Search Results for author:
Found 2 papers, 0 papers with code
Seeker: Synergizing Mobile and Energy Harvesting Wearable Sensors for Human Activity Recognition
To address these challenges, we propose \emph{Seeker}, a novel approach to efficiently execute DNN inferences for Human Activity Recognition (HAR) tasks, using both an EH-WSN and a host mobile device.
Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud
Towards this, we proposeCocktail, a costeffective ensembling-based model serving framework. Cock-tailcomprises of two key components: (i) a dynamic modelselection framework, which reduces the number of modelsin the ensemble, while satisfying the accuracy and latencyrequirements; (ii) an adaptive resource management (RM)framework that employs a distributed proactive autoscalingpolicy combined with importance sampling, to efficiently allo-cate resources for the models.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
