Can cognitive insights help pair more guide dogs with people who need them the most?
Jane Russenberger of Guiding Eyes for the Blind has been meticulously collecting all manner of guide-dog data sets for more than 30 years. Her long-held hope has been that the volumes of complex genetic mapping, medical records and journals and logs from thousands of puppy raisers, foster parents and trainers would one day serve to lift the success rate of guide-dog breeding.
As it stands, guide dog training is far from a perfect science.
Though the data that Jane has collected has successfully helped to inform breeding and training decisions, Guiding Eyes has really just scratched the surface of maximizing its value.
Currently, as few as 37% of puppies make it through the raising program to become successful service dogs for the blind. Given that it costs Guiding Eyes more than $40,000 to raise each dog, even a 5% increase in performance can yield the non-profit considerable savings.
The first step was to move all the data — which includes 30 years of structured genetic breeding data and thousands of unstructured questionnaire documents — to IBM Cloud.
Now, Professor Chris Tseng of San Jose State University and a group of his machine-learning students are using IBM Watson services on Bluemix to look for insight in all that data.
By combining the hard and soft data, the study will connect complex patterns, and yield useful insights that will help inform every stage of guide dog development.
Through their efforts, IBM and Guiding Eyes are looking for insights such as potential genetic patterns that can be linked to performance, or personality traits that can help identify how to successfully pair a trainer and puppy.
Are there genetic patterns that can be linked to performance?
Is it possible to look at personality traits in the questionnaires to identify what makes a successful pairing between trainer and puppy?
The study is still in its early stages and results will continue to roll out in the coming months.