Abstract

Electroencephalogram data are easily affected by artifacts, and a drift may occur during the signal acquisition process. At present, most research focuses on the automatic detection and elimination of artifacts in electrooculograms, electromyograms and electrocardiograms. However, electroencephalogram drift data, which affect the real-time performance, are mainly manually calibrated and abandoned. An emotion classification method based on 1/f fluctuation theory is proposed to classify electroencephalogram data without removing artifacts and drift data. The results show that the proposed method can still achieve a great classification accuracy of 75% in cases in which artifacts and drift data exist when using the support vector machine classifier. In addition, the real-time performance of the proposed method is guaranteed.

Highlights

  • Electroencephalogram (EEG) signals are time-varying and highly sensitive to various artifacts and interference.[1,2] For example, when the subject slightly moved his or her head, signals of many electrodes significantly undulated during acquisition, that is, the baselines of those electrodes were unstable

  • There is hardly any literature dealing with EEG drift data in affective computing, which is determined by how EEG data are analyzed

  • The results showed that the EEG drift data will cause significant adverse effects on emotion classification

Read more

Summary

Introduction

Electroencephalogram (EEG) signals are time-varying and highly sensitive to various artifacts and interference.[1,2] For example, when the subject slightly moved his or her head, signals of many electrodes significantly undulated during acquisition, that is, the baselines of those electrodes were unstable. These significant undulations are called ‘‘drift’’ in this paper. The works of rejecting EEG drift data are usually done manually after acquisition, so that the real-time performance (RTP) of data processing cannot be guaranteed. The results showed that the EEG drift data will cause significant adverse effects on emotion classification

Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call