Stochasticity as a solution for overfitting—A new model and comparative study on non-invasive EEG prospects
The potential and utility of inner speech is pivotal for developing practical, everyday Brain-Computer Interface (BCI) applications, as it represents a type of brain signal that operates independently of external stimuli however it is largely underdeveloped due to the challenges faced in deciphering...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Human Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2025.1484470/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589838141882368 |
|---|---|
| author | Yousef A. Radwan Eslam Ahmed Mohamed Donia Metwalli Mariam Barakat Anas Ahmed Antony E. Kiroles Sahar Selim |
| author_facet | Yousef A. Radwan Eslam Ahmed Mohamed Donia Metwalli Mariam Barakat Anas Ahmed Antony E. Kiroles Sahar Selim |
| author_sort | Yousef A. Radwan |
| collection | DOAJ |
| description | The potential and utility of inner speech is pivotal for developing practical, everyday Brain-Computer Interface (BCI) applications, as it represents a type of brain signal that operates independently of external stimuli however it is largely underdeveloped due to the challenges faced in deciphering its signals. In this study, we evaluated the behaviors of various Machine Learning (ML) and Deep Learning (DL) models on a publicly available dataset, employing popular preprocessing methods as feature extractors to enhance model training. We face significant challenges like subject-dependent variability, high noise levels, and overfitting. To address overfitting in particular, we propose using “BruteExtraTree”: a new classifier which relies on moderate stochasticity inherited from its base model, the ExtraTreeClassifier. This model not only matches the best DL model, ShallowFBCSPNet, in the subject-independent scenario in our experiments scoring 32% accuracy, but also surpasses the state-of-the-art by achieving 46.6% average per-subject accuracy in the subject-dependent case. Our results on the subject-dependent case show promise on the possibility of a new paradigm for using inner speech data inspired from LLM pretraining but we also highlight the crucial need for a drastic change in data recording or noise removal methods to open the way for more practical accuracies in the subject-independent case. |
| format | Article |
| id | doaj-art-547170b4599b4b8382465c1cfef81017 |
| institution | Kabale University |
| issn | 1662-5161 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Human Neuroscience |
| spelling | doaj-art-547170b4599b4b8382465c1cfef810172025-01-24T07:13:55ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612025-01-011910.3389/fnhum.2025.14844701484470Stochasticity as a solution for overfitting—A new model and comparative study on non-invasive EEG prospectsYousef A. RadwanEslam Ahmed MohamedDonia MetwalliMariam BarakatAnas AhmedAntony E. KirolesSahar SelimThe potential and utility of inner speech is pivotal for developing practical, everyday Brain-Computer Interface (BCI) applications, as it represents a type of brain signal that operates independently of external stimuli however it is largely underdeveloped due to the challenges faced in deciphering its signals. In this study, we evaluated the behaviors of various Machine Learning (ML) and Deep Learning (DL) models on a publicly available dataset, employing popular preprocessing methods as feature extractors to enhance model training. We face significant challenges like subject-dependent variability, high noise levels, and overfitting. To address overfitting in particular, we propose using “BruteExtraTree”: a new classifier which relies on moderate stochasticity inherited from its base model, the ExtraTreeClassifier. This model not only matches the best DL model, ShallowFBCSPNet, in the subject-independent scenario in our experiments scoring 32% accuracy, but also surpasses the state-of-the-art by achieving 46.6% average per-subject accuracy in the subject-dependent case. Our results on the subject-dependent case show promise on the possibility of a new paradigm for using inner speech data inspired from LLM pretraining but we also highlight the crucial need for a drastic change in data recording or noise removal methods to open the way for more practical accuracies in the subject-independent case.https://www.frontiersin.org/articles/10.3389/fnhum.2025.1484470/fullEEGbrain-computer interfaceinner speechmachine learningdeep learning |
| spellingShingle | Yousef A. Radwan Eslam Ahmed Mohamed Donia Metwalli Mariam Barakat Anas Ahmed Antony E. Kiroles Sahar Selim Stochasticity as a solution for overfitting—A new model and comparative study on non-invasive EEG prospects Frontiers in Human Neuroscience EEG brain-computer interface inner speech machine learning deep learning |
| title | Stochasticity as a solution for overfitting—A new model and comparative study on non-invasive EEG prospects |
| title_full | Stochasticity as a solution for overfitting—A new model and comparative study on non-invasive EEG prospects |
| title_fullStr | Stochasticity as a solution for overfitting—A new model and comparative study on non-invasive EEG prospects |
| title_full_unstemmed | Stochasticity as a solution for overfitting—A new model and comparative study on non-invasive EEG prospects |
| title_short | Stochasticity as a solution for overfitting—A new model and comparative study on non-invasive EEG prospects |
| title_sort | stochasticity as a solution for overfitting a new model and comparative study on non invasive eeg prospects |
| topic | EEG brain-computer interface inner speech machine learning deep learning |
| url | https://www.frontiersin.org/articles/10.3389/fnhum.2025.1484470/full |
| work_keys_str_mv | AT yousefaradwan stochasticityasasolutionforoverfittinganewmodelandcomparativestudyonnoninvasiveeegprospects AT eslamahmedmohamed stochasticityasasolutionforoverfittinganewmodelandcomparativestudyonnoninvasiveeegprospects AT doniametwalli stochasticityasasolutionforoverfittinganewmodelandcomparativestudyonnoninvasiveeegprospects AT mariambarakat stochasticityasasolutionforoverfittinganewmodelandcomparativestudyonnoninvasiveeegprospects AT anasahmed stochasticityasasolutionforoverfittinganewmodelandcomparativestudyonnoninvasiveeegprospects AT antonyekiroles stochasticityasasolutionforoverfittinganewmodelandcomparativestudyonnoninvasiveeegprospects AT saharselim stochasticityasasolutionforoverfittinganewmodelandcomparativestudyonnoninvasiveeegprospects |