Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice
<p>Abstract</p> <p>This work presents a non-invasive high-throughput system for automatically detecting characteristic behaviours in mice over extended periods of time, useful for phenotyping experiments. The system classifies time intervals on the order of 2 to 4 seconds as corres...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2008-04-01
|
| Series: | BioMedical Engineering OnLine |
| Online Access: | http://www.biomedical-engineering-online.com/content/7/1/14 |
| _version_ | 1811297079448829952 |
|---|---|
| author | Crane Eli R Medonza Dharshan C Donohue Kevin D O'Hara Bruce F |
| author_facet | Crane Eli R Medonza Dharshan C Donohue Kevin D O'Hara Bruce F |
| author_sort | Crane Eli R |
| collection | DOAJ |
| description | <p>Abstract</p> <p>This work presents a non-invasive high-throughput system for automatically detecting characteristic behaviours in mice over extended periods of time, useful for phenotyping experiments. The system classifies time intervals on the order of 2 to 4 seconds as corresponding to motions consistent with either active wake or inactivity associated with sleep. A single Polyvinylidine Difluoride (PVDF) sensor on the cage floor generates signals from motion resulting in pressure. This paper develops a linear classifier based on robust features extracted from normalized power spectra and autocorrelation functions, as well as novel features from the collapsed average (autocorrelation of complex spectrum), which characterize transient and periodic properties of the signal envelope. Performance is analyzed through an experiment comparing results from direct human observation and classification of the different behaviours with an automatic classifier used in conjunction with this system. Experimental results from over 28.5 hours of data from 4 mice indicate a 94% classification rate relative to the human observations. Examples of sequential classifications (2 second increments) over transition regions between sleep and wake behaviour are also presented to demonstrate robust performance to signal variation and explain performance limitations.</p> |
| first_indexed | 2024-04-13T05:58:43Z |
| format | Article |
| id | doaj.art-8c07af3289d54058a85dac029e5f1b03 |
| institution | Directory Open Access Journal |
| issn | 1475-925X |
| language | English |
| last_indexed | 2024-04-13T05:58:43Z |
| publishDate | 2008-04-01 |
| publisher | BMC |
| record_format | Article |
| series | BioMedical Engineering OnLine |
| spelling | doaj.art-8c07af3289d54058a85dac029e5f1b032022-12-22T02:59:32ZengBMCBioMedical Engineering OnLine1475-925X2008-04-01711410.1186/1475-925X-7-14Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in miceCrane Eli RMedonza Dharshan CDonohue Kevin DO'Hara Bruce F<p>Abstract</p> <p>This work presents a non-invasive high-throughput system for automatically detecting characteristic behaviours in mice over extended periods of time, useful for phenotyping experiments. The system classifies time intervals on the order of 2 to 4 seconds as corresponding to motions consistent with either active wake or inactivity associated with sleep. A single Polyvinylidine Difluoride (PVDF) sensor on the cage floor generates signals from motion resulting in pressure. This paper develops a linear classifier based on robust features extracted from normalized power spectra and autocorrelation functions, as well as novel features from the collapsed average (autocorrelation of complex spectrum), which characterize transient and periodic properties of the signal envelope. Performance is analyzed through an experiment comparing results from direct human observation and classification of the different behaviours with an automatic classifier used in conjunction with this system. Experimental results from over 28.5 hours of data from 4 mice indicate a 94% classification rate relative to the human observations. Examples of sequential classifications (2 second increments) over transition regions between sleep and wake behaviour are also presented to demonstrate robust performance to signal variation and explain performance limitations.</p>http://www.biomedical-engineering-online.com/content/7/1/14 |
| spellingShingle | Crane Eli R Medonza Dharshan C Donohue Kevin D O'Hara Bruce F Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice BioMedical Engineering OnLine |
| title | Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice |
| title_full | Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice |
| title_fullStr | Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice |
| title_full_unstemmed | Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice |
| title_short | Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice |
| title_sort | assessment of a non invasive high throughput classifier for behaviours associated with sleep and wake in mice |
| url | http://www.biomedical-engineering-online.com/content/7/1/14 |
| work_keys_str_mv | AT craneelir assessmentofanoninvasivehighthroughputclassifierforbehavioursassociatedwithsleepandwakeinmice AT medonzadharshanc assessmentofanoninvasivehighthroughputclassifierforbehavioursassociatedwithsleepandwakeinmice AT donohuekevind assessmentofanoninvasivehighthroughputclassifierforbehavioursassociatedwithsleepandwakeinmice AT oharabrucef assessmentofanoninvasivehighthroughputclassifierforbehavioursassociatedwithsleepandwakeinmice |