ISCA: Intelligent Sense-Compute Adaptive Co-optimization of Multimodal Machine Learning Kernels for Resilient mHealth Services on Wearables

mHealth services use multi-modal machine learning (MMML) models to process physiological and contextual data for automated decision making. Run-time input data perturbations degrade the prediction accuracy of MMML models, while continuous sensing, transmission, and processing of such noisy data drai...

Full description

Saved in:
Bibliographic Details
Published in:IEEE design and test 2024-09, p.1-1
Main Authors: Alikhani, Hamidreza, Kanduri, Anil, Naeini, Emad Kasaeyan, Shahhosseini, Sina, Liljeberg, Pasi, Rahmani, Amir M., Dutt, Nikil
Format: Magazinearticle
Language:English
Subjects:
Accuracy
Adaptation models
Computational modeling
Data models
Efficient inference
Electrocardiography
Energy efficiency
Feature extraction
Internet of Things
Multi-modal machine learning
Noise measurement
Pain
Perturbation methods
Sensors
Wearable computing
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:mHealth services use multi-modal machine learning (MMML) models to process physiological and contextual data for automated decision making. Run-time input data perturbations degrade the prediction accuracy of MMML models, while continuous sensing, transmission, and processing of such noisy data drains the energy resources of wearable devices. Identifying qualitative input data and dropping non-insightful modalities can improve prediction accuracy and energy efficiency simultaneously. We propose a ISCA: a sense-compute adaptive co-optimization framework that employs reinforcement learning to jointly determine sensing and compute configuration settings which minimizes energy consumption while providing accuracy guarantees. Our approach considers run-time noise levels to selectively sense specific modalities, followed by selecting MMML models that are suitable for the chosen modality combination. We demonstrate the effectiveness of our solution using an exemplar mHealth application of pain assessment over various noise levels. Our solution achieves up to 23% improvement in prediction accuracy compared to Noise-agnostic method, and 42% energy savings in comparison with state-of-the-art selective sensing frameworks.
ISSN:2168-2356
2168-2364
DOI:10.1109/MDAT.2024.3469828