Limits...
Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice.

Donohue KD, Medonza DC, Crane ER, O'Hara BF - Biomed Eng Online (2008)

Bottom Line: A single Polyvinylidine Difluoride (PVDF) sensor on the cage floor generates signals from motion resulting in pressure.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.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.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY 40506, USA. donohue@engr.uky.edu

ABSTRACT
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.

Show MeSH
Examples of (a) PS for sleep signals of Fig. 1,(b) PS for wake signals of Fig. 2,(c) AC for sleep signals of Fig. 1,(d) AC for wake signals of Fig. 2,(e) CA for sleep signals of Fig. 1,(f) CA for wake signals of Fig. 2.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC2365952&req=5

Figure 4: Examples of (a) PS for sleep signals of Fig. 1,(b) PS for wake signals of Fig. 2,(c) AC for sleep signals of Fig. 1,(d) AC for wake signals of Fig. 2,(e) CA for sleep signals of Fig. 1,(f) CA for wake signals of Fig. 2.

Mentions: Examples of the PS for the sleep signals are shown in Fig. 4a and for wake signals in Fig. 4b. The most obvious differences for the 2 states are the higher peaks in the spectral region from 2 Hz to 4 Hz for the sleep signal. However, active and resting states also exhibit high peak values in or near this range, creating ambiguity and a need for additional features. Examples of the AC are shown in Fig. 4c for sleep and Fig. 4d for wake. Note the strong peak at a lag corresponding to the sleep period (in the neighbourhood of 0.3 and 0.4 seconds) in Fig. 4c that distinguishes it from the wake AC. The maximum peaks for wake also can occur in this region; however their magnitudes are typically smaller due to their lack of regularity over the analysis window.


Assessment of a non-invasive high-throughput classifier for behaviours associated with sleep and wake in mice.

Donohue KD, Medonza DC, Crane ER, O'Hara BF - Biomed Eng Online (2008)

Examples of (a) PS for sleep signals of Fig. 1,(b) PS for wake signals of Fig. 2,(c) AC for sleep signals of Fig. 1,(d) AC for wake signals of Fig. 2,(e) CA for sleep signals of Fig. 1,(f) CA for wake signals of Fig. 2.
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC2365952&req=5

Figure 4: Examples of (a) PS for sleep signals of Fig. 1,(b) PS for wake signals of Fig. 2,(c) AC for sleep signals of Fig. 1,(d) AC for wake signals of Fig. 2,(e) CA for sleep signals of Fig. 1,(f) CA for wake signals of Fig. 2.
Mentions: Examples of the PS for the sleep signals are shown in Fig. 4a and for wake signals in Fig. 4b. The most obvious differences for the 2 states are the higher peaks in the spectral region from 2 Hz to 4 Hz for the sleep signal. However, active and resting states also exhibit high peak values in or near this range, creating ambiguity and a need for additional features. Examples of the AC are shown in Fig. 4c for sleep and Fig. 4d for wake. Note the strong peak at a lag corresponding to the sleep period (in the neighbourhood of 0.3 and 0.4 seconds) in Fig. 4c that distinguishes it from the wake AC. The maximum peaks for wake also can occur in this region; however their magnitudes are typically smaller due to their lack of regularity over the analysis window.

Bottom Line: A single Polyvinylidine Difluoride (PVDF) sensor on the cage floor generates signals from motion resulting in pressure.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.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.

View Article: PubMed Central - HTML - PubMed

Affiliation: Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY 40506, USA. donohue@engr.uky.edu

ABSTRACT
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.

Show MeSH