing
- 5:21Measuring workload
- 6:45Validating EEG with ground truth
- 7:283D maze application
- 9:16Questionnaire results
- 10:24Training computer to detect workload
- 11:47Testing EEG on complex tasks
- 13:15Continuous workload measurement
- 14:20Measuring multiple UX dimensions
- 15:03Limitations of EEG
- 16:29Summary and future work
- 17:33Q&A session
related talks
13mEnhanced EEG Data Classification with 3D SNN and On-Line Learning ESN
07mAssessing Cognitive Performance Using Physiological and Facial Features: Generalizing Across ...
10mVirtual Reality platform for functional Magnetic Resonance Imaging in Ecologically valid conditions
05mBrain Computer Interface: Reading Human Brains Using Deep Learning
09mUsing Gaze Behavior and Head Orientation for Implicit Identification in Virtual Reality
21mSelf-Calibrating Head-Mounted Eye Trackers Using Egocentric Visual Saliency
09mMind control, x-Ray vision, and Flight superpowers
20mNo Need to Laugh Out Loud: Predicting Humor Appraisal of Comic Strips Based on Physiological ...