Classification of brainwaves using convolutional neural network

Swapnil R. Joshi, Drew B. Headley, K. C. Ho, Denis Paré, Satish S. Nair

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Scopus citations

Abstract

Classification of brainwaves in recordings is of considerable interest to neuroscience and medical communities. Classification techniques used presently depend on the extraction of low-level features from the recordings, which in turn affects the classification performance. To alleviate this problem, this paper proposes an end-to-end approach using Convolutional Neural Network (CNN) which has been shown to detect complex patterns in a signal by exploiting its spatiotemporal nature. The present study uses time and frequency axes for the classification using synthesized Local Field Potential (LFP) data. The results are analyzed and compared with the FFT technique. In all the results, the CNN outperforms the FFT by a significant margin especially when the noise level is high. This study also sheds light on certain signal characteristics affecting network performance.

Original languageEnglish (US)
Title of host publicationEUSIPCO 2019 - 27th European Signal Processing Conference
PublisherEuropean Signal Processing Conference, EUSIPCO
ISBN (Electronic)9789082797039
DOIs
StatePublished - Sep 2019
Event27th European Signal Processing Conference, EUSIPCO 2019 - A Coruna, Spain
Duration: Sep 2 2019Sep 6 2019

Publication series

NameEuropean Signal Processing Conference
Volume2019-September
ISSN (Print)2219-5491

Conference

Conference27th European Signal Processing Conference, EUSIPCO 2019
Country/TerritorySpain
CityA Coruna
Period9/2/199/6/19

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering

Keywords

  • Brainwaves Classification
  • Convolutional Neural Network (CNN)
  • Deep Learning
  • FFT
  • Fourier Transform

Fingerprint

Dive into the research topics of 'Classification of brainwaves using convolutional neural network'. Together they form a unique fingerprint.

Cite this