Rancang Bangun Alat Monitoring Tanaman Hidroponik Pakcoy Memanfaatkan Mikrokontroler Dan Teknik Computer Vision

Abstract

Technology in agriculture is growing, one of them is hydroponic techniques because it uses anInternet of Things (IoT) based system. One of the plants used in hydroponic techniques is thepakcoy vegetable plant. Pakcoy is one of the vegetables that has the widest distribution in Asia.In addition, the characteristics of pakcoy vegetables are almost the same as mustard greens.Pakcoy vegetables are also easy to cultivate because they only require a small amount of landand a short harvest period. This system is built using a microcontroller and computer visiontechniques as a control center and uses a Raspberry Pi 4 type B mini PC as a visual notificationand is equipped with a dc motor gearbox, L298N motor driver and webcam camera. Thissystem works automatically to control which plants are healthy and which plants are sick. Thisstudy aims to detect diseased plants and healthy plants on pakcoy plants with a hydroponicpakcoy plant monitoring tool that uses a microcontroller and computer vision techniques. Thistool works by taking pictures directly through a webcam camera, then processing them with atrained model. The output of this tool displays the probability value of pakcoy plants showinghealthy plants and sick plants. From the results of testing the validation data using 60 validationdata, based on the accuracy of the detection tool healthy and sick plants were able to correctlyidentify 38 validation data and 22 data were not recognized properly, so the accuracy of thevalue was 63%. and produces an f1-score of 0,87