HAC-M-DNN: hardware aware compression of sustainable multimodal deep neural networks for efficient tinyML deployment

Tools

Rashid, H-A, Kanjo, E ORCID: https://orcid.org/0000-0002-1720-0661 and Mohsenin, T, 2025. HAC-M-DNN: hardware aware compression of sustainable multimodal deep neural networks for efficient tinyML deployment. In: Proceedings of the 12th IEEE Technologies for Sustainability Conference (SusTech 2025). IEEE. ISBN 9798331504311

Full text not available from this repository.

Official URL: https://doi.org/10.1109/SusTech63138.2025.11025634

Abstract

The increasing complexity and energy consumption of advanced artificial intelligence algorithms pose a significant challenge to environmental sustainability. This paper addresses this issue by introducing HAC-M-DNN, a system designed for energy-efficient tinyML deployment. HAC-M-DNN effectively manages multimodal data, develops carbon footprint-efficient multimodal deep neural networks, and employs hardware-aware model compression techniques to optimize memory utilization and power efficiency. We validated HAC-M-DNN through two tinyML application case studies: semantic segmentation of crop and weed species using multimodal RGB-D imaging and scene understanding from multimodal image and audio data, achiev- ing accuracies of 70% and 95%, respectively. Our hardware- aware results demonstrate that HAC-M-DNN generates highly accurate, compact models deployable on resource-constrained devices, achieving up to 85× and 177× reduction in memory usage respectively for two case-studies. These models also exhibit low latency and exceptional power efficiency. The outcomes of this study underscore the potential of HAC-M-DNN to drive both technological advancement and environmental responsibility in the field of tinyML, offering a sustainable alternative to traditional, resource-intensive AI models

Item Type:	Chapter in book
Description:	Paper presenterd at the 12th IEEE Technologies for Sustainability Conference (SusTech 2025), Santa Ana, California, United States, 20-23 April 2025.
Creators:	Rashid, H.-A., Kanjo, E. and Mohsenin, T.
Publisher:	IEEE
Date:	12 June 2025
ISBN:	9798331504311
Identifiers:	Number Type 10.1109/SusTech63138.2025.11025634 DOI 2451120 Other
Divisions:	Schools > School of Science and Technology
Record created by:	Jonathan Gallacher
Date Added:	16 Jun 2025 12:07
Last Modified:	16 Jun 2025 12:07
URI:	https://irep.ntu.ac.uk/id/eprint/53737