Consensus inference on mobile phone sensors for activity recognition

Huan Songg, Jayaraman J. Thiagarajan, Karthikeyan Natesan Ramamurthy, Andreas Spanias, Pavan Turaga

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

4 Citations (Scopus)

Abstract

The pervasive use of wearable sensors in activity and health monitoring presents a huge potential for building novel data analysis and prediction frameworks. In particular, approaches that can harness data from a diverse set of low-cost sensors for recognition are needed. Many of the existing approaches rely heavily on elaborate feature engineering to build robust recognition systems, and their performance is often limited by the inaccuracies in the data. In this paper, we develop a novel two-stage recognition system that enables a systematic fusion of complementary information from multiple sensors in a linear graph embedding setting, while employing an ensemble classifier phase that leverages the discriminative power of different feature extraction strategies. Experimental results on a challenging dataset show that our framework greatly improves the recognition performance when compared to using any single sensor.

Original languageEnglish (US)
Title of host publication2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2294-2298
Number of pages5
Volume2016-May
ISBN (Electronic)9781479999880
DOIs
StatePublished - May 18 2016
Event41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Shanghai, China
Duration: Mar 20 2016Mar 25 2016

Other

Other41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016
CountryChina
CityShanghai
Period3/20/163/25/16

Fingerprint

Mobile phones
Sensors
Feature extraction
Classifiers
Fusion reactions
Health
Monitoring
Costs

Keywords

  • Activity recognition
  • Multi-layer graph
  • Reference-based classification
  • Sensor fusion
  • Time-delay embedding

ASJC Scopus subject areas

  • Signal Processing
  • Software
  • Electrical and Electronic Engineering

Cite this

Songg, H., Thiagarajan, J. J., Ramamurthy, K. N., Spanias, A., & Turaga, P. (2016). Consensus inference on mobile phone sensors for activity recognition. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings (Vol. 2016-May, pp. 2294-2298). [7472086] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2016.7472086

Consensus inference on mobile phone sensors for activity recognition. / Songg, Huan; Thiagarajan, Jayaraman J.; Ramamurthy, Karthikeyan Natesan; Spanias, Andreas; Turaga, Pavan.

2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. p. 2294-2298 7472086.

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

Songg, H, Thiagarajan, JJ, Ramamurthy, KN, Spanias, A & Turaga, P 2016, Consensus inference on mobile phone sensors for activity recognition. in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. vol. 2016-May, 7472086, Institute of Electrical and Electronics Engineers Inc., pp. 2294-2298, 41st IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, 3/20/16. https://doi.org/10.1109/ICASSP.2016.7472086
Songg H, Thiagarajan JJ, Ramamurthy KN, Spanias A, Turaga P. Consensus inference on mobile phone sensors for activity recognition. In 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May. Institute of Electrical and Electronics Engineers Inc. 2016. p. 2294-2298. 7472086 https://doi.org/10.1109/ICASSP.2016.7472086
Songg, Huan ; Thiagarajan, Jayaraman J. ; Ramamurthy, Karthikeyan Natesan ; Spanias, Andreas ; Turaga, Pavan. / Consensus inference on mobile phone sensors for activity recognition. 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings. Vol. 2016-May Institute of Electrical and Electronics Engineers Inc., 2016. pp. 2294-2298
@inproceedings{e1880653fbb54de49712a933f7747eb0,
title = "Consensus inference on mobile phone sensors for activity recognition",
abstract = "The pervasive use of wearable sensors in activity and health monitoring presents a huge potential for building novel data analysis and prediction frameworks. In particular, approaches that can harness data from a diverse set of low-cost sensors for recognition are needed. Many of the existing approaches rely heavily on elaborate feature engineering to build robust recognition systems, and their performance is often limited by the inaccuracies in the data. In this paper, we develop a novel two-stage recognition system that enables a systematic fusion of complementary information from multiple sensors in a linear graph embedding setting, while employing an ensemble classifier phase that leverages the discriminative power of different feature extraction strategies. Experimental results on a challenging dataset show that our framework greatly improves the recognition performance when compared to using any single sensor.",
keywords = "Activity recognition, Multi-layer graph, Reference-based classification, Sensor fusion, Time-delay embedding",
author = "Huan Songg and Thiagarajan, {Jayaraman J.} and Ramamurthy, {Karthikeyan Natesan} and Andreas Spanias and Pavan Turaga",
year = "2016",
month = "5",
day = "18",
doi = "10.1109/ICASSP.2016.7472086",
language = "English (US)",
volume = "2016-May",
pages = "2294--2298",
booktitle = "2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Consensus inference on mobile phone sensors for activity recognition

AU - Songg, Huan

AU - Thiagarajan, Jayaraman J.

AU - Ramamurthy, Karthikeyan Natesan

AU - Spanias, Andreas

AU - Turaga, Pavan

PY - 2016/5/18

Y1 - 2016/5/18

N2 - The pervasive use of wearable sensors in activity and health monitoring presents a huge potential for building novel data analysis and prediction frameworks. In particular, approaches that can harness data from a diverse set of low-cost sensors for recognition are needed. Many of the existing approaches rely heavily on elaborate feature engineering to build robust recognition systems, and their performance is often limited by the inaccuracies in the data. In this paper, we develop a novel two-stage recognition system that enables a systematic fusion of complementary information from multiple sensors in a linear graph embedding setting, while employing an ensemble classifier phase that leverages the discriminative power of different feature extraction strategies. Experimental results on a challenging dataset show that our framework greatly improves the recognition performance when compared to using any single sensor.

AB - The pervasive use of wearable sensors in activity and health monitoring presents a huge potential for building novel data analysis and prediction frameworks. In particular, approaches that can harness data from a diverse set of low-cost sensors for recognition are needed. Many of the existing approaches rely heavily on elaborate feature engineering to build robust recognition systems, and their performance is often limited by the inaccuracies in the data. In this paper, we develop a novel two-stage recognition system that enables a systematic fusion of complementary information from multiple sensors in a linear graph embedding setting, while employing an ensemble classifier phase that leverages the discriminative power of different feature extraction strategies. Experimental results on a challenging dataset show that our framework greatly improves the recognition performance when compared to using any single sensor.

KW - Activity recognition

KW - Multi-layer graph

KW - Reference-based classification

KW - Sensor fusion

KW - Time-delay embedding

UR - http://www.scopus.com/inward/record.url?scp=84973321074&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84973321074&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2016.7472086

DO - 10.1109/ICASSP.2016.7472086

M3 - Conference contribution

VL - 2016-May

SP - 2294

EP - 2298

BT - 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -