Toward a smart system for pets

Abstract

When pet owners take care of their pets, it sparks the need to improve the well-being and happiness of their pets. This requires the ability to control an array of smart toys for pets and monitor the animals’ activities. By doing that, the owner has the possibilities to recognize unexpected behavior and to positively influence the behavior of the pets. Such smart toys’ systems are also useful for pet training purposes, which could be extended to more intelligent systems used to encourage specific behavior of pets. Currently, there are several existing products for monitoring purposes. However, they are lacking integrating features such as capabilities to be incorporated within current smart home systems and lacking the ability to add new devices to the product. This study aims to propose multi-use systems that can track and record data of pets (e.g. movements, body temperature) and which can be integrated into other smart systems. The thesis has implemented a demonstration system that includes a collar affixed to the pet, interacting with a mobile application, a cloud data storage and an analytic function. The achieved results of the presented study show that it is feasible to design and implement the targeted system’s architecture. It also demonstrates the abilities of using machine learning algorithms to detect pet behaviors.

Date	5 Mar 2021
Original language	American English
Awarding Institution	École de technologie supérieure
Supervisor	Lucas Hof (Supervisor) & Rolf Wuthrich (Co-supervisor)