Classifying postures of freely moving rodents with the help of fourier descriptors and a neural network

A computerized method for classifying the postures of freely moving rodents is presented. The behavior of the rats was recorded on videotape by means of a camera hanging perpendicular to an open field. An automatic tracking system (10 images/sec) was used to transform the video images of postures into a binary image, thereby providing silhouettes in a computer format. The contours of these silhouettes were used for determining their characteristic features with the help of a Fourier transformation. The resulting features were classified with the help of a Kohonen network composed of 32 neurons. The four bestwinning neurons, rather than the usual one, were used for the classification. The resolution (11,090 distinct classes of postures), reliability (96.9%), and validity of this method were determined. With the use of the same approach, the effectiveness of this method for classifying behaviors was illustrated by analyzing grooming (247 grooming images vs. 4,950 nongrooming images). We found 15.4% false positives and 2.5% false negatives.

[1]  F. Sams-Dodd,et al.  Automation of the social interaction test by a video-tracking system: behavioural effects of repeated phencyclidine treatment , 1995, Journal of Neuroscience Methods.

[2]  W. H. Gispen,et al.  Classification of rat behavior with an image-processing method and a neural network , 2000, Behavior research methods, instruments, & computers : a journal of the Psychonomic Society, Inc.

[3]  A. Cools,et al.  Search after neurobiological profile of individual-specific features of wistar rats , 1990, Brain Research Bulletin.

[4]  Charles R. Giardina,et al.  Elliptic Fourier features of a closed contour , 1982, Comput. Graph. Image Process..

[5]  Berrie M. Spruijt,et al.  Prolonged animal observation by use of digitized videodisplays , 1983, Pharmacology Biochemistry and Behavior.

[6]  Berry M. Spruijt,et al.  Approach, avoidance, and contact behavior of individually recognized animals automatically quantified with an imaging technique , 1992, Physiology and Behavior.

[7]  Joseph P. Huston,et al.  Video image analysis of behavior by microcomputer: categorization of turning and locomotion after 6-OHDA injection into the substantia nigra , 1987, Journal of Neuroscience Methods.

[8]  Phyllis J. Mullenix,et al.  Pattern recognition of rat behavior , 1987, Pharmacology Biochemistry and Behavior.

[9]  Robert J. Carey,et al.  A new method to quantify behavioral attention to a stimulus object in a modified open-field , 1994, Journal of Neuroscience Methods.

[10]  M. Gallagher,et al.  Severity of spatial learning impairment in aging: development of a learning index for performance in the Morris water maze. , 1993, Behavioral neuroscience.

[11]  A. R. Cools,et al.  Differences in vulnerability and susceptibility to dexamphetamine in Nijmegen high and low responders to novelty: a dose-effect analysis of spatio-temporal programming of behaviour , 1997, Psychopharmacology.