Miguel Camelo

Papers

Total Citations

H-Index

About

Miguel Camelo is a researcher at the forefront of intelligent, distributed systems for the Internet of Things (IoT) and wireless communications. His work primarily focuses on enabling autonomous decision-making in resource-constrained environments, with key contributions in reinforcement learning and deep learning for network management. In his highly cited 2019 paper, "Parallel Reinforcement Learning With Minimal Communication Overhead for IoT Environments" (22 citations), Camelo tackled a critical challenge: how to coordinate learning across distributed IoT devices without overwhelming their limited bandwidth. He introduced a novel algorithm that dramatically reduces communication overhead, making parallel learning practical for real-time, latency-sensitive applications. Building on this, his 2020 work, "Traffic classification at the radio spectrum level using deep learning models trained with synthetic data" (14 citations), pioneered a privacy-preserving approach to network monitoring. By analyzing raw radio signals instead of packet contents, Camelo’s model can classify traffic without accessing user data, and his use of synthetic training data overcomes the scarcity of labeled real-world spectrum samples. These contributions position Camelo as a key innovator in creating efficient, scalable, and privacy-aware AI for the next generation of wireless and IoT systems.