Feature Generation with Genetic Algorithms for Imagined Speech Electroencephalogram Signal Classification

This work presents a method for classifying EEG (Electroencephalogram) signals generated when a person concentrates on specific words, defined as “Imagined Speech”. Imagined speech is essential to enhance problem-solving, memory, and language development. In addition, imagined speech is beneficial b...

Full description

Saved in:
Bibliographic Details
Main Authors: Edgar Lara-Arellano, Andras Takacs, Saul Tovar-Arriaga, Juvenal Rodríguez-Reséndiz
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Eng
Subjects:
Online Access:https://www.mdpi.com/2673-4117/6/4/75
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849714131210338304
author Edgar Lara-Arellano
Andras Takacs
Saul Tovar-Arriaga
Juvenal Rodríguez-Reséndiz
author_facet Edgar Lara-Arellano
Andras Takacs
Saul Tovar-Arriaga
Juvenal Rodríguez-Reséndiz
author_sort Edgar Lara-Arellano
collection DOAJ
description This work presents a method for classifying EEG (Electroencephalogram) signals generated when a person concentrates on specific words, defined as “Imagined Speech”. Imagined speech is essential to enhance problem-solving, memory, and language development. In addition, imagined speech is beneficial because of its applications in therapy fields like managing anxiety or improving communication skills. EEG measures the electrical activity of the brain. EEG signal classification is difficult as the machine learning (ML) algorithm has to learn how to categorize the signal linked to the imagined word. This work proposes a novel method to generate a specific feature vector to achieve classification with superior accuracy results to those found in the state of the art. The method leverages a genetic algorithm to create an optimal feature combination for the classification task and machine learning model. This algorithm can efficiently explore ample feature space and identify the most relevant features for the task. The proposed method achieved an accuracy of 96% using eight electrodes for EEG signal recordings.
format Article
id doaj-art-df8e5c503a254fa98e67142ba36bc96f
institution DOAJ
issn 2673-4117
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Eng
spelling doaj-art-df8e5c503a254fa98e67142ba36bc96f2025-08-20T03:13:47ZengMDPI AGEng2673-41172025-04-01647510.3390/eng6040075Feature Generation with Genetic Algorithms for Imagined Speech Electroencephalogram Signal ClassificationEdgar Lara-Arellano0Andras Takacs1Saul Tovar-Arriaga2Juvenal Rodríguez-Reséndiz3Facultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MexicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MexicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MexicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Querétaro 76010, MexicoThis work presents a method for classifying EEG (Electroencephalogram) signals generated when a person concentrates on specific words, defined as “Imagined Speech”. Imagined speech is essential to enhance problem-solving, memory, and language development. In addition, imagined speech is beneficial because of its applications in therapy fields like managing anxiety or improving communication skills. EEG measures the electrical activity of the brain. EEG signal classification is difficult as the machine learning (ML) algorithm has to learn how to categorize the signal linked to the imagined word. This work proposes a novel method to generate a specific feature vector to achieve classification with superior accuracy results to those found in the state of the art. The method leverages a genetic algorithm to create an optimal feature combination for the classification task and machine learning model. This algorithm can efficiently explore ample feature space and identify the most relevant features for the task. The proposed method achieved an accuracy of 96% using eight electrodes for EEG signal recordings.https://www.mdpi.com/2673-4117/6/4/75imagined speechEEGfeature extractiongenetic algorithmclassificationoptimization algorithms
spellingShingle Edgar Lara-Arellano
Andras Takacs
Saul Tovar-Arriaga
Juvenal Rodríguez-Reséndiz
Feature Generation with Genetic Algorithms for Imagined Speech Electroencephalogram Signal Classification
Eng
imagined speech
EEG
feature extraction
genetic algorithm
classification
optimization algorithms
title Feature Generation with Genetic Algorithms for Imagined Speech Electroencephalogram Signal Classification
title_full Feature Generation with Genetic Algorithms for Imagined Speech Electroencephalogram Signal Classification
title_fullStr Feature Generation with Genetic Algorithms for Imagined Speech Electroencephalogram Signal Classification
title_full_unstemmed Feature Generation with Genetic Algorithms for Imagined Speech Electroencephalogram Signal Classification
title_short Feature Generation with Genetic Algorithms for Imagined Speech Electroencephalogram Signal Classification
title_sort feature generation with genetic algorithms for imagined speech electroencephalogram signal classification
topic imagined speech
EEG
feature extraction
genetic algorithm
classification
optimization algorithms
url https://www.mdpi.com/2673-4117/6/4/75
work_keys_str_mv AT edgarlaraarellano featuregenerationwithgeneticalgorithmsforimaginedspeechelectroencephalogramsignalclassification
AT andrastakacs featuregenerationwithgeneticalgorithmsforimaginedspeechelectroencephalogramsignalclassification
AT saultovararriaga featuregenerationwithgeneticalgorithmsforimaginedspeechelectroencephalogramsignalclassification
AT juvenalrodriguezresendiz featuregenerationwithgeneticalgorithmsforimaginedspeechelectroencephalogramsignalclassification