Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalography
IntroductionParalyzed and physically impaired patients face communication difficulties, even when they are mentally coherent and aware. Electroencephalographic (EEG) brain–computer interfaces (BCIs) offer a potential communication method for these people without invasive surgery or physical device c...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-12-01
|
| Series: | Frontiers in Neuroinformatics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fninf.2023.1306277/full |
| _version_ | 1797387645890854912 |
|---|---|
| author | John LaRocco Qudsia Tahmina Sam Lecian Jason Moore Cole Helbig Surya Gupta |
| author_facet | John LaRocco Qudsia Tahmina Sam Lecian Jason Moore Cole Helbig Surya Gupta |
| author_sort | John LaRocco |
| collection | DOAJ |
| description | IntroductionParalyzed and physically impaired patients face communication difficulties, even when they are mentally coherent and aware. Electroencephalographic (EEG) brain–computer interfaces (BCIs) offer a potential communication method for these people without invasive surgery or physical device controls.MethodsAlthough virtual keyboard protocols are well documented in EEG BCI paradigms, these implementations are visually taxing and fatiguing. All English words combine 44 unique phonemes, each corresponding to a unique EEG pattern. In this study, a complete phoneme-based imagined speech EEG BCI was developed and tested on 16 subjects.ResultsUsing open-source hardware and software, machine learning models, such as k-nearest neighbor (KNN), reliably achieved a mean accuracy of 97 ± 0.001%, a mean F1 of 0.55 ± 0.01, and a mean AUC-ROC of 0.68 ± 0.002 in a modified one-versus-rest configuration, resulting in an information transfer rate of 304.15 bits per minute. In line with prior literature, the distinguishing feature between phonemes was the gamma power on channels F3 and F7.DiscussionHowever, adjustments to feature selection, trial window length, and classifier algorithms may improve performance. In summary, these are iterative changes to a viable method directly deployable in current, commercially available systems and software. The development of an intuitive phoneme-based EEG BCI with open-source hardware and software demonstrates the potential ease with which the technology could be deployed in real-world applications. |
| first_indexed | 2024-03-08T22:29:03Z |
| format | Article |
| id | doaj.art-1559e3c31c2e4aacb9b49f15b7c9e2d1 |
| institution | Directory Open Access Journal |
| issn | 1662-5196 |
| language | English |
| last_indexed | 2024-03-08T22:29:03Z |
| publishDate | 2023-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neuroinformatics |
| spelling | doaj.art-1559e3c31c2e4aacb9b49f15b7c9e2d12023-12-18T07:37:16ZengFrontiers Media S.A.Frontiers in Neuroinformatics1662-51962023-12-011710.3389/fninf.2023.13062771306277Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalographyJohn LaRocco0Qudsia Tahmina1Sam Lecian2Jason Moore3Cole Helbig4Surya Gupta5Wexner Medical Center, The Ohio State University, Columbus, OH, United StatesDepartment of Electrical Engineering, The Ohio State University, Columbus, OH, United StatesDepartment of Electrical Engineering, The Ohio State University, Columbus, OH, United StatesDepartment of Electrical Engineering, The Ohio State University, Columbus, OH, United StatesDepartment of Electrical Engineering, The Ohio State University, Columbus, OH, United StatesDepartment of Electrical Engineering, The Ohio State University, Columbus, OH, United StatesIntroductionParalyzed and physically impaired patients face communication difficulties, even when they are mentally coherent and aware. Electroencephalographic (EEG) brain–computer interfaces (BCIs) offer a potential communication method for these people without invasive surgery or physical device controls.MethodsAlthough virtual keyboard protocols are well documented in EEG BCI paradigms, these implementations are visually taxing and fatiguing. All English words combine 44 unique phonemes, each corresponding to a unique EEG pattern. In this study, a complete phoneme-based imagined speech EEG BCI was developed and tested on 16 subjects.ResultsUsing open-source hardware and software, machine learning models, such as k-nearest neighbor (KNN), reliably achieved a mean accuracy of 97 ± 0.001%, a mean F1 of 0.55 ± 0.01, and a mean AUC-ROC of 0.68 ± 0.002 in a modified one-versus-rest configuration, resulting in an information transfer rate of 304.15 bits per minute. In line with prior literature, the distinguishing feature between phonemes was the gamma power on channels F3 and F7.DiscussionHowever, adjustments to feature selection, trial window length, and classifier algorithms may improve performance. In summary, these are iterative changes to a viable method directly deployable in current, commercially available systems and software. The development of an intuitive phoneme-based EEG BCI with open-source hardware and software demonstrates the potential ease with which the technology could be deployed in real-world applications.https://www.frontiersin.org/articles/10.3389/fninf.2023.1306277/fullEEGelectroencephalographycovert speechimagined speechbrain-computer interfaceBCI |
| spellingShingle | John LaRocco Qudsia Tahmina Sam Lecian Jason Moore Cole Helbig Surya Gupta Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalography Frontiers in Neuroinformatics EEG electroencephalography covert speech imagined speech brain-computer interface BCI |
| title | Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalography |
| title_full | Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalography |
| title_fullStr | Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalography |
| title_full_unstemmed | Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalography |
| title_short | Evaluation of an English language phoneme-based imagined speech brain computer interface with low-cost electroencephalography |
| title_sort | evaluation of an english language phoneme based imagined speech brain computer interface with low cost electroencephalography |
| topic | EEG electroencephalography covert speech imagined speech brain-computer interface BCI |
| url | https://www.frontiersin.org/articles/10.3389/fninf.2023.1306277/full |
| work_keys_str_mv | AT johnlarocco evaluationofanenglishlanguagephonemebasedimaginedspeechbraincomputerinterfacewithlowcostelectroencephalography AT qudsiatahmina evaluationofanenglishlanguagephonemebasedimaginedspeechbraincomputerinterfacewithlowcostelectroencephalography AT samlecian evaluationofanenglishlanguagephonemebasedimaginedspeechbraincomputerinterfacewithlowcostelectroencephalography AT jasonmoore evaluationofanenglishlanguagephonemebasedimaginedspeechbraincomputerinterfacewithlowcostelectroencephalography AT colehelbig evaluationofanenglishlanguagephonemebasedimaginedspeechbraincomputerinterfacewithlowcostelectroencephalography AT suryagupta evaluationofanenglishlanguagephonemebasedimaginedspeechbraincomputerinterfacewithlowcostelectroencephalography |