Computational Analysis of Movement Patterns of Dogs with ADHD-Like Behavior
Information Systems Department, University of Haifa, Haifa 3498838, Israel
Department of Automation and Control Processes, Saint Petersburg Electrotechnical University “LETI”, Saint Petersburg 197376, Russia
Clinique de la Tivolliere, 38340 Voreppe, France
Department of Computer Science, University of Bristol, Bristol BS8 1TH, UK
Author to whom correspondence should be addressed.
Received: 18 October 2019 / Revised: 10 December 2019 / Accepted: 11 December 2019 / Published: 13 December 2019
ADHD-like (attention deficit hyperactivity disorder) behavior in dogs may be expressed as impulsivity, inattentiveness, or aggression, compromising both dog and owner quality of life. Its treatment in a clinical setting requires behavioral modification and sometimes a medical treatment is added. There is a lack of objective tools for assessment and diagnosis of the problem, and behavioral experts mostly rely on owner reports. To address this gap, in this paper we use a self-developed computational tool which automatically analyzes movement of a dog from video footage collected during behavioral consultation. Based on a computational analysis of behavioral consultations of 12 dogs medically treated due to ADHD-like behavior and of a control group of 12 dogs with no reported behavioral problems, we identify three dimensions of characteristic movement patterns of dogs with ADHD-like behaviors, which are detectable during consultation. These include (i) high speed of movement, (ii) large coverage of room space, and (iii) frequent re-orientation in room space. These patterns can form the basis for computational methods for objective assessment of dogs with ADHD-like behavior that could help for diagnosis and clinical treatment of the disorder.