Enabling Machine Learning Across Heterogeneous Sensor Networks with Graph Autoencoders

12/12/2019
by   Johan Medrano, et al.
0

Machine Learning (ML) has been applied to enable many life-assisting appli-cations, such as abnormality detection and emdergency request for the soli-tary elderly. However, in most cases machine learning algorithms depend on the layout of the target Internet of Things (IoT) sensor network. Hence, to deploy an application across Heterogeneous Sensor Networks (HSNs), i.e. sensor networks with different sensors type or layouts, it is required to repeat the process of data collection and ML algorithm training. In this paper, we introduce a novel framework leveraging deep learning for graphs to enable using the same activity recognition system across HSNs deployed in differ-ent smart homes. Using our framework, we were able to transfer activity classifiers trained with activity labels on a source HSN to a target HSN, reaching about 75 labels. Moreover, our model can quickly adapt to unseen sensor layouts, which makes it highly suitable for the gradual deployment of real-world ML-based applications. In addition, we show that our framework is resilient to suboptimal graph representations of HSNs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/17/2022

Label Flipping Data Poisoning Attack Against Wearable Human Activity Recognition System

Human Activity Recognition (HAR) is a problem of interpreting sensor dat...
research
09/03/2019

Personalizing Smartwatch Based Activity Recognition Using Transfer Learning

Smartwatches are increasingly being used to recognize human daily life a...
research
09/12/2023

Overview of Human Activity Recognition Using Sensor Data

Human activity recognition (HAR) is an essential research field that has...
research
09/27/2021

Automated Estimation of Construction Equipment Emission using Inertial Sensors and Machine Learning Models

The construction industry is one of the main producers of greenhouse gas...
research
10/05/2022

SECOE: Alleviating Sensors Failure in Machine Learning-Coupled IoT Systems

Machine learning (ML) applications continue to revolutionize many domain...
research
09/21/2020

A Sequential Modelling Approach for Indoor Temperature Prediction and Heating Control in Smart Buildings

The rising availability of large volume data has enabled a wide applicat...
research
01/01/2021

MoSen: Activity Modelling in Multiple-Occupancy Smart Homes

Smart home solutions increasingly rely on a variety of sensors for behav...

Please sign up or login with your details

Forgot password? Click here to reset