ABSTRACT
Gait analysis is important for guide dog organizations, as ideal guide dogs have a smooth and efficient gait, where they can also easily shift between and maintain various gaits. Gait quality and natural traveling speed are two of the multiple factors important in matching a guide dog to its visually impaired handler. Gait evaluation typically includes subjective visual observation of the dog or objective assessments obtained from special-designed equipment. Guide dog organizations need a method to easily collect and analyze objective data of gait information. In this work, we explored how various machine learning models could learn and analyze gait patterns from inertial measurements data that were collected during two different data collection experiments using a wearable sensor device. We also evaluated how well each machine learning model could generalize behavior patterns from various dogs under different environments. Additionally, we compared how sensor placement locations could affect gait prediction performance by attaching the sensor device to the dog’s neck and back area respectively. The tested machine learning models were able to classify different gaits in the range of 42% to 91% in terms of accuracy, and predict various gait parameters with an error rate ranging from 14% to 29% depending on the setup. Furthermore, we also observed that using behavior data collected from the neck region contains more movement information than the back area. By performing a cross-dataset generalization test on the machine learning models, we found that even with performance drop, the models were able to learn gait-specific behavior patterns that are generalizable for different dogs. Although the results were preliminary, the proposed gait analysis exploration still showed promising potential for studying behavior patterns of candidate guide dogs.
- Satyabrata Aich, Sabyasachi Chakraborty, Jong-Seong Sim, Dong-Jin Jang, and Hee-Cheol Kim. 2019. The Design of an Automated System for the Analysis of the Activity and Emotional Patterns of Dogs with Wearable Sensors Using Machine Learning. Applied Sciences 9, 22 (2019), 4938. https://doi.org/10.3390/app9224938Google ScholarCross Ref
- Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. arxiv:1607.06450 [stat.ML]Google Scholar
- Rita Brugarolas, Robert T. Loftin, Pu Yang, David L. Roberts, Barbara Sherman, and Alper Bozkurt. 2013. Behavior recognition based on machine learning algorithms for a wireless canine machine interface. In 2013 IEEE International Conference on Body Sensor Networks. 1–5. https://doi.org/10.1109/BSN.2013.6575505Google ScholarCross Ref
- Rita Brugarolas, David Roberts, Barbara Sherman, and Alper Bozkurt. 2012. Posture estimation for a canine machine interface based training system. In 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 4489–4492. https://doi.org/10.1109/EMBC.2012.6346964Google ScholarCross Ref
- Rita Brugarolas, David Roberts, Barbara Sherman, and Alper Bozkurt. 2013. Machine learning based posture estimation for a wireless canine machine interface. In 2013 IEEE Topical Conference on Biomedical Wireless Technologies, Networks, and Sensing Systems. 10–12. https://doi.org/10.1109/BioWireleSS.2013.6613658Google ScholarCross Ref
- Frances L. Chen, Madeline Zimmermann, Jessica P. Hekman, Kathryn A. Lord, Brittney Logan, Jane Russenberger, Eldin A. Leighton, and Elinor K. Karlsson. 2021. Advancing Genetic Selection and Behavioral Genomics of Working Dogs Through Collaborative Science. Frontiers in Veterinary Science 8 (2021). https://doi.org/10.3389/fvets.2021.662429Google ScholarCross Ref
- Zach Cleghern, Evan Williams, Sean Mealin, Marc Foster, Timothy Holder, Alper Bozkurt, and David L. Roberts. 2020. An IoT and Analytics Platform for Characterizing Adolescent Dogs’ Suitability for Guide Work. In Proceedings of the Sixth International Conference on Animal-Computer Interaction (Haifa, Israel) (ACI ’19). Association for Computing Machinery, New York, NY, USA, Article 1, 6 pages. https://doi.org/10.1145/3371049.3371056Google ScholarDigital Library
- Zach Cleghern, Evan Williams, Sean Mealin, Marc Foster, Timothy Holder, Alper Bozkurt, and David L. Roberts. 2021. Behavioral and Environmental Analytics from Potential Guide Dogs with IoT Sensor Data Informed by Expert Insight. In Proceedings of the Seventh International Conference on Animal-Computer Interaction (Milton Keynes, United Kingdom) (ACI ’20). Association for Computing Machinery, New York, NY, USA, Article 1, 12 pages. https://doi.org/10.1145/3446002.3446121Google ScholarDigital Library
- Stephen Cunnane. 2017. Stephen Cunnane art and animation. Retrieved Aug. 5, 2023 from https://www.stephencunnane.com/3d-workGoogle Scholar
- Fi. 2017. THE SMARTEST TECH EVER BUILT FOR YOUR DOG. Retrieved Aug. 12, 2023 from https://tryfi.com/Google Scholar
- FitBark. 2013. FitBark GPS 2nd Generation. Retrieved Aug. 12, 2023 from https://www.fitbark.com/Google Scholar
- Linda Gerencsér, Gábor Vásárhelyi, Máté Nagy, Tamas Vicsek, and Adam Miklósi. 2013. Identification of Behaviour in Freely Moving Dogs (Canis familiaris) Using Inertial Sensors. PLOS ONE 8, 10 (10 2013), null. https://doi.org/10.1371/journal.pone.0077814Google ScholarCross Ref
- Gregory J Jenkins, Chady H Hakim, N Nora Yang, Gang Yao, and Dongsheng Duan. 2018. Automatic characterization of stride parameters in canines with a single wearable inertial sensor. PLoS One 13, 6 (June 2018), e0198893.Google ScholarCross Ref
- Sean Mealin, Marc Foster, Zach Cleghern, Alper Bozkurt, and David L. Roberts. 2021. Using Inertial Measurement Unit Data for Objective Evaluations of Potential Guide Dogs. In Proceedings of the Seventh International Conference on Animal-Computer Interaction (Milton Keynes, United Kingdom) (ACI ’20). Association for Computing Machinery, New York, NY, USA, Article 2, 11 pages. https://doi.org/10.1145/3446002.3446064Google ScholarDigital Library
- Fanny Menuge, Míriam Marcet-Rius, Muriel Jochem, Orane François, Camille Assali, Camille Chabaud, Eva Teruel, Justine Guillemot, and Patrick Pageat. 2021. Early evaluation of fearfulness in future guide dogs for blind people. Animals (Basel) 11, 2 (Feb. 2021), 412.Google Scholar
- Alejandra Mondino, Michael Khan, Beth Case, Sara Giovagnoli, Andrea Thomson, B Duncan X Lascelles, Margaret Gruen, and Natasha Olby. 2023. Activity patterns are associated with fractional lifespan, memory, and gait speed in aged dogs. Sci. Rep. 13, 1 (Feb. 2023), 2588.Google Scholar
- PetPace. 2012. Welcome to the Future of Pet Healthcare. Retrieved Aug. 12, 2023 from https://petpace.com/Google Scholar
- scikit learn. 2013. Supervised learning. Retrieved Jun. 5, 2023 from https://scikit-learn.org/stable/supervised_learning.htmlGoogle Scholar
- IBM Watson Studio. 2010. IBM Watson Studio. Retrieved Jun. 6, 2023 from https://www.ibm.com/cloud/watson-studioGoogle Scholar
- Tekscan. 2018. Tekscan Strideway Gait Anlysis System Data Sheet for Animals. Retrieved Aug. 10, 2022 from https://camatsystem.com/wp-content/uploads/2018/03/MDL_Strideway-Data-Sheet-ANIMAL.pdfGoogle Scholar
- Tekscan. 2018. Tekscan Strideway System. Retrieved Jul. 28, 2022 from https://www.tekscan.com/products-solutions/systems/strideway-systemGoogle Scholar
- Giancarlo Valentin, Joelle Alcaidinho, Ayanna Howard, Melody M. Jackson, and Thad Starner. 2015. Towards a Canine-Human Communication System Based on Head Gestures. In Proceedings of the 12th International Conference on Advances in Computer Entertainment Technology (Iskandar, Malaysia) (ACE ’15). Association for Computing Machinery, New York, NY, USA, Article 65, 9 pages. https://doi.org/10.1145/2832932.2837016Google ScholarDigital Library
- Giancarlo Valentin, Joelle Alcaidinho, Ayanna Howard, Melody M. Jackson, and Thad Starner. 2016. Creating Collar-Sensed Motion Gestures for Dog-Human Communication in Service Applications. In Proceedings of the 2016 ACM International Symposium on Wearable Computers (Heidelberg, Germany) (ISWC ’16). Association for Computing Machinery, New York, NY, USA, 100–107. https://doi.org/10.1145/2971763.2971788Google ScholarDigital Library
- Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. arxiv:1706.03762 [cs.CL]Google Scholar
- Whistle. 2013. The new way to help pets stay healthy, happy, and safe. Retrieved Aug. 12, 2023 from https://www.whistle.com/Google Scholar
- Evan Williams, Zach Cleghern, Marc Foster, Timothy Holder, David Roberts, and Alper Bozkurt. 2020. A Smart Collar for Assessment of Activity Levels and Environmental Conditions for Guide Dogs *, Vol. 2020. 4628–4631. https://doi.org/10.1109/EMBC44109.2020.9175814Google ScholarCross Ref
- Yifan Wu, Timothy Holder, Marc Foster, Evan Williams, Masataka Enomoto, B. Duncan Lascelles, Alper Bozkurt, and David Roberts. 2023. Spatial and Temporal Analytic Pipeline for Evaluation of Potential Guide Dogs Using Location and Behavior Data. In Proceedings of the Ninth International Conference on Animal-Computer Interaction (Newcastle-upon-Tyne, United Kingdom) (ACI ’22). Association for Computing Machinery, New York, NY, USA, Article 19, 10 pages. https://doi.org/10.1145/3565995.3566033Google ScholarDigital Library
- Xiqiao Zhang, Gregory J Jenkins, Chady H Hakim, Dongsheng Duan, and Gang Yao. 2022. Four-limb wireless IMU sensor system for automatic gait detection in canines. Sci. Rep. 12, 1 (March 2022), 4788.Google Scholar
Index Terms
- An Exploration of Machine Learning Methods for Gait Analysis of Potential Guide Dogs
Recommendations
Behavior Analysis for Potential Guide Dogs
ACI '23: Proceedings of the Tenth International Conference on Animal-Computer InteractionBehavior analysis serves an important role in guide dog training, where guide dog experts evaluate each potential guide dog and make decisions based on their behaviors under various environments. However, a lack of objective measures to comprehensively ...
Spatial and Temporal Analytic Pipeline for Evaluation of Potential Guide Dogs Using Location and Behavior Data
ACI '22: Proceedings of the Ninth International Conference on Animal-Computer InteractionTraining guide dogs for visually-impaired people is a resource-consuming task for guide dog schools. This task is further complicated by a dearth of capabilities to objectively measure and analyze candidate guide dogs’ temperaments as they are placed ...
Validation of a motion capture suit for clinical gait analysis
PervasiveHealth '17: Proceedings of the 11th EAI International Conference on Pervasive Computing Technologies for HealthcareGait analysis is often supported by technology. Due to limitations in optical systems, such as limited measurement volumes and the requirement of a laboratory environment, low-cost inertial measurement unit (IMU) based motion capture systems might be ...
Comments