Data-Driven Intelligent Feeding System for Pet Care

The rapid development of artificial intelligence, the internet of things, and digital information processing technology has a huge impact on our daily lives with smart devices and wearables. The well-being of companion animals such as dogs and cats has become a large challenge. An increasing number of pet owners, their emotional attachment with their pets, and the 21st-century's lifestyle importantly need the safety and welfare of pets by harnessing a smart technological approach. This paper analyzes and compares different machine learning algorithms for data-driven intelligent feeding system for pet care application. Different parameters such as body weight growth, body temperature, heart rate, eating habits, activity, sleep, and urine pH have been considered with other correlated sub-variables in creating virtual datasets. The supervised machine learning models: linear regression, gaussian process regression, narrow neural network, linear support vector machine, and fine tree are evaluated and discussed for estimating feed quantity. The machine learning model was verified by training, validation, and testing datasets. The developed model will be an innovative breakthrough for pet care applications. Feed estimation can be automated using the pet's health parameters, this will help the pet to prevent obesity and related disorders.