UCI HAR

The UCI-HAR dataset is a benchmark that contains human activity recognition data collected from smartphones, used to evaluate machine learning models in the context of federated learning.

Papers using UCI HAR (6)

CA-AFP: Cluster-Aware Adaptive Federated Pruning2026FedPBS: Proximal-Balanced Scaling Federated Learning Model for Robust Personalized Training for Non-IID Data2026FedKDX: Federated Learning with Negative Knowledge Distillation for Enhanced Healthcare AI Systems2026Evidential Trust-Aware Model Personalization in Decentralized Federated Learning for Wearable IoT2025Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy2025FedSkipTwin: Digital-Twin-Guided Client Skipping for Communication-Efficient Federated Learning2025