Epilepsy Classification Framework Utilizing Joint Time-Frequency Signal Analysis and Processing
Time Frequency Signal Analysis and Processing (TFSAP) have been proposed in order to analyse the signal in both the time and the frequency domains. Electroencephalography (EEG) as a time-varying frequency signal is an interesting field in which Time Frequency Distribution (TFD) could be used in orde...
| Hauptverfasser: | , |
|---|---|
| Format: | Artikel |
| Sprache: | English |
| Veröffentlicht: |
Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca
2015-06-01
|
| Schriftenreihe: | Applied Medical Informatics |
| Schlagworte: | |
| Online Zugang: | http://ami.info.umfcluj.ro/index.php/AMI/article/view/519 |
| _version_ | 1831602886874759168 |
|---|---|
| author | Shiva KHOSHNOUD Mousa SHAMSI |
| author_facet | Shiva KHOSHNOUD Mousa SHAMSI |
| author_sort | Shiva KHOSHNOUD |
| collection | DOAJ |
| description | Time Frequency Signal Analysis and Processing (TFSAP) have been proposed in order to analyse the signal in both the time and the frequency domains. Electroencephalography (EEG) as a time-varying frequency signal is an interesting field in which Time Frequency Distribution (TFD) could be used in order to visualize the simultaneous distributions of signal energy in different physiological and pathological brain states. Particularly, epileptic signals due to their great features of seizure activity are introduced as the most attractive research field among researchers. This study outlines an investigation on two main pathologic brain states including, pre-ictal activity and seizure activity compared to normal activity. Pseudo-Wigner -Ville and Choi-William distributions are used in order to visualize the energy content of signals in these states. Different segments of brain electrical activity are analyzed using these distributions. Finally, Renyi’s entropy as an important characteristic which offer insight towards the EEG signal processing has been extracted from TFDs. The results obtained indicate that Renyi’s entropy is a high-quality discriminative feature especially in alpha and delta sub-bands of the EEG signal. |
| first_indexed | 2024-12-18T15:29:06Z |
| format | Article |
| id | doaj.art-2518d88b610b4b8c928d86b51fd5b66f |
| institution | Directory Open Access Journal |
| issn | 1224-5593 2067-7855 |
| language | English |
| last_indexed | 2024-12-18T15:29:06Z |
| publishDate | 2015-06-01 |
| publisher | Iuliu Hatieganu University of Medicine and Pharmacy, Cluj-Napoca |
| record_format | Article |
| series | Applied Medical Informatics |
| spelling | doaj.art-2518d88b610b4b8c928d86b51fd5b66f2022-12-21T21:03:12ZengIuliu Hatieganu University of Medicine and Pharmacy, Cluj-NapocaApplied Medical Informatics1224-55932067-78552015-06-0136218Epilepsy Classification Framework Utilizing Joint Time-Frequency Signal Analysis and ProcessingShiva KHOSHNOUD0Mousa SHAMSI 1Faculty of Electrical Engineering, Sahand University of Technology, Tabriz, Islamic Republic of Iran.Faculty of Electrical Engineering, Sahand University of Technology, Tabriz, Islamic Republic of Iran.Time Frequency Signal Analysis and Processing (TFSAP) have been proposed in order to analyse the signal in both the time and the frequency domains. Electroencephalography (EEG) as a time-varying frequency signal is an interesting field in which Time Frequency Distribution (TFD) could be used in order to visualize the simultaneous distributions of signal energy in different physiological and pathological brain states. Particularly, epileptic signals due to their great features of seizure activity are introduced as the most attractive research field among researchers. This study outlines an investigation on two main pathologic brain states including, pre-ictal activity and seizure activity compared to normal activity. Pseudo-Wigner -Ville and Choi-William distributions are used in order to visualize the energy content of signals in these states. Different segments of brain electrical activity are analyzed using these distributions. Finally, Renyi’s entropy as an important characteristic which offer insight towards the EEG signal processing has been extracted from TFDs. The results obtained indicate that Renyi’s entropy is a high-quality discriminative feature especially in alpha and delta sub-bands of the EEG signal.http://ami.info.umfcluj.ro/index.php/AMI/article/view/519Time-frequency analysisSignal processingEpilepsyRenyi’s entropy |
| spellingShingle | Shiva KHOSHNOUD Mousa SHAMSI Epilepsy Classification Framework Utilizing Joint Time-Frequency Signal Analysis and Processing Applied Medical Informatics Time-frequency analysis Signal processing Epilepsy Renyi’s entropy |
| title | Epilepsy Classification Framework Utilizing Joint Time-Frequency Signal Analysis and Processing |
| title_full | Epilepsy Classification Framework Utilizing Joint Time-Frequency Signal Analysis and Processing |
| title_fullStr | Epilepsy Classification Framework Utilizing Joint Time-Frequency Signal Analysis and Processing |
| title_full_unstemmed | Epilepsy Classification Framework Utilizing Joint Time-Frequency Signal Analysis and Processing |
| title_short | Epilepsy Classification Framework Utilizing Joint Time-Frequency Signal Analysis and Processing |
| title_sort | epilepsy classification framework utilizing joint time frequency signal analysis and processing |
| topic | Time-frequency analysis Signal processing Epilepsy Renyi’s entropy |
| url | http://ami.info.umfcluj.ro/index.php/AMI/article/view/519 |
| work_keys_str_mv | AT shivakhoshnoud epilepsyclassificationframeworkutilizingjointtimefrequencysignalanalysisandprocessing AT mousashamsi epilepsyclassificationframeworkutilizingjointtimefrequencysignalanalysisandprocessing |