Webbläsaren som du använder stöds inte av denna webbplats. Alla versioner av Internet Explorer stöds inte längre, av oss eller Microsoft (läs mer här: * https://www.microsoft.com/en-us/microsoft-365/windows/end-of-ie-support).

Var god och använd en modern webbläsare för att ta del av denna webbplats, som t.ex. nyaste versioner av Edge, Chrome, Firefox eller Safari osv.

Default user image.

Bo Bernhardsson

Modellering och styrning av osäkra system. Programdirektör för masterprogrammet i maskininlärning, system och styrning.

Default user image.

Improving EEG-based decoding of the locus of auditory attention through domain adaptation

Författare

  • Johanna Wilroth
  • Bo Bernhardsson
  • Frida Heskebeck
  • Martin A Skoglund
  • Carolina Bergeling
  • Emina Alickovic

Summary, in English

This paper presents a novel domain adaptation framework to enhance the accuracy of EEG-based auditory attention classification, specifically for classifying the direction (left or right) of attended speech. The framework aims to improve the performances for subjects with initially low classification accuracy, overcoming challenges posed by instrumental and human factors. Limited dataset size, variations in EEG data quality due to factors such as noise, electrode misplacement or subjects, and the need for generalization across different trials, conditions and subjects necessitate the use of domain adaptation methods. By leveraging domain adaptation methods, the framework can learn from one EEG dataset and adapt to another, potentially resulting in more reliable and robust classification models.
Approach: This paper focuses on investigating a domain adaptation method, based on parallel transport, for addressing the auditory attention classification problem. The EEG data utilized in this study originates from an experiment where subjects were instructed to selectively attend to one of the two spatially separated voices presented simultaneously.
Main results: Significant improvement in classification accuracy was observed when poor data from one subject was transported to the domain of good data from different subjects, as compared to the baseline. The mean classification accuracy for subjects with poor data increased from 45.84% to 67.92%. Specifically, the highest achieved classification accuracy from one subject reached 83.33%, a substantial increase from the baseline accuracy of 43.33%. 
Significance: The findings of our study demonstrate the improved classification performances achieved through the implementation of domain adaptation methods. This brings us a step closer to leveraging EEG in neuro-steered hearing devices.

Avdelning/ar

  • LU profilområde: Naturlig och artificiell kognition
  • LTH profilområde: AI och digitalisering
  • LTH profilområde: Teknik för hälsa
  • Institutionen för reglerteknik
  • ELLIIT: the Linköping-Lund initiative on IT and mobile communication

Publiceringsår

2023

Språk

Engelska

Publikation/Tidskrift/Serie

Journal of Neural Engineering

Dokumenttyp

Artikel i tidskrift

Förlag

IOP Publishing

Ämne

  • Control Engineering

Status

Published

Projekt

  • Optimizing the Next Generation Brain Computer Interfaces using Cloud Computing

ISBN/ISSN/Övrigt

  • ISSN: 1741-2560