Classification of Epileptic Seizures by Simple Machine Learning Techniques: Application to Animals’ Electroencephalography Signals
Detection and prediction of the onset of seizures are among the most challenging problems in epilepsy diagnostics and treatment. Small electronic devices capable of doing that will improve the quality of life for epilepsy patients while also open new opportunities for pharmacological intervention. T...
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10835066/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592867115139072 |
|---|---|
| author | Illia Pidvalnyi Anna Kostenko Oleksandr Sudakov Dmytro Isaev Oleksandr Maximyuk Oleg Krishtal Olena Iegorova Ievgen Kabin Zoya Dyka Steffen Ortmann Peter Langendorfer |
| author_facet | Illia Pidvalnyi Anna Kostenko Oleksandr Sudakov Dmytro Isaev Oleksandr Maximyuk Oleg Krishtal Olena Iegorova Ievgen Kabin Zoya Dyka Steffen Ortmann Peter Langendorfer |
| author_sort | Illia Pidvalnyi |
| collection | DOAJ |
| description | Detection and prediction of the onset of seizures are among the most challenging problems in epilepsy diagnostics and treatment. Small electronic devices capable of doing that will improve the quality of life for epilepsy patients while also open new opportunities for pharmacological intervention. This paper presents a novel approach using machine learning techniques to detect seizures onset using intracranial electroencephalography (EEG) signals. The proposed approach was tested on intracranial EEG data recorded in rats with pilocarpine model of temporal lobe epilepsy. A principal component analysis was applied for feature selection before using a support vector machine for the detection of seizures. Hjorth’s parameters and Daubechies discrete wavelet transform coefficients were found to be the most informative features of EEG data. We found that the support vector machine approach had a classification sensitivity of 90% and a specificity of 74% for detecting ictal episodes. Changing the epoch parameter from one to twenty-one seconds results in changing the redistribution of principal components’ values to 10% but does not affect the classification result. Support vector machines are accessible and convenient methods for classification that have achieved promising classification quality, and are rather lightweight compared to other machine learning methods. So we suggest their future use in mobile devices for early epileptic seizure and preictal episode detection. |
| format | Article |
| id | doaj-art-76b68359b7134afda43edd8a6442b9c6 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-76b68359b7134afda43edd8a6442b9c62025-01-21T00:02:06ZengIEEEIEEE Access2169-35362025-01-01138951896210.1109/ACCESS.2025.352786610835066Classification of Epileptic Seizures by Simple Machine Learning Techniques: Application to Animals’ Electroencephalography SignalsIllia Pidvalnyi0https://orcid.org/0000-0001-5812-9817Anna Kostenko1https://orcid.org/0009-0002-0036-3218Oleksandr Sudakov2Dmytro Isaev3https://orcid.org/0000-0002-4126-2563Oleksandr Maximyuk4https://orcid.org/0000-0003-3288-4974Oleg Krishtal5https://orcid.org/0000-0003-3342-9930Olena Iegorova6https://orcid.org/0000-0001-7394-9418Ievgen Kabin7https://orcid.org/0000-0002-3838-6493Zoya Dyka8https://orcid.org/0000-0002-6819-0467Steffen Ortmann9https://orcid.org/0000-0003-2542-0020Peter Langendorfer10https://orcid.org/0000-0002-6209-9048Medical Radiophysics Department, Faculty of Radiophysics Electronics and Computer Systems, Taras Shevchenko National University of Kyiv, Kyiv, UkraineMedical Radiophysics Department, Faculty of Radiophysics Electronics and Computer Systems, Taras Shevchenko National University of Kyiv, Kyiv, UkraineMedical Radiophysics Department, Faculty of Radiophysics Electronics and Computer Systems, Taras Shevchenko National University of Kyiv, Kyiv, UkraineDepartment of Cellular Membranology, Bogomoletz Institute of Physiology, Kyiv, UkraineDepartment of Cellular Membranology, Bogomoletz Institute of Physiology, Kyiv, UkraineDepartment of Cellular Membranology, Bogomoletz Institute of Physiology, Kyiv, UkraineDepartment of Cellular Membranology, Bogomoletz Institute of Physiology, Kyiv, UkraineIHP – Leibniz Institute for High Performance Microelectronics, Frankfurt (Oder), GermanyIHP – Leibniz Institute for High Performance Microelectronics, Frankfurt (Oder), GermanyThiem-Research, Cottbus, GermanyIHP – Leibniz Institute for High Performance Microelectronics, Frankfurt (Oder), GermanyDetection and prediction of the onset of seizures are among the most challenging problems in epilepsy diagnostics and treatment. Small electronic devices capable of doing that will improve the quality of life for epilepsy patients while also open new opportunities for pharmacological intervention. This paper presents a novel approach using machine learning techniques to detect seizures onset using intracranial electroencephalography (EEG) signals. The proposed approach was tested on intracranial EEG data recorded in rats with pilocarpine model of temporal lobe epilepsy. A principal component analysis was applied for feature selection before using a support vector machine for the detection of seizures. Hjorth’s parameters and Daubechies discrete wavelet transform coefficients were found to be the most informative features of EEG data. We found that the support vector machine approach had a classification sensitivity of 90% and a specificity of 74% for detecting ictal episodes. Changing the epoch parameter from one to twenty-one seconds results in changing the redistribution of principal components’ values to 10% but does not affect the classification result. Support vector machines are accessible and convenient methods for classification that have achieved promising classification quality, and are rather lightweight compared to other machine learning methods. So we suggest their future use in mobile devices for early epileptic seizure and preictal episode detection.https://ieeexplore.ieee.org/document/10835066/Epilepsysingle-channel intracranial encephalographic dataPCASVMautomated systemrats |
| spellingShingle | Illia Pidvalnyi Anna Kostenko Oleksandr Sudakov Dmytro Isaev Oleksandr Maximyuk Oleg Krishtal Olena Iegorova Ievgen Kabin Zoya Dyka Steffen Ortmann Peter Langendorfer Classification of Epileptic Seizures by Simple Machine Learning Techniques: Application to Animals’ Electroencephalography Signals IEEE Access Epilepsy single-channel intracranial encephalographic data PCA SVM automated system rats |
| title | Classification of Epileptic Seizures by Simple Machine Learning Techniques: Application to Animals’ Electroencephalography Signals |
| title_full | Classification of Epileptic Seizures by Simple Machine Learning Techniques: Application to Animals’ Electroencephalography Signals |
| title_fullStr | Classification of Epileptic Seizures by Simple Machine Learning Techniques: Application to Animals’ Electroencephalography Signals |
| title_full_unstemmed | Classification of Epileptic Seizures by Simple Machine Learning Techniques: Application to Animals’ Electroencephalography Signals |
| title_short | Classification of Epileptic Seizures by Simple Machine Learning Techniques: Application to Animals’ Electroencephalography Signals |
| title_sort | classification of epileptic seizures by simple machine learning techniques application to animals x2019 electroencephalography signals |
| topic | Epilepsy single-channel intracranial encephalographic data PCA SVM automated system rats |
| url | https://ieeexplore.ieee.org/document/10835066/ |
| work_keys_str_mv | AT illiapidvalnyi classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT annakostenko classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT oleksandrsudakov classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT dmytroisaev classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT oleksandrmaximyuk classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT olegkrishtal classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT olenaiegorova classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT ievgenkabin classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT zoyadyka classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT steffenortmann classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals AT peterlangendorfer classificationofepilepticseizuresbysimplemachinelearningtechniquesapplicationtoanimalsx2019electroencephalographysignals |