EUVIMEDEUVIMED entdecken
Crossref

Design of an Intelligent System for the Early Diagnosis of Parkinson's Disease based on Voice Intonation Fondamental Frequencies through an Ensemble of Classifiers Made Up of XGBoost, SVM and Random Forest (RF)

Romain Atangana, Vivien Loick Kamgang Beyala, Amstrong Emini Me Zenanga, Laurent Cabrel Tabueu Fotso, Emmanuel Baba, Vincent Bayang Nyomo, Abdel Aziz Baba, Perrin L, Nel Daryl Naoussi Nde, Daniel Tchiotsop, Godpromesse Kenne

Signal & Image Processing : An International Journal · 14.07.2026 · 17 (1/2/3) · 27-46

DOI: 10.5121/sipij.2026.17303 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Signal & Image Processing : An International Journal, online erschienen am 14.07.2026. Verfasst von Romain Atangana und 10 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This document presents a non-invasive early diagnostic system for Parkinson’s disease using 22 acoustic biomarkers. A hard-voting classifier combining SVM, Random Forest, and XGBoost, with preprocessing (StandardScaler, SMOTE), achieves 94% test accuracy and 93.20% in 10-fold cross-validation, with an AUC near 1.00. Interpretability analysis reveals that the most important variables (PPE, Spread1, jitter, shimmer) match known physiological alterations in Parkinson’s. The work shows that heterogeneous models can offer a reliable and transparent decision-support tool for clinicians, enabling earlier diagnosis before motor symptoms appear.

Zitieren

APA

Atangana, R., Beyala, V. L. K., Zenanga, A. E. M., Fotso, L. C. T., Baba, E., Nyomo, V. B., Baba, A. A., L, P., Nde, N. D. N., Tchiotsop, D., & Kenne, G. (2026). Design of an Intelligent System for the Early Diagnosis of Parkinson's Disease based on Voice Intonation Fondamental Frequencies through an Ensemble of Classifiers Made Up of XGBoost, SVM and Random Forest (RF). Signal & Image Processing : An International Journal, 17(1/2/3), 27-46. https://doi.org/10.5121/sipij.2026.17303

Vancouver

Atangana R, Beyala VLK, Zenanga AEM, Fotso LCT, Baba E, Nyomo VB, et al. Design of an Intelligent System for the Early Diagnosis of Parkinson's Disease based on Voice Intonation Fondamental Frequencies through an Ensemble of Classifiers Made Up of XGBoost, SVM and Random Forest (RF). Signal & Image Processing : An International Journal. 2026;17(1/2/3):27-46. doi:10.5121/sipij.2026.17303

BibTeX
@article{Atangana2026,
  author = {Atangana, Romain and Beyala, Vivien Loick Kamgang and Zenanga, Amstrong Emini Me and Fotso, Laurent Cabrel Tabueu and Baba, Emmanuel and Nyomo, Vincent Bayang and Baba, Abdel Aziz and L, Perrin and Nde, Nel Daryl Naoussi and Tchiotsop, Daniel and Kenne, Godpromesse},
  title = {Design of an Intelligent System for the Early Diagnosis of Parkinson's Disease based on Voice Intonation Fondamental Frequencies through an Ensemble of Classifiers Made Up of XGBoost, SVM and Random Forest (RF)},
  journal = {Signal & Image Processing : An International Journal},
  year = {2026},
  volume = {17},
  number = {1/2/3},
  pages = {27--46},
  doi = {10.5121/sipij.2026.17303}
}
Kostenlos starten →