Edge-centric Optimization of Multi-modal ML-driven eHealth Applications

TL;DR

This paper presents edge-centric optimization techniques for multi-modal ML-driven eHealth applications, focusing on compute placement, accuracy-performance trade-offs, and cross-layer co-optimization to enhance efficiency and practical deployment.

Contribution

It introduces novel edge-centric methods for optimizing compute placement and sense-compute co-optimization in multi-modal eHealth applications, addressing run-time variability and network unreliability.

Findings

Improved compute placement strategies for efficiency

Effective trade-offs between accuracy and performance

Validated framework through a pain assessment case study

Abstract

Smart eHealth applications deliver personalized and preventive digital healthcare services to clients through remote sensing, continuous monitoring, and data analytics. Smart eHealth applications sense input data from multiple modalities, transmit the data to edge and/or cloud nodes, and process the data with compute intensive machine learning (ML) algorithms. Run-time variations with continuous stream of noisy input data, unreliable network connection, computational requirements of ML algorithms, and choice of compute placement among sensor-edge-cloud layers affect the efficiency of ML-driven eHealth applications. In this chapter, we present edge-centric techniques for optimized compute placement, exploration of accuracy-performance trade-offs, and cross-layered sense-compute co-optimization for ML-driven eHealth applications. We demonstrate the practical use cases of smart eHealth applications in everyday settings, through a sensor-edge-cloud framework for an objective pain assessment case study.