Abstract
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.
| Original language | English |
|---|---|
| Journal | International Journal of Distributed Sensor Networks |
| Volume | 13 |
| Issue number | 1 |
| DOIs | |
| Publication status | Published - 2017 Jan 1 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Engineering(all)
- Computer Networks and Communications
Cite this
}
Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models. / Ronao, Charissa Ann; Cho, Sung Bae.
In: International Journal of Distributed Sensor Networks, Vol. 13, No. 1, 01.01.2017.Research output: Contribution to journal › Article
TY - JOUR
T1 - Recognizing human activities from smartphone sensors using hierarchical continuous hidden Markov models
AU - Ronao, Charissa Ann
AU - Cho, Sung Bae
PY - 2017/1/1
Y1 - 2017/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85011854067&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85011854067&partnerID=8YFLogxK
U2 - 10.1177/1550147716683687
DO - 10.1177/1550147716683687
M3 - Article
AN - SCOPUS:85011854067
VL - 13
JO - International Journal of Distributed Sensor Networks
JF - International Journal of Distributed Sensor Networks
SN - 1550-1329
IS - 1
ER -