Detecting SSVEP with Minimal Channels using CNN-Based Deep Learning Approach

Published on May 19, 2022

Imagine you’re a detective trying to find a hidden treasure in a crowded room. The treasure is the SSVEP signal, a type of brain activity that can be used for brain-computer interfaces (BCI). However, this signal is strongest in the visual cortex, making it difficult to detect from other areas of the head. But fear not! Scientists have come up with a clever solution using binaural ear-EEG. They developed a CNN-based deep learning approach that focuses on detecting SSVEP around both ears, using minimal channels. By training their model on a public dataset, they achieved an impressive 69.21% accuracy, surpassing previous single-ear implementations by 12.47%. This promising approach holds great potential for practical implementation of wearable EEG devices and could greatly enhance the performance of BCI applications. If you’re interested in diving deeper into their research, check out the full article.

This paper discusses a machine learning approach for detecting SSVEP at both ears with minimal channels. SSVEP is a robust EEG signal suitable for many BCI applications. It is strong at the visual cortex around the occipital area, but the SNR gets worse when detected from other areas of the head. To make use of SSVEP measured around the ears following the ear-EEG concept, especially for practical binaural implementation, we propose a CNN structure coupled with regressed softmax outputs to improve accuracy. Evaluating on a public dataset, we studied classification performance for both subject-dependent and subject-independent trainings. It was found that with the proposed structure using a group training approach, a 69.21% accuracy was achievable. An ITR of 6.42 bit/min given 63.49 % accuracy was recorded while only monitoring data from T7 and T8. This represents a 12.47% improvement from a single ear implementation and illustrates potential of the approach to enhance performance for practical implementation of wearable EEG.

Read Full Article (External Site)

Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes:

<a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>