Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models

Human activity recognition has been gaining more and more attention from researchers in recent years, particularly with the use of widespread and commercially available devices such as smartphones. However, most of the existing works focus on discriminative classifiers while neglecting the inherent...

Full description

Saved in:
Bibliographic Details
Main Authors: Charissa Ann Ronao, Sung-Bae Cho
Format: Article
Language:English
Published: Wiley 2017-01-01
Series:International Journal of Distributed Sensor Networks
Online Access:https://doi.org/10.1177/1550147716683687
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832553126162333696
author Charissa Ann Ronao
Sung-Bae Cho
author_facet Charissa Ann Ronao
Sung-Bae Cho
author_sort Charissa Ann Ronao
collection DOAJ
description Human activity recognition has been gaining more and more attention from researchers in recent years, particularly with the use of widespread and commercially available devices such as smartphones. However, most of the existing works focus on discriminative classifiers while neglecting the inherent time-series and continuous characteristics of sensor data. To address this, we propose a two-stage continuous hidden Markov model framework, which also takes advantage of the innate hierarchical structure of basic activities. This kind of system architecture not only enables the use of different feature subsets on different subclasses, which effectively reduces feature computation overhead, but also allows for varying number of states and iterations. Experiments show that the hierarchical structure dramatically increases classification performance. We analyze the behavior of the accelerometer and gyroscope signals for each activity through graphs, and with added fine tuning of states and training iterations, the proposed method is able to achieve an overall accuracy of up to 93.18%, which is the best performance among the state-of-the-art classifiers for the problem at hand.
format Article
id doaj-art-64e704feda5649bc8a7249141d722ecf
institution Kabale University
issn 1550-1477
language English
publishDate 2017-01-01
publisher Wiley
record_format Article
series International Journal of Distributed Sensor Networks
spelling doaj-art-64e704feda5649bc8a7249141d722ecf2025-02-03T05:55:22ZengWileyInternational Journal of Distributed Sensor Networks1550-14772017-01-011310.1177/1550147716683687Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov modelsCharissa Ann RonaoSung-Bae ChoHuman activity recognition has been gaining more and more attention from researchers in recent years, particularly with the use of widespread and commercially available devices such as smartphones. However, most of the existing works focus on discriminative classifiers while neglecting the inherent time-series and continuous characteristics of sensor data. To address this, we propose a two-stage continuous hidden Markov model framework, which also takes advantage of the innate hierarchical structure of basic activities. This kind of system architecture not only enables the use of different feature subsets on different subclasses, which effectively reduces feature computation overhead, but also allows for varying number of states and iterations. Experiments show that the hierarchical structure dramatically increases classification performance. We analyze the behavior of the accelerometer and gyroscope signals for each activity through graphs, and with added fine tuning of states and training iterations, the proposed method is able to achieve an overall accuracy of up to 93.18%, which is the best performance among the state-of-the-art classifiers for the problem at hand.https://doi.org/10.1177/1550147716683687
spellingShingle Charissa Ann Ronao
Sung-Bae Cho
Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models
International Journal of Distributed Sensor Networks
title Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models
title_full Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models
title_fullStr Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models
title_full_unstemmed Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models
title_short Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models
title_sort recognizing human activities from smartphone sensors using hierarchical continuous hidden markov models
url https://doi.org/10.1177/1550147716683687
work_keys_str_mv AT charissaannronao recognizinghumanactivitiesfromsmartphonesensorsusinghierarchicalcontinuoushiddenmarkovmodels
AT sungbaecho recognizinghumanactivitiesfromsmartphonesensorsusinghierarchicalcontinuoushiddenmarkovmodels