Towards Implementing Energy-aware Data-driven Intelligence for Smart Health Applications on Mobile Platforms
G. Dumindu Samaraweera, Hung Nguyen, Hadi Zanddizari, Behnam Zeinali,, and J. Morris Chang

TL;DR
This paper reviews recent advances in on-device deep learning for smart health apps, emphasizing energy efficiency, and introduces an adaptive framework to optimize inference based on available mobile resources.
Contribution
It provides a comprehensive review of on-device deep learning advancements and proposes the EAMCR framework for energy-aware, adaptive inference in mobile health applications.
Findings
Empirical evaluation of state-of-the-art ML architectures on mobile devices.
Analysis of energy consumption patterns during deep learning inference.
Demonstration of improved efficiency using the proposed EAMCR framework.
Abstract
Recent breakthrough technological progressions of powerful mobile computing resources such as low-cost mobile GPUs along with cutting-edge, open-source software architectures have enabled high-performance deep learning on mobile platforms. These advancements have revolutionized the capabilities of today's mobile applications in different dimensions to perform data-driven intelligence locally, particularly for smart health applications. Unlike traditional machine learning (ML) architectures, modern on-device deep learning frameworks are proficient in utilizing computing resources in mobile platforms seamlessly, in terms of producing highly accurate results in less inference time. However, on the flip side, energy resources in a mobile device are typically limited. Hence, whenever a complex Deep Neural Network (DNN) architecture is fed into the on-device deep learning framework, while it…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsGreen IT and Sustainability · IoT and Edge/Fog Computing · Context-Aware Activity Recognition Systems
MethodsFLIP
