High performance biomedical time series indexes using salient segmentation.

abstract

• 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.

authors

• Mortazavi, Bobak

published proceedings

• Annu Int Conf IEEE Eng Med Biol Soc

author list (cited authors)

• Woodbridge, J., Mortazavi, B., Bui, A., & Sarrafzadeh, M.

citation count

• 3

complete list of authors

• Woodbridge, Jonathan||Mortazavi, Bobak||Bui, Alex AT||Sarrafzadeh, Majid

publication date

• August 2012

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference  Journal

keywords

• Algorithms
• Computer Simulation
• Diagnosis, Computer-Assisted
• Humans
• Models, Biological
• Monitoring, Ambulatory
• Signal Processing, Computer-Assisted

PubMed Central ID

• 23367072

Digital Object Identifier (DOI)

• 10.1109/EMBC.2012.6347137

start page

• 5086

end page

• 5089

volume

• 2012

URL

• http://dx.doi.org/10.1109/embc.2012.6347137