Human activity recognition using smartphone sensors with two-stage continuous hidden markov models

Charissa Ann Ronao, Sung Bae Cho

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

44 Citations (Scopus)

Abstract

Recognizing human activities from temporal streams of sensory data observations is a very important task on a wide variety of applications in context recognition. Especially for timeseries sensory data, a method that takes into account the inherent sequential characteristics of the data is needed. Moreover, activities are hierarchical in nature, in as much that complex activities can be decomposed to a number of simpler ones. In this paper, we propose a two-stage continuous hidden Markov model (CHMM) approach for the task of activity recognition using accelerometer and gyroscope sensory data gathered from a smartphone. The proposed method consists of first-level CHMMs for coarse classification, which separates stationary and moving activities, and second-level CHMMs for fine classification, which classifies the data into their corresponding activity classes. Random Forests (RF) variable importance measures are exploited to determine the optimal feature subsets for both coarse and fine classification. Experiments show that with the use of a significantly reduced number of features, the proposed method shows competitive performance in comparison to other classification algorithms, achieving an over-all accuracy of 91.76%.

Original languageEnglish
Title of host publication2014 10th International Conference on Natural Computation, ICNC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages681-686
Number of pages6
ISBN (Electronic)9781479951505
DOIs
Publication statusPublished - 2014 Jan 1
Event2014 10th International Conference on Natural Computation, ICNC 2014 - Xiamen, China
Duration: 2014 Aug 192014 Aug 21

Other

Other2014 10th International Conference on Natural Computation, ICNC 2014
CountryChina
CityXiamen
Period14/8/1914/8/21

Fingerprint

Smartphones
Hidden Markov models
Sensors
Gyroscopes
Accelerometers
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Vision and Pattern Recognition
  • Signal Processing
  • Biomedical Engineering

Cite this

Ronao, C. A., & Cho, S. B. (2014). Human activity recognition using smartphone sensors with two-stage continuous hidden markov models. In 2014 10th International Conference on Natural Computation, ICNC 2014 (pp. 681-686). [6975918] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICNC.2014.6975918
Ronao, Charissa Ann ; Cho, Sung Bae. / Human activity recognition using smartphone sensors with two-stage continuous hidden markov models. 2014 10th International Conference on Natural Computation, ICNC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 681-686
@inproceedings{67da7477543d4665b94c4994220484f4,
title = "Human activity recognition using smartphone sensors with two-stage continuous hidden markov models",
abstract = "Recognizing human activities from temporal streams of sensory data observations is a very important task on a wide variety of applications in context recognition. Especially for timeseries sensory data, a method that takes into account the inherent sequential characteristics of the data is needed. Moreover, activities are hierarchical in nature, in as much that complex activities can be decomposed to a number of simpler ones. In this paper, we propose a two-stage continuous hidden Markov model (CHMM) approach for the task of activity recognition using accelerometer and gyroscope sensory data gathered from a smartphone. The proposed method consists of first-level CHMMs for coarse classification, which separates stationary and moving activities, and second-level CHMMs for fine classification, which classifies the data into their corresponding activity classes. Random Forests (RF) variable importance measures are exploited to determine the optimal feature subsets for both coarse and fine classification. Experiments show that with the use of a significantly reduced number of features, the proposed method shows competitive performance in comparison to other classification algorithms, achieving an over-all accuracy of 91.76{\%}.",
author = "Ronao, {Charissa Ann} and Cho, {Sung Bae}",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/ICNC.2014.6975918",
language = "English",
pages = "681--686",
booktitle = "2014 10th International Conference on Natural Computation, ICNC 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Ronao, CA & Cho, SB 2014, Human activity recognition using smartphone sensors with two-stage continuous hidden markov models. in 2014 10th International Conference on Natural Computation, ICNC 2014., 6975918, Institute of Electrical and Electronics Engineers Inc., pp. 681-686, 2014 10th International Conference on Natural Computation, ICNC 2014, Xiamen, China, 14/8/19. https://doi.org/10.1109/ICNC.2014.6975918

Human activity recognition using smartphone sensors with two-stage continuous hidden markov models. / Ronao, Charissa Ann; Cho, Sung Bae.

2014 10th International Conference on Natural Computation, ICNC 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 681-686 6975918.

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

TY - GEN

T1 - Human activity recognition using smartphone sensors with two-stage continuous hidden markov models

AU - Ronao, Charissa Ann

AU - Cho, Sung Bae

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Recognizing human activities from temporal streams of sensory data observations is a very important task on a wide variety of applications in context recognition. Especially for timeseries sensory data, a method that takes into account the inherent sequential characteristics of the data is needed. Moreover, activities are hierarchical in nature, in as much that complex activities can be decomposed to a number of simpler ones. In this paper, we propose a two-stage continuous hidden Markov model (CHMM) approach for the task of activity recognition using accelerometer and gyroscope sensory data gathered from a smartphone. The proposed method consists of first-level CHMMs for coarse classification, which separates stationary and moving activities, and second-level CHMMs for fine classification, which classifies the data into their corresponding activity classes. Random Forests (RF) variable importance measures are exploited to determine the optimal feature subsets for both coarse and fine classification. Experiments show that with the use of a significantly reduced number of features, the proposed method shows competitive performance in comparison to other classification algorithms, achieving an over-all accuracy of 91.76%.

AB - Recognizing human activities from temporal streams of sensory data observations is a very important task on a wide variety of applications in context recognition. Especially for timeseries sensory data, a method that takes into account the inherent sequential characteristics of the data is needed. Moreover, activities are hierarchical in nature, in as much that complex activities can be decomposed to a number of simpler ones. In this paper, we propose a two-stage continuous hidden Markov model (CHMM) approach for the task of activity recognition using accelerometer and gyroscope sensory data gathered from a smartphone. The proposed method consists of first-level CHMMs for coarse classification, which separates stationary and moving activities, and second-level CHMMs for fine classification, which classifies the data into their corresponding activity classes. Random Forests (RF) variable importance measures are exploited to determine the optimal feature subsets for both coarse and fine classification. Experiments show that with the use of a significantly reduced number of features, the proposed method shows competitive performance in comparison to other classification algorithms, achieving an over-all accuracy of 91.76%.

UR - http://www.scopus.com/inward/record.url?scp=84926615131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926615131&partnerID=8YFLogxK

U2 - 10.1109/ICNC.2014.6975918

DO - 10.1109/ICNC.2014.6975918

M3 - Conference contribution

SP - 681

EP - 686

BT - 2014 10th International Conference on Natural Computation, ICNC 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Ronao CA, Cho SB. Human activity recognition using smartphone sensors with two-stage continuous hidden markov models. In 2014 10th International Conference on Natural Computation, ICNC 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 681-686. 6975918 https://doi.org/10.1109/ICNC.2014.6975918