EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Seizure Type Classification Based on Hybrid Feature Engineering and Mutual Information Analysis Using Electroencephalogram

Yao Miao iD

Entropy · 11.10.2025 · 27 (10) · 1057

DOI: 10.3390/e27101057 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 11.10.2025. Verfasst von Yao Miao. Beteiligte Einrichtung: College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Top Talent of SZTU, Shenzhen Major Science and Technology Projects.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Epilepsy has diverse seizure types that challenge diagnosis and treatment, requiring automated and accurate classification to improve patient outcomes. Traditional electroencephalogram (EEG)-based diagnosis relies on manual interpretation, which is subjective and inefficient, particularly for multi-class differentiation in imbalanced datasets. This study aims to develop a hybrid framework for automated multi-class seizure type classification using segment-wise EEG processing and multi-band feature engineering to enhance precision and address data challenges. EEG signals from the TUSZ dataset were segmented into 1-s windows with 0.5-s overlaps, followed by the extraction of multi-band features, including statistical measures, sample entropy, wavelet energies, Hurst exponent, and Hjorth parameters. The mutual information (MI) approach was employed to select the optimal features, and seven machine learning models (SVM, KNN, DT, RF, XGBoost, CatBoost, LightGBM) were evaluated via 10-fold stratified cross-validation with a class balancing strategy. The results showed the following: (1) XGBoost achieved the highest performance (accuracy: 0.8710, F1 score: 0.8721, AUC: 0.9797), with γ-band features dominating importance. (2) Confusion matrices indicated robust discrimination but noted overlaps in focal subtypes. This framework advances seizure type classification by integrating multi-band features and the MI method, which offers a scalable and interpretable tool for supporting clinical epilepsy diagnostics.

Schlagwörter

Stichwörter der Autor:innen

electroencephalogram (EEG)machine learningmulti-band featuresmutual information (MI)seizure type

Autor:innen und Institutionen

  • College of Health Science and Environmental Engineering, Shenzhen Technology University, Shenzhen 518118, China.

ORCID-Profile: Yao Miao

Förderung

  • Natural Science Foundation of Top Talent of SZTU
  • Shenzhen Major Science and Technology Projects

Zitieren

APA

Miao, Y. (2025). Seizure Type Classification Based on Hybrid Feature Engineering and Mutual Information Analysis Using Electroencephalogram. Entropy, 27(10), 1057. https://doi.org/10.3390/e27101057

Vancouver

Miao Y. Seizure Type Classification Based on Hybrid Feature Engineering and Mutual Information Analysis Using Electroencephalogram. Entropy. 2025;27(10):1057. doi:10.3390/e27101057

BibTeX
@article{Miao2025,
  author = {Miao, Yao},
  title = {Seizure Type Classification Based on Hybrid Feature Engineering and Mutual Information Analysis Using Electroencephalogram},
  journal = {Entropy},
  year = {2025},
  volume = {27},
  number = {10},
  pages = {1057},
  doi = {10.3390/e27101057}
}
Kostenlos starten →