Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG)
Epilepsy is a neurological disease characterized by recurrent seizures caused by abnormal electrical activity in the brain. One of the methods used to diagnose epilepsy is through electroencephalogram (EEG) analysis. EEG is a non-invasive medical test for quantifying electrical activity in the brain...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Computers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2073-431X/12/10/197 |
| _version_ | 1797574202167918592 |
|---|---|
| author | Swetha Lenkala Revathi Marry Susmitha Reddy Gopovaram Tahir Cetin Akinci Oguzhan Topsakal |
| author_facet | Swetha Lenkala Revathi Marry Susmitha Reddy Gopovaram Tahir Cetin Akinci Oguzhan Topsakal |
| author_sort | Swetha Lenkala |
| collection | DOAJ |
| description | Epilepsy is a neurological disease characterized by recurrent seizures caused by abnormal electrical activity in the brain. One of the methods used to diagnose epilepsy is through electroencephalogram (EEG) analysis. EEG is a non-invasive medical test for quantifying electrical activity in the brain. Applying machine learning (ML) to EEG data for epilepsy diagnosis has the potential to be more accurate and efficient. However, expert knowledge is required to set up the ML model with correct hyperparameters. Automated machine learning (AutoML) tools aim to make ML more accessible to non-experts and automate many ML processes to create a high-performing ML model. This article explores the use of automated machine learning (AutoML) tools for diagnosing epilepsy using electroencephalogram (EEG) data. The study compares the performance of three different AutoML tools, AutoGluon, Auto-Sklearn, and Amazon Sagemaker, on three different datasets from the UC Irvine ML Repository, Bonn EEG time series dataset, and Zenodo. Performance measures used for evaluation include accuracy, F1 score, recall, and precision. The results show that all three AutoML tools were able to generate high-performing ML models for the diagnosis of epilepsy. The generated ML models perform better when the training dataset is larger in size. Amazon Sagemaker and Auto-Sklearn performed better with smaller datasets. This is the first study to compare several AutoML tools and shows that AutoML tools can be utilized to create well-performing solutions for the diagnosis of epilepsy via processing hard-to-analyze EEG timeseries data. |
| first_indexed | 2024-03-10T21:20:34Z |
| format | Article |
| id | doaj.art-5411fc2f941d4c5c8b5f25e28a772795 |
| institution | Directory Open Access Journal |
| issn | 2073-431X |
| language | English |
| last_indexed | 2024-03-10T21:20:34Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Computers |
| spelling | doaj.art-5411fc2f941d4c5c8b5f25e28a7727952023-11-19T16:07:58ZengMDPI AGComputers2073-431X2023-09-01121019710.3390/computers12100197Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG)Swetha Lenkala0Revathi Marry1Susmitha Reddy Gopovaram2Tahir Cetin Akinci3Oguzhan Topsakal4Department of Computer Science, Florida Polytechnic University, Lakeland, FL 33805, USADepartment of Computer Science, Florida Polytechnic University, Lakeland, FL 33805, USADepartment of Computer Science, Florida Polytechnic University, Lakeland, FL 33805, USAWinston Chung Global Energy Center, University of California at Riverside, Riverside, CA 92509, USADepartment of Computer Science, Florida Polytechnic University, Lakeland, FL 33805, USAEpilepsy is a neurological disease characterized by recurrent seizures caused by abnormal electrical activity in the brain. One of the methods used to diagnose epilepsy is through electroencephalogram (EEG) analysis. EEG is a non-invasive medical test for quantifying electrical activity in the brain. Applying machine learning (ML) to EEG data for epilepsy diagnosis has the potential to be more accurate and efficient. However, expert knowledge is required to set up the ML model with correct hyperparameters. Automated machine learning (AutoML) tools aim to make ML more accessible to non-experts and automate many ML processes to create a high-performing ML model. This article explores the use of automated machine learning (AutoML) tools for diagnosing epilepsy using electroencephalogram (EEG) data. The study compares the performance of three different AutoML tools, AutoGluon, Auto-Sklearn, and Amazon Sagemaker, on three different datasets from the UC Irvine ML Repository, Bonn EEG time series dataset, and Zenodo. Performance measures used for evaluation include accuracy, F1 score, recall, and precision. The results show that all three AutoML tools were able to generate high-performing ML models for the diagnosis of epilepsy. The generated ML models perform better when the training dataset is larger in size. Amazon Sagemaker and Auto-Sklearn performed better with smaller datasets. This is the first study to compare several AutoML tools and shows that AutoML tools can be utilized to create well-performing solutions for the diagnosis of epilepsy via processing hard-to-analyze EEG timeseries data.https://www.mdpi.com/2073-431X/12/10/197AutoMLelectroencephalogramEEGepilepsymachine learningevaluating |
| spellingShingle | Swetha Lenkala Revathi Marry Susmitha Reddy Gopovaram Tahir Cetin Akinci Oguzhan Topsakal Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG) Computers AutoML electroencephalogram EEG epilepsy machine learning evaluating |
| title | Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG) |
| title_full | Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG) |
| title_fullStr | Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG) |
| title_full_unstemmed | Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG) |
| title_short | Comparison of Automated Machine Learning (AutoML) Tools for Epileptic Seizure Detection Using Electroencephalograms (EEG) |
| title_sort | comparison of automated machine learning automl tools for epileptic seizure detection using electroencephalograms eeg |
| topic | AutoML electroencephalogram EEG epilepsy machine learning evaluating |
| url | https://www.mdpi.com/2073-431X/12/10/197 |
| work_keys_str_mv | AT swethalenkala comparisonofautomatedmachinelearningautomltoolsforepilepticseizuredetectionusingelectroencephalogramseeg AT revathimarry comparisonofautomatedmachinelearningautomltoolsforepilepticseizuredetectionusingelectroencephalogramseeg AT susmithareddygopovaram comparisonofautomatedmachinelearningautomltoolsforepilepticseizuredetectionusingelectroencephalogramseeg AT tahircetinakinci comparisonofautomatedmachinelearningautomltoolsforepilepticseizuredetectionusingelectroencephalogramseeg AT oguzhantopsakal comparisonofautomatedmachinelearningautomltoolsforepilepticseizuredetectionusingelectroencephalogramseeg |