Towards Applying Deep Learning to The Internet of Things: A Model and A Framework

TL;DR

This paper proposes a deep learning optimization model and a management framework to facilitate the deployment of deep learning networks in IoT applications, addressing trade-offs in accuracy, latency, and cost.

Contribution

It introduces a novel DL optimization model and an initial framework for managing DL models tailored for IoT, aiding selection and reuse.

Findings

Provides criteria for selecting optimal DL models for IoT scenarios

Designs a framework to manage DL optimization models effectively

Enhances decision-making for deploying DLNs in IoT environments

Abstract

Deep Learning (DL) modeling has been a recent topic of interest. With the accelerating need to embed Deep Learning Networks (DLNs) to the Internet of Things (IoT) applications, many DL optimization techniques were developed to enable applying DL to IoTs. However, despite the plethora of DL optimization techniques, there is always a trade-off between accuracy, latency, and cost. Moreover, there are no specific criteria for selecting the best optimization model for a specific scenario. Therefore, this research aims at providing a DL optimization model that eases the selection and re-using DLNs on IoTs. In addition, the research presents an initial design for a DL optimization model management framework. This framework would help organizations choose the optimal DL optimization model that maximizes performance without sacrificing quality. The research would add to the IS design science knowledge as well as the industry by providing insights to many IT managers to apply DLNs to IoTs such as machines and robots.