ToSiM-IoT: Towards a sustainable optimisation of machine learning tasks in Internet of Things

Kaushal, Ashish, Almurshed, Osama, Muftah, Asmail, Auluck, Nitin and Rana, Omer ORCID: https://orcid.org/0000-0003-3597-2646 2025. ToSiM-IoT: Towards a sustainable optimisation of machine learning tasks in Internet of Things. IEEE Internet of Things Journal 10.1109/JIOT.2025.3537169

Preview

PDF - Accepted Post-Print Version Download (6MB) | Preview

Abstract

With the rise of digital infrastructure and Internet of Things (IoT), a substantial amount of data is continuously generated that needs to be processed efficiently. While modern artificial intelligence (AI) approaches have shown good capabilities in handling large volumes of data, their excessive demands for memory and processing power result in very high utilisation of resources. In this work, we propose ToSiM-IoT, an optimisation framework that introduces a layer selection approach to identify an ideal mix of active, and inactive layers, using a genetic algorithm for model training. Next, we design a pruning mechanism that identifies performance-critical features using heatmap visualisation, during model inference, and eliminates the remaining features. Two machine learning (ML) models – InceptionV3 and VGG16, have been evaluated on an agricultural weed detection scenario, using the DeepWeeds image classification dataset. Experimental results demonstrate that our framework can achieve a significant reduction in model size and training time, while maintaining high accuracy, for both models. Therefore, this approach provides the potential to be efficiently deployed on intelligent IoT systems where computational capabilities are limited.

Item Type:	Article
Status:	In Press
Schools:	Schools > Computer Science & Informatics
Publisher:	Institute of Electrical and Electronics Engineers
ISSN:	2327-4662
Date of First Compliant Deposit:	6 February 2025
Date of Acceptance:	20 January 2025
Last Modified:	18 Feb 2025 12:15
URI:	https://orca.cardiff.ac.uk/id/eprint/175977

Actions (repository staff only)

Edit Item