A Modified Edge Cloud Framework for Reproducible Latency Evaluation of Diabetes Prediction Using FogBus2 and XGBoost
IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies · 2026
DOI: 10.68307/crnh0c22 ↗Kurz gefasst
Fachartikel in der Zeitschrift IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies, 2026. Verfasst von Nisha Lodhi und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Diabetes mellitus
Abstract (Originalsprache)
Edge and fog computing can reduce communication delay for distributed healthcare analytics, but latency claims require controlled measurement. This paper specifies a three-tier framework in which the same trained XGBoost classifier and identical records are deployed in cloud-only, original FogBus2, and modified FogBus2 configurations. The proposed cost-based scheduler selects fog or cloud execution using round-trip time, CPU utilization, queue length, and bandwidth. On the 768-record Pima benchmark, leakage-safe evaluation produced 79.2% holdout accuracy, 68.0% F1-score, and 0.890 ROC-AUC; repeated stratified cross-validation produced 76.5% ± 3.3% accuracy and 0.840 ± 0.020 ROC-AUC. Earlier system-latency averages remain pilot observations pending repeated multi-device measurements. The Pima data are used only as a static benchmark workload, and no clinical-validation claim is made.
Zitieren
APA
Lodhi, N., & Jain, D. R. (2026). A Modified Edge Cloud Framework for Reproducible Latency Evaluation of Diabetes Prediction Using FogBus2 and XGBoost. IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies. https://doi.org/10.68307/crnh0c22
Vancouver
Lodhi N, Jain DR. A Modified Edge Cloud Framework for Reproducible Latency Evaluation of Diabetes Prediction Using FogBus2 and XGBoost. IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies. 2026. doi:10.68307/crnh0c22
BibTeX
@article{Lodhi2026,
author = {Lodhi, Nisha and Jain, Dr. Ruchi},
title = {A Modified Edge Cloud Framework for Reproducible Latency Evaluation of Diabetes Prediction Using FogBus2 and XGBoost},
journal = {IJAICET - International Journal of Artificial Intelligence, Cybersecurity and Emerging Technologies},
year = {2026},
doi = {10.68307/crnh0c22}
}
EUVIMED