Novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals
Abstract This paper presents a novel, explainable feature engineering framework for classifying EEG and ECG signals with high accuracy. The proposed method employs the Order Transition Pattern (OTPat) feature extractor. The presented OTPat feature extractor captures both channel/column-based pattern...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-05-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-00071-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850280093934419968 |
|---|---|
| author | Mehmet Ali Gelen Prabal Datta Barua Irem Tasci Gulay Tasci Emrah Aydemir Sengul Dogan Turker Tuncer U. R. Acharya |
| author_facet | Mehmet Ali Gelen Prabal Datta Barua Irem Tasci Gulay Tasci Emrah Aydemir Sengul Dogan Turker Tuncer U. R. Acharya |
| author_sort | Mehmet Ali Gelen |
| collection | DOAJ |
| description | Abstract This paper presents a novel, explainable feature engineering framework for classifying EEG and ECG signals with high accuracy. The proposed method employs the Order Transition Pattern (OTPat) feature extractor. The presented OTPat feature extractor captures both channel/column-based patterns (spatial features) using all channels for each point and signal/row-based patterns (temporal features) by extracting features from individual channels using overlapping blocks. The extracted features are then refined using cumulative weighted iterative neighborhood component analysis (CWINCA) for feature selection and classified with a t‑algorithm k‑nearest neighbors (tkNN) classifier. Finally, two symbolic languages, Directed Lobish (DLob) and Cardioish, generate interpretable results in the form of cortical and cardiac connectome diagrams. The OTPat-based XFE model achieves over 95% accuracy on several EEG and ECG datasets and reaches 86.07% accuracy on an 8‑class EEG artifact dataset. These results demonstrate high performance and clear interpretability, highlighting the model’s potential for robust biomedical signal classification. |
| format | Article |
| id | doaj-art-c3a9c631f93e4ed8a4ee4ac9225df838 |
| institution | OA Journals |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-c3a9c631f93e4ed8a4ee4ac9225df8382025-08-20T01:48:53ZengNature PortfolioScientific Reports2045-23222025-05-0115112210.1038/s41598-025-00071-wNovel accurate classification system developed using order transition pattern feature engineering technique with physiological signalsMehmet Ali Gelen0Prabal Datta Barua1Irem Tasci2Gulay Tasci3Emrah Aydemir4Sengul Dogan5Turker Tuncer6U. R. Acharya7Department of Cardiology, Elazig Fethi Sekin City HospitalSchool of Business (Information System), University of Southern QueenslandDepartment of Neurology, School of Medicine, Firat UniversityDepartment of Psychiatry, Elazig Fethi Sekin City HospitalDepartment of Management Information Systems, Management Faculty, Sakarya UniversityDepartment of Digital Forensics Engineering, Technology Faculty, Firat UniversityDepartment of Digital Forensics Engineering, Technology Faculty, Firat UniversitySchool of Mathematics, Physics and Computing, University of Southern QueenslandAbstract This paper presents a novel, explainable feature engineering framework for classifying EEG and ECG signals with high accuracy. The proposed method employs the Order Transition Pattern (OTPat) feature extractor. The presented OTPat feature extractor captures both channel/column-based patterns (spatial features) using all channels for each point and signal/row-based patterns (temporal features) by extracting features from individual channels using overlapping blocks. The extracted features are then refined using cumulative weighted iterative neighborhood component analysis (CWINCA) for feature selection and classified with a t‑algorithm k‑nearest neighbors (tkNN) classifier. Finally, two symbolic languages, Directed Lobish (DLob) and Cardioish, generate interpretable results in the form of cortical and cardiac connectome diagrams. The OTPat-based XFE model achieves over 95% accuracy on several EEG and ECG datasets and reaches 86.07% accuracy on an 8‑class EEG artifact dataset. These results demonstrate high performance and clear interpretability, highlighting the model’s potential for robust biomedical signal classification.https://doi.org/10.1038/s41598-025-00071-wOTPatExplainable feature engineeringBiomedical signal classificationTkNNDirected lobishCardioish |
| spellingShingle | Mehmet Ali Gelen Prabal Datta Barua Irem Tasci Gulay Tasci Emrah Aydemir Sengul Dogan Turker Tuncer U. R. Acharya Novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals Scientific Reports OTPat Explainable feature engineering Biomedical signal classification TkNN Directed lobish Cardioish |
| title | Novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals |
| title_full | Novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals |
| title_fullStr | Novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals |
| title_full_unstemmed | Novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals |
| title_short | Novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals |
| title_sort | novel accurate classification system developed using order transition pattern feature engineering technique with physiological signals |
| topic | OTPat Explainable feature engineering Biomedical signal classification TkNN Directed lobish Cardioish |
| url | https://doi.org/10.1038/s41598-025-00071-w |
| work_keys_str_mv | AT mehmetaligelen novelaccurateclassificationsystemdevelopedusingordertransitionpatternfeatureengineeringtechniquewithphysiologicalsignals AT prabaldattabarua novelaccurateclassificationsystemdevelopedusingordertransitionpatternfeatureengineeringtechniquewithphysiologicalsignals AT iremtasci novelaccurateclassificationsystemdevelopedusingordertransitionpatternfeatureengineeringtechniquewithphysiologicalsignals AT gulaytasci novelaccurateclassificationsystemdevelopedusingordertransitionpatternfeatureengineeringtechniquewithphysiologicalsignals AT emrahaydemir novelaccurateclassificationsystemdevelopedusingordertransitionpatternfeatureengineeringtechniquewithphysiologicalsignals AT senguldogan novelaccurateclassificationsystemdevelopedusingordertransitionpatternfeatureengineeringtechniquewithphysiologicalsignals AT turkertuncer novelaccurateclassificationsystemdevelopedusingordertransitionpatternfeatureengineeringtechniquewithphysiologicalsignals AT uracharya novelaccurateclassificationsystemdevelopedusingordertransitionpatternfeatureengineeringtechniquewithphysiologicalsignals |