University of Sussex
Browse
draft_007_HASCA_submission.pdf (586.27 kB)

Smartphone location identification and transport mode recognition using an ensemble of generative adversarial networks

Download (586.27 kB)
We present a generative adversarial network (GAN) approach to recognising modes of transportation from smartphone motion sensor data, as part of our contribution to the Sussex-Huawei Locomotion-Transportation (SHL) recognition challenge 2020 as team noname. Our approach identifies the location where the smartphone of the test dataset is carried on the body through heuristics, after which a location-specific model is trained based on the available published data at this location. Performance on the validation data is 0.95, which we expect to be very similar on the test set, if our estimation of the location of the phone on the test set is correct. We are highly confident in this location estimation. If however it were wrong, an accuracy as low as 30% could be expected.

History

Publication status

  • Published

File Version

  • Accepted version

Journal

Adjunct Proceedings of the 2020 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2020 ACM International Symposium on Wearable Computers

Publisher

ACM

Page range

311-316

Event name

UbiComp/ISWC '20

Event location

Virtual Event Mexico

Event type

conference

Event date

September, 2020

Place of publication

NY, United States

ISBN

9781450380768

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2020-10-14

First Open Access (FOA) Date

2021-02-19

First Compliant Deposit (FCD) Date

2020-10-14

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC