Recognizing multi-modal sensor signals using evolutionary learning of dynamic Bayesian networks

Young Seol Lee, Sung-Bae Cho

Research output: Contribution to journalArticle

Abstract

Multi-modal context-aware systems can provide user-adaptive services, but it requires complicated recognition models with larger resources. The limitations to build optimal models and infer the context efficiently make it difficult to develop practical context-aware systems. We developed a multi-modal context-aware system with various wearable sensors including accelerometers, gyroscopes, physiological sensors, and data gloves. The system used probabilistic models to handle the uncertain and noisy time-series sensor data. In order to construct the efficient probabilistic models, this paper uses an evolutionary algorithm to model structure and EM algorithm to determine parameters. The trained models are selectively inferred based on a semantic network which describes the semantic relations of the contexts and sensors. Experiments with the real data collected show the usefulness of the proposed method.

Original languageEnglish
Pages (from-to)695-707
Number of pages13
JournalPattern Analysis and Applications
Volume17
Issue number4
DOIs
Publication statusPublished - 2014 Oct 16

Fingerprint

Bayesian networks
Sensors
Semantics
Gyroscopes
Model structures
Accelerometers
Evolutionary algorithms
Time series
Experiments
Statistical Models

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Artificial Intelligence

Cite this

@article{d03b3ff442c040e3aca7d30766ea350b,
title = "Recognizing multi-modal sensor signals using evolutionary learning of dynamic Bayesian networks",
abstract = "Multi-modal context-aware systems can provide user-adaptive services, but it requires complicated recognition models with larger resources. The limitations to build optimal models and infer the context efficiently make it difficult to develop practical context-aware systems. We developed a multi-modal context-aware system with various wearable sensors including accelerometers, gyroscopes, physiological sensors, and data gloves. The system used probabilistic models to handle the uncertain and noisy time-series sensor data. In order to construct the efficient probabilistic models, this paper uses an evolutionary algorithm to model structure and EM algorithm to determine parameters. The trained models are selectively inferred based on a semantic network which describes the semantic relations of the contexts and sensors. Experiments with the real data collected show the usefulness of the proposed method.",
author = "Lee, {Young Seol} and Sung-Bae Cho",
year = "2014",
month = "10",
day = "16",
doi = "10.1007/s10044-012-0300-z",
language = "English",
volume = "17",
pages = "695--707",
journal = "Pattern Analysis and Applications",
issn = "1433-7541",
publisher = "Springer London",
number = "4",

}

Recognizing multi-modal sensor signals using evolutionary learning of dynamic Bayesian networks. / Lee, Young Seol; Cho, Sung-Bae.

In: Pattern Analysis and Applications, Vol. 17, No. 4, 16.10.2014, p. 695-707.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Recognizing multi-modal sensor signals using evolutionary learning of dynamic Bayesian networks

AU - Lee, Young Seol

AU - Cho, Sung-Bae

PY - 2014/10/16

Y1 - 2014/10/16

N2 - Multi-modal context-aware systems can provide user-adaptive services, but it requires complicated recognition models with larger resources. The limitations to build optimal models and infer the context efficiently make it difficult to develop practical context-aware systems. We developed a multi-modal context-aware system with various wearable sensors including accelerometers, gyroscopes, physiological sensors, and data gloves. The system used probabilistic models to handle the uncertain and noisy time-series sensor data. In order to construct the efficient probabilistic models, this paper uses an evolutionary algorithm to model structure and EM algorithm to determine parameters. The trained models are selectively inferred based on a semantic network which describes the semantic relations of the contexts and sensors. Experiments with the real data collected show the usefulness of the proposed method.

AB - Multi-modal context-aware systems can provide user-adaptive services, but it requires complicated recognition models with larger resources. The limitations to build optimal models and infer the context efficiently make it difficult to develop practical context-aware systems. We developed a multi-modal context-aware system with various wearable sensors including accelerometers, gyroscopes, physiological sensors, and data gloves. The system used probabilistic models to handle the uncertain and noisy time-series sensor data. In order to construct the efficient probabilistic models, this paper uses an evolutionary algorithm to model structure and EM algorithm to determine parameters. The trained models are selectively inferred based on a semantic network which describes the semantic relations of the contexts and sensors. Experiments with the real data collected show the usefulness of the proposed method.

UR - http://www.scopus.com/inward/record.url?scp=84919464484&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919464484&partnerID=8YFLogxK

U2 - 10.1007/s10044-012-0300-z

DO - 10.1007/s10044-012-0300-z

M3 - Article

AN - SCOPUS:84919464484

VL - 17

SP - 695

EP - 707

JO - Pattern Analysis and Applications

JF - Pattern Analysis and Applications

SN - 1433-7541

IS - 4

ER -