A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure
Abstract Introduction Epilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroenc...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-03-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-024-02460-z |
| _version_ | 1797274414946975744 |
|---|---|
| author | Sergio Alejandro Holguin-Garcia Ernesto Guevara-Navarro Alvaro Eduardo Daza-Chica Maria Alejandra Patiño-Claro Harold Brayan Arteaga-Arteaga Gonzalo A. Ruz Reinel Tabares-Soto Mario Alejandro Bravo-Ortiz |
| author_facet | Sergio Alejandro Holguin-Garcia Ernesto Guevara-Navarro Alvaro Eduardo Daza-Chica Maria Alejandra Patiño-Claro Harold Brayan Arteaga-Arteaga Gonzalo A. Ruz Reinel Tabares-Soto Mario Alejandro Bravo-Ortiz |
| author_sort | Sergio Alejandro Holguin-Garcia |
| collection | DOAJ |
| description | Abstract Introduction Epilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroencephalogram (EEG), which is lengthy. Method To optimize these processes and make them more efficient, we have resorted to innovative artificial intelligence methods essential in classifying EEG signals. For this, comparing traditional models, such as machine learning or deep learning, with cutting-edge models, in this case, using Capsule-Net architectures and Transformer Encoder, has a crucial role in finding the most accurate model and helping the doctor to have a faster diagnosis. Result In this paper, a comparison was made between different models for binary and multiclass classification of the epileptic seizure detection database, achieving a binary accuracy of 99.92% with the Capsule-Net model and a multiclass accuracy with the Transformer Encoder model of 87.30%. Conclusion Artificial intelligence is essential in diagnosing pathology. The comparison between models is helpful as it helps to discard those that are not efficient. State-of-the-art models overshadow conventional models, but data processing also plays an essential role in evaluating the higher accuracy of the models. |
| first_indexed | 2024-03-07T14:58:00Z |
| format | Article |
| id | doaj.art-f5fc24eb1c5d450e9c88f5097a2080c9 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-03-07T14:58:00Z |
| publishDate | 2024-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-f5fc24eb1c5d450e9c88f5097a2080c92024-03-05T19:19:48ZengBMCBMC Medical Informatics and Decision Making1472-69472024-03-0124112310.1186/s12911-024-02460-zA comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizureSergio Alejandro Holguin-Garcia0Ernesto Guevara-Navarro1Alvaro Eduardo Daza-Chica2Maria Alejandra Patiño-Claro3Harold Brayan Arteaga-Arteaga4Gonzalo A. Ruz5Reinel Tabares-Soto6Mario Alejandro Bravo-Ortiz7Departamento de Electrónica y Automatización, Universidad Autónoma de ManizalesDepartamento de Electrónica y Automatización, Universidad Autónoma de ManizalesDepartamento de Electrónica y Automatización, Universidad Autónoma de ManizalesDepartamento de Electrónica y Automatización, Universidad Autónoma de ManizalesDepartamento de Electrónica y Automatización, Universidad Autónoma de ManizalesFacultad de Ingeniería y Ciencias, Universidad Adolfo IbáñezDepartamento de Electrónica y Automatización, Universidad Autónoma de ManizalesDepartamento de Electrónica y Automatización, Universidad Autónoma de ManizalesAbstract Introduction Epilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroencephalogram (EEG), which is lengthy. Method To optimize these processes and make them more efficient, we have resorted to innovative artificial intelligence methods essential in classifying EEG signals. For this, comparing traditional models, such as machine learning or deep learning, with cutting-edge models, in this case, using Capsule-Net architectures and Transformer Encoder, has a crucial role in finding the most accurate model and helping the doctor to have a faster diagnosis. Result In this paper, a comparison was made between different models for binary and multiclass classification of the epileptic seizure detection database, achieving a binary accuracy of 99.92% with the Capsule-Net model and a multiclass accuracy with the Transformer Encoder model of 87.30%. Conclusion Artificial intelligence is essential in diagnosing pathology. The comparison between models is helpful as it helps to discard those that are not efficient. State-of-the-art models overshadow conventional models, but data processing also plays an essential role in evaluating the higher accuracy of the models.https://doi.org/10.1186/s12911-024-02460-zCapsule-NetElectroencephalogramsEpilepsyMachine learningTransformer Encoder |
| spellingShingle | Sergio Alejandro Holguin-Garcia Ernesto Guevara-Navarro Alvaro Eduardo Daza-Chica Maria Alejandra Patiño-Claro Harold Brayan Arteaga-Arteaga Gonzalo A. Ruz Reinel Tabares-Soto Mario Alejandro Bravo-Ortiz A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure BMC Medical Informatics and Decision Making Capsule-Net Electroencephalograms Epilepsy Machine learning Transformer Encoder |
| title | A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure |
| title_full | A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure |
| title_fullStr | A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure |
| title_full_unstemmed | A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure |
| title_short | A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure |
| title_sort | comparative study of cnn capsule net cnn transformer encoder and traditional machine learning algorithms to classify epileptic seizure |
| topic | Capsule-Net Electroencephalograms Epilepsy Machine learning Transformer Encoder |
| url | https://doi.org/10.1186/s12911-024-02460-z |
| work_keys_str_mv | AT sergioalejandroholguingarcia acomparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT ernestoguevaranavarro acomparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT alvaroeduardodazachica acomparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT mariaalejandrapatinoclaro acomparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT haroldbrayanarteagaarteaga acomparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT gonzaloaruz acomparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT reineltabaressoto acomparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT marioalejandrobravoortiz acomparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT sergioalejandroholguingarcia comparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT ernestoguevaranavarro comparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT alvaroeduardodazachica comparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT mariaalejandrapatinoclaro comparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT haroldbrayanarteagaarteaga comparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT gonzaloaruz comparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT reineltabaressoto comparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure AT marioalejandrobravoortiz comparativestudyofcnncapsulenetcnntransformerencoderandtraditionalmachinelearningalgorithmstoclassifyepilepticseizure |