GenHAR generalizes cross-domain human activity recognition by 9.97% accuracy and 6.4x lower FLOPs via tokenized sensor data, frequency channel correlations, selective masking, and efficient attention, with deployment detecting 2.15 billion activities.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Supervised ML models trained on smartphone-captured 5G metrics can predict uplink throughput and block error rate across indoor/outdoor and mobility scenarios.
citing papers explorer
-
GenHAR: Generalizing Cross-domain Human Activity Recognition for Last-mile Delivery
GenHAR generalizes cross-domain human activity recognition by 9.97% accuracy and 6.4x lower FLOPs via tokenized sensor data, frequency channel correlations, selective masking, and efficient attention, with deployment detecting 2.15 billion activities.
-
ML and Smartphones Assisted Real-Time Uplink Performance Prediction in 5G Cellular System
Supervised ML models trained on smartphone-captured 5G metrics can predict uplink throughput and block error rate across indoor/outdoor and mobility scenarios.