The implementation of artificial intelligence on very tiny chips plays an important role in the future of IoT.
Typically, these chips do not conduct artificial intelligence operations locally. They mostly send collected data to a cloud service, where artificial intelligence is implemented for decision-making. This leads to a time lag and significant dependency of the system on an internet connection, making it unsuitable for systems requiring immediate action. In a hydroponic system, there is an immediate need to control the speed of a pump to maintain pH level. However, there are many challenges in designing an intelligent system using low-powered chips with low computational power. Therefore, achieving high AI accuracy is very difficult for these devices. Additionally, tiny devices need to communicate with the user to execute IoT operations. To overcome these challenges, a hydroponic system was designed in this study to incorporate an ESP32 chip-based microcontroller with sensors and actuators attached to it, so that AI on edge and IoT tasks can be executed simultaneously. A dedicated Android app was implemented to monitor and control the system remotely via IoT. Results show that the predicted pump speed just falls behind the expected speed by an average of 2.94%. The overall design system was stable and reliable. Komatsuna plants were grown in a hydroponic system and the yield was compared with the plants grown in standard potting compost.
The hydroponic system was monitored by the proposed method to produce a higher yield compared to the potting compost.
Sharma, Arpit & Taherkhani, Anahita & Orba, Ezekiel & Taherkhani, Aboozar. (2025). A Machine Learning Method on a Tiny Hardware for Monitoring and Controlling a Hydroponic System. AI, Computer Science and Robotics Technology. 4. 10.5772/acrt.20240016.
Source: Research Gate