Factored state-abstract hidden Markov models for activity recognition using pervasive multi-modal sensors

Current probabilistic models for activity recognition do not incorporate much sensory input data due to the problem of state space explosion. In this paper, we propose a model for activity recognition, called the Factored State-Abtract Hidden Markov Model (FS-AHMM) to allow us to integrate many sens...

Full description

Bibliographic Details
Main Authors: Tran, Dung, Phung, Dinh, Bui, H.H., Venkatesh, Svetha
Other Authors: M Palaniswami
Format: Conference Paper
Published: IEEE Computer Society Press 2005
Online Access:http://hdl.handle.net/20.500.11937/11457
_version_ 1848747811101736960
author Tran, Dung
Phung, Dinh
Bui, H.H.
Venkatesh, Svetha
author2 M Palaniswami
author_facet M Palaniswami
Tran, Dung
Phung, Dinh
Bui, H.H.
Venkatesh, Svetha
author_sort Tran, Dung
building Curtin Institutional Repository
collection Online Access
description Current probabilistic models for activity recognition do not incorporate much sensory input data due to the problem of state space explosion. In this paper, we propose a model for activity recognition, called the Factored State-Abtract Hidden Markov Model (FS-AHMM) to allow us to integrate many sensors for improving recognition performance. The proposed FS-AHMM is an extension of the Abstract Hidden Markov Model which applies the concept of factored state representations to compactly represent the state transitions. The parameters of the FS-AHMM are estimated using the EM algorithm from the data acquired through multiple multi-modal sensors and cameras. The model is evaluated and compared with other existing models on real-world data. The results show that the proposed model outperforms other models and that the integrated sensor information helps in recognizing activity more accurately.
first_indexed 2025-11-14T06:55:04Z
format Conference Paper
id curtin-20.500.11937-11457
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T06:55:04Z
publishDate 2005
publisher IEEE Computer Society Press
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-114572018-12-14T00:48:20Z Factored state-abstract hidden Markov models for activity recognition using pervasive multi-modal sensors Tran, Dung Phung, Dinh Bui, H.H. Venkatesh, Svetha M Palaniswami Current probabilistic models for activity recognition do not incorporate much sensory input data due to the problem of state space explosion. In this paper, we propose a model for activity recognition, called the Factored State-Abtract Hidden Markov Model (FS-AHMM) to allow us to integrate many sensors for improving recognition performance. The proposed FS-AHMM is an extension of the Abstract Hidden Markov Model which applies the concept of factored state representations to compactly represent the state transitions. The parameters of the FS-AHMM are estimated using the EM algorithm from the data acquired through multiple multi-modal sensors and cameras. The model is evaluated and compared with other existing models on real-world data. The results show that the proposed model outperforms other models and that the integrated sensor information helps in recognizing activity more accurately. 2005 Conference Paper http://hdl.handle.net/20.500.11937/11457 10.1109/ISSNIP.2005.1595601 IEEE Computer Society Press restricted
spellingShingle Tran, Dung
Phung, Dinh
Bui, H.H.
Venkatesh, Svetha
Factored state-abstract hidden Markov models for activity recognition using pervasive multi-modal sensors
title Factored state-abstract hidden Markov models for activity recognition using pervasive multi-modal sensors
title_full Factored state-abstract hidden Markov models for activity recognition using pervasive multi-modal sensors
title_fullStr Factored state-abstract hidden Markov models for activity recognition using pervasive multi-modal sensors
title_full_unstemmed Factored state-abstract hidden Markov models for activity recognition using pervasive multi-modal sensors
title_short Factored state-abstract hidden Markov models for activity recognition using pervasive multi-modal sensors
title_sort factored state-abstract hidden markov models for activity recognition using pervasive multi-modal sensors
url http://hdl.handle.net/20.500.11937/11457