A Performance Comparison of Physiological Data Models via Computational Analytics
International Journal of Computer-Aided Design and Applications · 23.04.2026 · 2 (1) · 90
DOI: 10.66419/ijcada.3195 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computer-Aided Design and Applications, online erschienen am 23.04.2026. Verfasst von Bako Halilu Egga und 2 weiteren Autor:innen. Die Arbeit nennt 2 Literaturangaben.
Abstract (Originalsprache)
When evaluating the performance of physiological models, researchers typically prioritize sensitivity, specificity, and computational latency. Traditional statistical approaches, while interpretable, often struggle with the high-dimensional, non-linear nature of real-time biological signals. In contrast, advanced machine learning architectures, particularly deep learning models like Long Short-Term Memory (LSTM) networks and Transformers, have demonstrated superior predictive accuracy by capturing intricate temporal dependencies within the data. However, this gain in performance often comes at the cost of ”black-box” opacity and increased demand for hardware resources. We employed a comparative assessment strategy to evaluate our physiological data model, utilizing computational analytics to measure predictive reliability and real-time processing capabilities. By comparing the model’s performance metrics against industry-standard benchmarks, we identified key operational improvements, statistically validating the model’s ability to interpret complex physiological trends with greater precision and reduced computational overhead.
Zitieren
APA
Egga, B. H., Makela, L. M., & Isiaka, F. (2026). A Performance Comparison of Physiological Data Models via Computational Analytics. International Journal of Computer-Aided Design and Applications, 2(1), 90. https://doi.org/10.66419/ijcada.3195
Vancouver
Egga BH, Makela LM, Isiaka F. A Performance Comparison of Physiological Data Models via Computational Analytics. International Journal of Computer-Aided Design and Applications. 2026;2(1):90. doi:10.66419/ijcada.3195
BibTeX
@article{Egga2026,
author = {Egga, Bako Halilu and Makela, Lauri Matias and Isiaka, Fatima},
title = {A Performance Comparison of Physiological Data Models via Computational Analytics},
journal = {International Journal of Computer-Aided Design and Applications},
year = {2026},
volume = {2},
number = {1},
pages = {90},
doi = {10.66419/ijcada.3195}
}
EUVIMED