Abstract

Detecting a user's intentions is critical in human-computer interactions. Recently, brain-computer interfaces (BCIs) have been extensively studied to facilitate more accurate detection and prediction of the user's intentions. Specifically, various deep learning approaches have been applied to the BCIs for decoding the user's intent from motor-imagery electroencephalography (EEG) signals. However, their ability to capture the important features of an EEG signal remains limited, resulting in the deterioration of performance. In this paper, we propose a multi-layer temporal pyramid pooling approach to improve the performance of motor imagery-based BCIs. The proposed scheme introduces the application of multilayer multiscale pooling and fusion methods to capture various features of an EEG signal, which can be easily integrated into modern convolutional neural networks (CNNs). The experimental results based on the BCI competition IV dataset indicate that the CNN architectures with the proposed multilayer pyramid pooling method enhance classification performance compared to the original networks.

Highlights

  • Detecting a user’s intent correctly and providing them appropriate information or service on time is essential in human–computer interactions (HCIs)

  • TEMPORAL PYRAMID POOLING LAYER we describe the architecture of the proposed multilayer temporal pyramid pooling (TPP) approach

  • WORK In this paper, we discussed the concept of pyramid pooling designed to improve the performance of convolutional neural networks (CNNs)

Read more

Summary

INTRODUCTION

Detecting a user’s intent correctly and providing them appropriate information or service on time is essential in human–computer interactions (HCIs). Various interaction methods, such as eye tracking, gesture recognition, and brain signal-based approaches, have been proposed to detect a user’s intentions more accurately, thereby improving the user experience in HCI. The authors of [20] observed that the multilevel pooling strategy was helpful in learning the various perspectives of the features when training the models for image classification and object detection tasks. The results from [20] validated that multilevel (or multiscale) feature extraction and fusion helps in extracting more informative data from the network It contributes to improving the performance of the original network for various tasks. This study aims to discuss the feasibility of a multilevel pooling approach to decode EEG signals for MI-based BCI applications.

RELATED WORK
MOTOR IMAGERY EEG CLASSIFICATION WITH CNNs
Findings
CONCLUSION AND FUTURE WORK
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