Skip to content

Research at St Andrews

Visualization as Intermediate Representations (VLAIR) for human activity recognition

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Open Access Status

  • Embargoed (until 1/01/50)

Abstract

Ambient, binary, event-driven sensor data is useful for many human activity recognition applications such as smart homes and ambient-assisted living. These sensors are privacy-preserving, unobtrusive, inexpensive and easy to deploy in scenarios that require detection of simple activities such as going to sleep, and leaving the house. However, classification performance is still a challenge, especially when multiple people share the same space or when different activities take place in the same areas. To improve classification performance we develop what we call a Visualization as Intermediate Representations (VLAIR) approach. The main idea is to re-represent the data as visualizations (generated pixel images) in a similar way as how visualizations are created for humans to analyze and communicate data. Then we can feed these images to a convolutional neural network whose strength resides in extracting effective visual features. We have tested five variants (mappings) of the VLAIR approach and compared them to a collection of classifiers commonly used in classic human activity recognition. The best of the VLAIR approaches outperforms the best baseline, with strong advantage in recognising less frequent activities and distinguishing users and activities in common areas. We conclude the paper with a discussion on why and how VLAIR can be useful in human activity recognition scenarios and beyond.
Close

Details

Original languageEnglish
Title of host publication14th EAI International Conference on Pervasive Computing Technologies for Healthcare (PervasiveHealth 2020)
PublisherACM
Number of pages10
Publication statusAccepted/In press - 12 Mar 2020
Event14th EAI International Conference on Pervasive Computing Technologies for Healthcare (EAI PervasiveHealth 2020) - Atlanta, United States
Duration: 20 Mar 2020 → …
Conference number: 14

Conference

Conference14th EAI International Conference on Pervasive Computing Technologies for Healthcare (EAI PervasiveHealth 2020)
Abbreviated titleEAI PervasiveHealth 2020
CountryUnited States
CityAtlanta
Period20/03/20 → …

    Research areas

  • Information visualization, Intermediate representations, Human activity recognition, Convolutional neural networks, Smart homes

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Unsupervised domain adaptation for activity recognition across heterogeneous datasets

    Rosales Sanabria, A. & Ye, J., 14 Mar 2020, In : Pervasive and Mobile Computing. In press, 101147.

    Research output: Contribution to journalArticle

  2. Synch-Graph: multisensory emotion recognition through neural synchrony via graph convolutional networks

    Mansouri Benssassi, E. & Ye, J., 7 Feb 2020, Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-2020). AAAI Press, p. 1-8 8 p.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

  3. XLearn: learning activity labels across heterogeneous datasets

    Ye, J., Dobson, S. A. & Zambonelli, F., Jan 2020, In : ACM Transactions on Intelligent Systems and Technology. 11, 2, 28 p., 17.

    Research output: Contribution to journalArticle

  4. Lifelong learning in sensor-based human activity recognition

    Ye, J., Dobson, S. A. & Zambonelli, F., 18 Nov 2019, In : IEEE Pervasive Computing. 18, 3, p. 49-58 10 p.

    Research output: Contribution to journalArticle

  5. Representation learning for minority and subtle activities in a smart home environment

    Rosales Sanabria, A., Kelsey, T., Dobson, S. A. & Ye, J., 28 Oct 2019, In : Journal of Ambient Intelligence and Smart Environments. Pre-press, p. 1-19

    Research output: Contribution to journalArticle

ID: 267071323

Top