Abstract

Target image detection based on a rapid serial visual presentation (RSVP) paradigm is a typical brain-computer interface system with various applications, such as image retrieval. In an RSVP paradigm, a P300 component is detected to determine target images. This strategy requires high-precision single-trial P300 detection methods. However, the performance of single-trial detection methods is relatively lower than that of multitrial P300 detection methods. Image retrieval based on multitrial P300 is a new research direction. In this paper, we propose a triple-RSVP paradigm with three images being presented simultaneously and a target image appearing three times. Thus, multitrial P300 classification methods can be used to improve detection accuracy. In this study, these mechanisms were extended and validated, and the characteristics of the multi-RSVP framework were further explored. Two different P300 detection algorithms were also utilized in multi-RSVP to demonstrate that the scheme is universally applicable. Results revealed that the detection accuracy of the multi-RSVP paradigm was higher than that of the standard RSVP paradigm. The results validate the effectiveness of the proposed method, and this method can provide a whole new idea in the field of EEG-based target detection.

Highlights

  • A brain-computer interface (BCI) is an advanced humanmachine interaction technology that uses a person’s electroencephalogram (EEG) and analyzes his/her intentions to interact with the external environment directly

  • Target image detection based on a rapid serial visual presentation (RSVP) paradigm is a typical BCI application [1, 2]

  • The P300 component is detected in the RSVP paradigm to determine the target image of a subject of interest

Read more

Summary

Introduction

A brain-computer interface (BCI) is an advanced humanmachine interaction technology that uses a person’s electroencephalogram (EEG) and analyzes his/her intentions to interact with the external environment directly. In the RSVP paradigm, the latency and amplitude of P300 components may vary with different experimental parameters [8], such as target probability and stimulus semantics This variation is a great challenge for single-trial EEG classification in RSVP tasks. Marathe et al [18, 19] developed the sliding HDCA (sHDCA) algorithm, which involves standard HDCA evaluation formulated in a typical P300 interval (300–600 ms), and a standard HDCA classifier is slid on single-trial EEG to form a score signal With this special method of dimension reduction, the imperceptible variation latency of P300 in single-trial EEG data can adapt to the different conditions of subjects. Cecotti et al [20] developed a spatiotemporal filter that uses the map matrix of a convolutional neural network classifier input layer to a second hidden layer These algorithms are effective single-trial detection methods, and the target image is assumed to appear only once.

Methods
Results
Discussion
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