World PulseNow
Newsletter

Multi-Frequency Federated Learning for Human Activity Recognition Using Head-Worn Sensors

arXiv — cs.LG•Thursday, December 4, 2025 at 5:00:00 AM
PositiveArtificial Intelligence
  • A new study introduces multi-frequency Federated Learning (FL) for Human Activity Recognition (HAR) using head-worn sensors like earbuds and smart glasses. This approach addresses privacy concerns associated with centralized data collection by enabling decentralized model training across devices with varying sampling frequencies.
  • The development is significant as it enhances privacy-aware machine learning, allowing for improved HAR applications in health and elderly care, while also making head-worn devices a viable option for activity recognition, an area previously dominated by smartwatches and smartphones.
  • This advancement reflects a growing trend in the integration of Federated Learning across various domains, including medical imaging and assistive technologies, highlighting the importance of privacy and personalization in AI applications. The emergence of frameworks that tackle challenges such as label-distribution skew and energy efficiency further underscores the potential of decentralized learning in diverse environments.
— via World Pulse Now AI Editorial System
Read Original

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps

LucidQuery AI

Combines diffusion reasoning with autoregressive LLM for advanced AI analysis.

AI & DataTry the app

HubRE AI

AI agents that boost user engagement, ensure compliance, and streamline knowledge management.

AI & DataTry the app

Open Source Surveillance

Search social media, cameras, and IoT devices for public safety insights.

AI & DataTry the app
Continue Readings
Energy-Efficient Federated Learning via Adaptive Encoder Freezing for MRI-to-CT Conversion: A Green AI-Guided Research
arXiv — cs.LG2 days ago
Energy-Efficient Federated Learning via Adaptive Encoder Freezing for MRI-to-CT Conversion: A Green AI-Guided Research
PositiveArtificial Intelligence
A new approach to Federated Learning (FL) has been introduced, focusing on energy efficiency through an adaptive encoder freezing strategy for MRI-to-CT conversion. This method aims to reduce computational load and energy consumption while maintaining model performance, addressing the challenges faced by healthcare institutions with limited resources.
Read full article
via arXiv — cs.LG
Single-Round Scalable Analytic Federated Learning
arXiv — stat.ML2 days ago
Single-Round Scalable Analytic Federated Learning
PositiveArtificial Intelligence
A new framework called SAFLe has been introduced to address the challenges of high communication overhead and performance collapse in Federated Learning (FL). This framework achieves scalable non-linear expressivity while maintaining the single-round benefits of Analytic FL, significantly outperforming previous models like DeepAFL in accuracy across various benchmarks.
Read full article
via arXiv — stat.ML
Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks
arXiv — cs.LG2 days ago
Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks
PositiveArtificial Intelligence
A new study proposes an asynchronous design for Federated Learning (FL) that incorporates periodic aggregation to address the straggler issue in wireless networks. This approach emphasizes the importance of scheduling policies that consider channel quality and data representation, aiming to enhance the convergence performance of distributed machine learning models.
Read full article
via arXiv — cs.LG