The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems
<b>Background/Objectives</b>: Accurately classifying Electroencephalography (EEG) signals is essential for the effective operation of Brain-Computer Interfaces (BCI), which is needed for reliable neurorehabilitation applications. However, many factors in the processing pipeline can influ...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Brain Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3425/14/12/1272 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846105520703799296 |
|---|---|
| author | András Adolf Csaba Márton Köllőd Gergely Márton Ward Fadel István Ulbert |
| author_facet | András Adolf Csaba Márton Köllőd Gergely Márton Ward Fadel István Ulbert |
| author_sort | András Adolf |
| collection | DOAJ |
| description | <b>Background/Objectives</b>: Accurately classifying Electroencephalography (EEG) signals is essential for the effective operation of Brain-Computer Interfaces (BCI), which is needed for reliable neurorehabilitation applications. However, many factors in the processing pipeline can influence classification performance. The objective of this study is to assess the effects of different processing steps on classification accuracy in EEG-based BCI systems. <b>Methods</b>: This study explores the impact of various processing techniques and stages, including the FASTER algorithm for artifact rejection (AR), frequency filtering, transfer learning, and cropped training. The Physionet dataset, consisting of four motor imagery classes, was used as input due to its relatively large number of subjects. The raw EEG was tested with EEGNet and Shallow ConvNet. To examine the impact of adding a spatial dimension to the input data, we also used the Multi-branch Conv3D Net and developed two new models, Conv2D Net and Conv3D Net. <b>Results</b>: Our analysis showed that classification accuracy can be affected by many factors at every stage. Applying the AR method, for instance, can either enhance or degrade classification performance, depending on the subject and the specific network architecture. Transfer learning was effective in improving the performance of all networks for both raw and artifact-rejected data. However, the improvement in classification accuracy for artifact-rejected data was less pronounced compared to unfiltered data, resulting in reduced precision. For instance, the best classifier achieved 46.1% accuracy on unfiltered data, which increased to 63.5% with transfer learning. In the filtered case, accuracy rose from 45.5% to only 55.9% when transfer learning was applied. An unexpected outcome regarding frequency filtering was observed: networks demonstrated better classification performance when focusing on lower-frequency components. Higher frequency ranges were more discriminative for EEGNet and Shallow ConvNet, but only when cropped training was applied. <b>Conclusions</b>: The findings of this study highlight the complex interaction between processing techniques and neural network performance, emphasizing the necessity for customized processing approaches tailored to specific subjects and network architectures. |
| format | Article |
| id | doaj-art-cbe777126a4e43d6b1bc71b3932d0b13 |
| institution | Kabale University |
| issn | 2076-3425 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Brain Sciences |
| spelling | doaj-art-cbe777126a4e43d6b1bc71b3932d0b132024-12-27T14:14:58ZengMDPI AGBrain Sciences2076-34252024-12-011412127210.3390/brainsci14121272The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface SystemsAndrás Adolf0Csaba Márton Köllőd1Gergely Márton2Ward Fadel3István Ulbert4Roska Tamás Doctoral School of Sciences and Technology, Práter utca 50/a, 1083 Budapest, HungaryFaculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/a, 1083 Budapest, HungaryFaculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/a, 1083 Budapest, HungaryRoska Tamás Doctoral School of Sciences and Technology, Práter utca 50/a, 1083 Budapest, HungaryFaculty of Information Technology and Bionics, Pázmány Péter Catholic University, Práter utca 50/a, 1083 Budapest, Hungary<b>Background/Objectives</b>: Accurately classifying Electroencephalography (EEG) signals is essential for the effective operation of Brain-Computer Interfaces (BCI), which is needed for reliable neurorehabilitation applications. However, many factors in the processing pipeline can influence classification performance. The objective of this study is to assess the effects of different processing steps on classification accuracy in EEG-based BCI systems. <b>Methods</b>: This study explores the impact of various processing techniques and stages, including the FASTER algorithm for artifact rejection (AR), frequency filtering, transfer learning, and cropped training. The Physionet dataset, consisting of four motor imagery classes, was used as input due to its relatively large number of subjects. The raw EEG was tested with EEGNet and Shallow ConvNet. To examine the impact of adding a spatial dimension to the input data, we also used the Multi-branch Conv3D Net and developed two new models, Conv2D Net and Conv3D Net. <b>Results</b>: Our analysis showed that classification accuracy can be affected by many factors at every stage. Applying the AR method, for instance, can either enhance or degrade classification performance, depending on the subject and the specific network architecture. Transfer learning was effective in improving the performance of all networks for both raw and artifact-rejected data. However, the improvement in classification accuracy for artifact-rejected data was less pronounced compared to unfiltered data, resulting in reduced precision. For instance, the best classifier achieved 46.1% accuracy on unfiltered data, which increased to 63.5% with transfer learning. In the filtered case, accuracy rose from 45.5% to only 55.9% when transfer learning was applied. An unexpected outcome regarding frequency filtering was observed: networks demonstrated better classification performance when focusing on lower-frequency components. Higher frequency ranges were more discriminative for EEGNet and Shallow ConvNet, but only when cropped training was applied. <b>Conclusions</b>: The findings of this study highlight the complex interaction between processing techniques and neural network performance, emphasizing the necessity for customized processing approaches tailored to specific subjects and network architectures.https://www.mdpi.com/2076-3425/14/12/1272artifact rejectionbrain-computer interfaceelectroencephalographymotor imageryfasterCNN |
| spellingShingle | András Adolf Csaba Márton Köllőd Gergely Márton Ward Fadel István Ulbert The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems Brain Sciences artifact rejection brain-computer interface electroencephalography motor imagery faster CNN |
| title | The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems |
| title_full | The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems |
| title_fullStr | The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems |
| title_full_unstemmed | The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems |
| title_short | The Effect of Processing Techniques on the Classification Accuracy of Brain-Computer Interface Systems |
| title_sort | effect of processing techniques on the classification accuracy of brain computer interface systems |
| topic | artifact rejection brain-computer interface electroencephalography motor imagery faster CNN |
| url | https://www.mdpi.com/2076-3425/14/12/1272 |
| work_keys_str_mv | AT andrasadolf theeffectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT csabamartonkollod theeffectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT gergelymarton theeffectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT wardfadel theeffectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT istvanulbert theeffectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT andrasadolf effectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT csabamartonkollod effectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT gergelymarton effectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT wardfadel effectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems AT istvanulbert effectofprocessingtechniquesontheclassificationaccuracyofbraincomputerinterfacesystems |