Carlos David Castro-Rodriguez
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Carlos David Castro-Rodriguez has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Ariel Pincay
Communication Networks and Intelligent Services Research Group (ComNet Innova YT), School of Mathematical and Computational Sciences, Yachay Tech University, Hacienda San José s/n y Proyecto Yachay, Urcuquí 100119, Ecuador
1 shared publication - Francisco Hidrobo
Yachay Tech University
1 shared publication - Freddy Valenzuela
Communication Networks and Intelligent Services Research Group (ComNet Innova YT), School of Mathematical and Computational Sciences, Yachay Tech University, Hacienda San José s/n y Proyecto Yachay, Urcuquí 100119, Ecuador
1 shared publication - Joseph L. Tipan-Vera
Communication Networks and Intelligent Services Research Group (ComNet Innova YT), School of Mathematical and Computational Sciences, Yachay Tech University, Hacienda San José s/n y Proyecto Yachay, Urcuquí 100119, Ecuador
1 shared publication - Juan Pablo Astudillo León
Communication Networks and Intelligent Services Research Group (ComNet Innova YT), School of Mathematical and Computational Sciences, Yachay Tech University, Hda. San José s/n y Proyecto Yachay, Urcuquí 100119, Ecuador
1 shared publication
Latest Publications
- Open Access
- 18 September 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 153 (1) , 3
Comparative Study of Federated Learning Architectures on Resource-Constrained Edge Devices
This paper presents a comparative experimental evaluation of centralized, semi-decentralized, and hierarchical federated learning (FL) architectures combined with FedAvg, FedProx, and FedNova for premature non-communicable disease (NCD) mortality prediction. Using the Ecuadorian mortality registry (89,877 records), we construct a non-IID institutional setting with quantity, label, and feature skew across five hospitals and deploy all configurations on a six-device Raspberry Pi 4 cluster. The evaluation jointly considers predictive performance, convergence, communication overhead, energy estimates, CPU usage, RAM usage, temperature, and straggler delay. Hierarchical FedNova achieves the highest global F1-score (0.808) and accuracy (0.941), with near-zero straggler delay and the lowest cumulative energy among hierarchical configurations (15.35 J). Semi-decentralized FL reduces communication and energy cost but is sensitive to lottery-based aggregator selection under hardware volatility. Centralized FedNova provides the lowest estimated cumulative energy ( J) at the cost of lower predictive performance. The findings provide practical guidance for FL deployment in resource-limited, data-heterogeneous public-health environments under the evaluated hardware and data-partition conditions.- 18 September 2026
- Published by MDPI AG in Engineering Proceedings
- Vol. 153 (1) , 3
Open AccessComparative Study of Federated Learning Architectures on Resource-Constrained Edge Devices
This paper presents a comparative experimental evaluation of centralized, semi-decentralized, and hierarchical federated learning (FL) architectures combined with FedAvg, FedProx, and FedNova for premature non-communicable disease (NCD) mortality prediction. Using the Ecuadorian mortality registry (89,877 records), we construct a non-IID institutional setting with quantity, label, and feature skew across five hospitals and deploy all configurations on a six-device Raspberry Pi 4 cluster. The evaluation jointly considers predictive performance, convergence, communication overhead, energy estimates, CPU usage, RAM usage, temperature, and straggler delay. Hierarchical FedNova achieves the highest global F1-score (0.808) and accuracy (0.941), with near-zero straggler delay and the lowest cumulative energy among hierarchical configurations (15.35 J). Semi-decentralized FL reduces communication and energy cost but is sensitive to lottery-based aggregator selection under hardware volatility. Centralized FedNova provides the lowest estimated cumulative energy ( J) at the cost of lower predictive performance. The findings provide practical guidance for FL deployment in resource-limited, data-heterogeneous public-health environments under the evaluated hardware and data-partition conditions.