L2M – Embedded TinyML solution for behavioral analysis, welfare monitoring, and localization of livestock using Internet of Things devices and Edge Computing
The North American livestock industry faces a combination of factors that decrease productivity, while demand for derived products continues to rise due to population growth. This necessitates the emergence of innovative, sustainable technologies to support processes, and collaborative efforts. Hence, a solution is proposed to enhance the livestock industry through an innovative IoT collar for cattle that integrates sensors and embedded machine learning algorithms to monitor animal behavior, health, and location in real time. By providing actionable insights, this will enable data-based decision-making and task management to sustainably and efficiently improve livestock quality of life and health, optimize resource use, and boost productivity. Through the L2M Validation program, the proposed solution will be validated in the market to understand the specific needs of users, promoting entrepreneurial skills and enabling research discoveries to move out of the laboratory and be commercialized, thereby accelerating and growing the translation of research excellence to impact the Canadian economy.
View Full Project DescriptionTsz Ho Kwok
Springboard Atlantic Inc.
Engineering
Artificial Intelligence; Technology; Agriculture and Food
Concordia University
Business Strategy Internship
