Predicting the Suitability of Service Animals Using Instrumented Dog Toys

Abstract

Working dogs1 are significantly beneficial to society; however, a substantial number of dogs are released from time consuming and expensive training programs because of unsuitability in behavior. Early prediction of successful service dog placement could save time, resources, and funding. Our research focus is to explore whether aspects of canine temperament can be detected from interactions with sensors, and to develop classifiers that correlate sensor data to predict the success (or failure) of assistance dogs in advanced training. In a 2-year longitudinal study, our team tested a cohort of dogs entering advanced training in the Canine Companions for Independence (CCI) Program with 2 instrumented dog toys: a silicone ball and a silicone tug sensor. We then create a logistic model tree classifier to predict service dog success using only 5 features derived from dog-toy interactions. During randomized 10-fold cross validation where 4 of the 40 dogs were kept in an independent test set for each fold, our classifier predicts the dogs' outcomes with 87.5% average accuracy. We assess the reliability of our model by performing the testing routine 10 times over 1.5 years for a single suitable working dog, which predicts that the dog would pass each time. We calculate the resource benefit of identifying dogs who will fail early in their training, and the value for a cohort of 40 dogs using our toys and our methods for prediction is over $70,000. With CCI's 6 training centers, annual savings could be upwards of $5 million per year.

Homozygosity for Mobile Element Insertions Associated with WBSCR17 Could Predict Success in Assistance Dog Training Programs

“…Lormier and colleagues [42] found that canine fear and aggression are behaviors responsible for dismissal from assistance training programs. Currently, the costs of raising and training an assistance dog are as high as US$50,000 [18]. Genetic screening of dogs for insertions at WBSCR17 may assist in identifying social predispositions of dogs early in development, which could increase successful training and placement of assistance dogs.…”

“…Assistance dog training programs explicitly survey behaviors that are imperative to their program’s success, and include robustness to environmental stressors, social behaviors, trainability, attention, and problem-solving [6]. However, these programs often document up to 60% failure rates [18], with behavioral problems reported as one of the primary causes for dismissal. For instance, 60% of dogs that are withdrawn from the Guide Dogs for the Blind program for behavioral reasons that include high activity level, incompatibility with cats or other dogs, and assertiveness toward leadership [19].…”

An IoT and Analytics Platform for Characterizing Adolescent Dogs' Suitability for Guide Work

“…Another method of predicting service dog suitability is to use objective data provided by sensors. Byrne et al [7] used instrumented dog toys with sensors to develop a logistic model tree to classify outcomes in a service dog organization (Canine Companions for Independence) and were able to achieve accuracy of 87.5%. They calculated that this could save $70,000 by identifying dogs that will likely fail the program.…”

Seven Years after the Manifesto: Literature Review and Research Directions for Technologies in Animal Computer Interaction

“…Byrne et al [54] have recently proposed a technological approach to predict the suitability of dogs for assistive dog training programs. The authors have explored whether aspects of canine temperament can be detected from dogs' interactions with sensors embedded in two instrumented dog toys: a silicone ball and a silicone tug sensor.…”