eprintid: 19213
rev_number: 2
eprint_status: archive
userid: 1
dir: disk0/00/01/92/13
datestamp: 2024-06-04 14:11:40
lastmod: 2024-06-04 14:11:40
status_changed: 2024-06-04 14:05:10
type: conference_item
metadata_visibility: show
creators_name: Abdullah, 
creators_name: Faye, I.
creators_name: Islam, M.R.
title: Electroencephalogram Channel Selection using Deep Q-Network
ispublished: pub
keywords: Brain computer interface; Electroencephalography; Markov processes; Reinforcement learning, Channel classification; Channel selection; Deep neural network; Deep Q-network; Deep reinforcement learning; EEG channel classification; Model training; Optimal channels; Reinforcement learnings; Speed up, Deep neural networks
note: cited By 1; Conference of 2023 International Conference on Recent Advances in Electrical, Electronics and Digital Healthcare Technologies, REEDCON 2023 ; Conference Date: 1 May 2023 Through 3 May 2023; Conference Code:189584
abstract: In brain-computer interfaces, electroencephalogram channel selection picks the most informative channels. To speed up the model training and improve accuracy by selecting a small number of optimal channels. In this study, we trained an agent that automatically learned the policy to choose an optimal channel, from given EEG data, even without hand engineering. We frame the problem of EEG channel selection as a Markov decision process (MDP), offer a productive method for parameterizing it, and then apply deep reinforcement learning (DRL) to solve it. After the agent has been trained, it tries to learn a policy for channel selection that directs it to choose channels sequentially while leveraging EEG signals and previously selected tracks. The study also offers two reward systems for the DRL environment simulation and analyzes them in trials. This is the first work to look at a DRL model for EEG data interpretation, opening up a new field of study and highlighting DRL's immense potential in the brain-computer interface. © 2023 IEEE.
date: 2023
official_url: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85163813417&doi=10.1109%2fREEDCON57544.2023.10151281&partnerID=40&md5=34aad657ed0bf25a8827c0c2f07302c6
id_number: 10.1109/REEDCON57544.2023.10151281
full_text_status: none
publication: 2023 International Conference on Recent Advances in Electrical, Electronics and Digital Healthcare Technologies, REEDCON 2023
pagerange: 340-344
refereed: TRUE
citation:   Abdullah and Faye, I. and Islam, M.R.  (2023) Electroencephalogram Channel Selection using Deep Q-Network.  In: UNSPECIFIED.