High performance biomedical time series indexes using salient segmentation

The advent of remote and wearable medical sensing has created a dire need for efficient medical time series databases. Wearable medical sensing devices provide continuous patient monitoring by various types of sensors and have the potential to create massive amounts of data. Therefore, time series d...

Full description

Saved in:
Bibliographic Details
Published in:2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2012-01, Vol.2012, p.5086-5089
Main Authors: Woodbridge, J., Mortazavi, B., Bui, A. A. T., Sarrafzadeh, M.
Format: Article
Language:English
Subjects:
Algorithms
Computer Simulation
Diagnosis, Computer-Assisted - methods
Electrocardiography
Humans
Indexing
Models, Biological
Monitoring, Ambulatory - methods
Sensors
Signal Processing, Computer-Assisted
Time series analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The advent of remote and wearable medical sensing has created a dire need for efficient medical time series databases. Wearable medical sensing devices provide continuous patient monitoring by various types of sensors and have the potential to create massive amounts of data. Therefore, time series databases must utilize highly optimized indexes in order to efficiently search and analyze stored data. This paper presents a highly efficient technique for indexing medical time series signals using Locality Sensitive Hashing (LSH). Unlike previous work, only salient (or interesting) segments are inserted into the index. This technique reduces search times by up to 95% while yielding near identical search results.
ISSN:1094-687X
1558-4615
2694-0604
DOI:10.1109/EMBC.2012.6347137