PID6448055.pdf (621.86 kB)

Classifying imbalanced multi-modal sensor data for human activity recognition in a smart home using deep learning

Download (621.86 kB)
conference contribution
posted on 08.10.2020 by Ali A Alani, Georgina Cosma, Aboozar Taherkhani
In smart homes, data generated from real-time sensors for human activity recognition is complex, noisy and imbalanced. It is a significant challenge to create machine learning models that can classify activities which are not as commonly occurring as other activities. Machine learning models designed to classify imbalanced data are biased towards learning the more commonly occurring classes. Such learning bias occurs naturally, since the models better learn classes which contain more records. This paper examines whether fusing real-world imbalanced multi-modal sensor data improves classification results as opposed to using unimodal data; and compares deep learning approaches to dealing with imbalanced multi-modal sensor data when using various resampling methods and deep learning models. Experiments were carried out using a large multi-modal sensor dataset generated from the Sensor Platform for HEalthcare in a Residential Environment (SPHERE). The data comprises 16104 samples, where each sample comprises 5608 features and belongs to one of 20 activities (classes). Experimental results using SPHERE demonstrate the challenges of dealing with imbalanced multi-modal data and highlight the importance of having a suitable number of samples within each class for sufficiently training and testing deep learning models. Furthermore, the results revealed that when fusing the data and using the Synthetic Minority Oversampling Technique (SMOTE) to correct class imbalance, CNN-LSTM achieved the highest classification accuracy of 93.67% followed by CNN, 93.55%, and LSTM, i.e. 92.98%.

Funding

The Leverhulme Trust for the Research Project Grant RPG-2016-252 entitled Novel Approaches for Constructing Optimised Multi-modal Data Spaces

History

School

  • Science

Department

  • Computer Science

Published in

2020 International Joint Conference on Neural Networks (IJCNN)

Pages

1 - 8

Source

2020 International Joint Conference on Neural Networks (IJCNN)

Publisher

IEEE

Version

AM (Accepted Manuscript)

Rights holder

© IEEE

Publisher statement

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Acceptance date

20/03/2020

Publication date

2020-09-28

Copyright date

2020

ISBN

9781728169262

eISSN

2161-4407

Language

en

Location

Glasgow, U.K

Event dates

19th July 2020 - 24th July 2020

Depositor

Dr Georgina Cosma Deposit date: 7 October 2020

Exports