AgriNode ML
Project Overview
Year
About
Remote farms rely on battery powered sensors to track environmental conditions, but frequent measurements and wireless transmissions can quickly drain their batteries. AgriNode ML uses compact machine learning on each sensor to decide when new readings are needed, allowing it to sleep longer during stable conditions and combine data before transmission. In a field trial lasting 60 days on a Peruvian pitaya farm, the system reduced energy use by 77.8% while preserving accurate temperature data, potentially enabling longer lasting crop monitoring with less maintenance.
Team
Adrian Hinostroza
Electronics Engineer with over 6 years of experience in the end-to-end design, development, and implementation of hardware and software for embedded systems within the Internet of Things (IoT) ecosystem. Specialized in the development of high-precision GNSS receivers and Wireless Sensor Networks (WSN) applied to environmental monitoring. Expert in digital circuit design, strategic component selection, microcontroller programming across multiple platforms, 3D enclosure modeling, and the development of IoT-oriented web platforms. Track record focused on Research and Development (R&D), backed by peer-reviewed publications in international journals and conferences that demonstrate a commitment to technological innovation and scientific rigor.