The development of transgenic and knock-out mouse models of human disorders, particularly psychiatric disorders has led to the need for sensitive automated methods for detecting behavioral abnormalities in mice. We propose to develop novel mathematical and computer algorithms that will be able to automatically track mouse and identify mouse normal behaviors such as locamotor movements and in home cage and even recognize deviations from their normal behaviors, including complex animal behaviors such as forelimb reaching (in Phase II). The purpose is to use these sophisticated digital video analysis algorithms to allow computer interpretation of behavior. Once the complete home-cage behavioral repertoire is codified, it will be possible to produce a normal profile of behavior across the daily cycle for commonly used inbred strains of mice of different ages and genders. This will enable investigators to detect deviations from the normative pattern of behaviors, either in the types, amount, or daily rhythms of individual behaviors. Having identified deviations, video clips of the deviant behaviors could be presented by the system to the investigator for interpretation of the meaning of the deviation. Digital video algorithms will also allow non linear access to desired animal behavior scenes effectively and efficiently.
This proposed research will not only create enormous benefits for the neuroscience and behavior research community including medical research institutes, universities, pharmaceutical companies, and hospitals and clinics who are conducting behavior study and analysis, but also find applications in the entire area of biology which will be interested in this system to help them conduct research in such areas as genetic research, cancel research, HIV research, etc. I can be applied to human-computer interface and surveillance and monitoring areas.
