Výsledky vyhledávání - "HUANG, Yushan"

Report

Towards Low-Energy Adaptive Personalization for Resource-Constrained Devices

Autor: Huang, Yushan, Millar, Josh, Long, Yuxuan, Zhao, Yuchen, Haddadi, Hamed

The personalization of machine learning (ML) models to address data drift is a significant challenge in the context of Internet of Things (IoT) applications. Presently, most approaches focus on fine-tuning either the full base model or its last few l

Externí odkaz: http://arxiv.org/abs/2403.15905

Zobrazit plný text záznamu

Report

Low-Energy On-Device Personalization for MCUs

Autor: Huang, Yushan, Aloufi, Ranya, Cadet, Xavier, Zhao, Yuchen, Barnaghi, Payam, Haddadi, Hamed

Microcontroller Units (MCUs) are ideal platforms for edge applications due to their low cost and energy consumption, and are widely used in various applications, including personalized machine learning tasks, where customized models can enhance the t

Externí odkaz: http://arxiv.org/abs/2403.08040

Zobrazit plný text záznamu

Report

Towards Machine Learning and Inference for Resource-constrained MCUs

Autor: Huang, Yushan, Haddadi, Hamed

Machine learning (ML) is moving towards edge devices. However, ML models with high computational demands and energy consumption pose challenges for ML inference in resource-constrained environments, such as the deep sea. To address these challenges,

Externí odkaz: http://arxiv.org/abs/2305.18954

Zobrazit plný text záznamu

Report

Information Theory Inspired Pattern Analysis for Time-series Data

Autor: Huang, Yushan, Zhao, Yuchen, Capstick, Alexander, Palermo, Francesca, Haddadi, Hamed, Barnaghi, Payam

Current methods for pattern analysis in time series mainly rely on statistical features or probabilistic learning and inference methods to identify patterns and trends in the data. Such methods do not generalize well when applied to multivariate, mul

Externí odkaz: http://arxiv.org/abs/2302.11654

Zobrazit plný text záznamu

Report

Using Entropy Measures for Monitoring the Evolution of Activity Patterns

Autor: Huang, Yushan, Zhao, Yuchen, Haddadi, Hamed, Barnaghi, Payam

In this work, we apply information theory inspired methods to quantify changes in daily activity patterns. We use in-home movement monitoring data and show how they can help indicate the occurrence of healthcare-related events. Three different types

Externí odkaz: http://arxiv.org/abs/2210.01736

Zobrazit plný text záznamu