A method for extracting temporal parameters based on hidden Markov models in body sensor networks with inertial sensors

Eric Guenterberg; Allen Y Yang; Hassan Ghasemzadeh; Roozbeh Jafari; Ruzena Bajcsy; S Shankar Sastry

doi:10.1109/TITB.2009.2028421

Back

A method for extracting temporal parameters based on hidden Markov models in body sensor networks with inertial sensors

Journal article

Open access

A method for extracting temporal parameters based on hidden Markov models in body sensor networks with inertial sensors

Eric Guenterberg, Allen Y Yang, Hassan Ghasemzadeh, Roozbeh Jafari, Ruzena Bajcsy and S Shankar Sastry

IEEE transactions on information technology in biomedicine, Vol.13(6), pp.1019-1030

11/2009

DOI: https://doi.org/10.1109/TITB.2009.2028421

Handle:

https://hdl.handle.net/2376/116131

PMID: 19726268

Files and links (1)

url

https://doi.org/10.1109/TITB.2009.2028421View

Published (Version of record) Open

Abstract

Young Adult

Motion

Markov Chains

Reproducibility of Results

Monitoring, Ambulatory - methods

Artificial Intelligence

Signal Processing, Computer-Assisted

Models, Genetic

Pattern Recognition, Automated

Gait - physiology

Algorithms

Human movement models often divide movements into parts. In walking, the stride can be segmented into four different parts, and in golf and other sports, the swing is divided into sections based on the primary direction of motion. These parts are often divided based on key events, also called temporal parameters. When analyzing a movement, it is important to correctly locate these key events, and so automated techniques are needed. There exist many methods for dividing specific actions using data from specific sensors, but for new sensors or sensing positions, new techniques must be developed. We introduce a generic method for temporal parameter extraction called the hidden Markov event model based on hidden Markov models. Our method constrains the state structure to facilitate precise location of key events. This method can be quickly adapted to new movements and new sensors/sensor placements. Furthermore, it generalizes well to subjects not used for training. A multiobjective optimization technique using genetic algorithms is applied to decrease error and increase cross-subject generalizability. Further, collaborative techniques are explored. We validate this method on a walking dataset by using inertial sensors placed on various locations on a human body. Our technique is designed to be computationally complex for training, but computationally simple at runtime to allow deployment on resource-constrained sensor nodes.

Metrics

9 Record Views

See more details

Details

Title: A method for extracting temporal parameters based on hidden Markov models in body sensor networks with inertial sensors
Creators: Eric Guenterberg - Embedded Systems and Signal Processing Laboratory, Department of Electrical Engineering, University of Texas at Dallas, Dallas, TX 75080, USA. etg062000@utdallas.edu
Allen Y Yang
Hassan Ghasemzadeh
Roozbeh Jafari
Ruzena Bajcsy
S Shankar Sastry
Publication Details: IEEE transactions on information technology in biomedicine, Vol.13(6), pp.1019-1030
Academic Unit: School of Electrical Engineering and Computer Science
Publisher: United States
Identifiers: 99900547987501842
Language: English
Resource Type: Journal article