Publication Search

This research aims to be able to meet the water supply of lettuce plants automatically by using three sensors such as soil moisture, water level, and water discharge. The goal is to provide water needs to plants automatically and regularly. The developed tool uses YL-96 sensor for soil moisture, HC-SR04 for water level and YF-S201 for water discharge. Sensor data is sent to the arduino to be processed using the fuzzy mamdani method so that these three data values affect the movement of the tap servo motor that flows to the lettuce plant. Fuzzy logic here as a decision maker from the value of 3 sensor data and then processed automatically by arduino using fuzzy mamdani to determine how many degrees the servo motor moves. The result is that the Lettuce Plant Water Needs Analysis System Automation Tool is able to maintain the water supply of lettuce plants and soil moisture ideally at 76% with a servo motor movement system success rate of 100%.

The performance of data mining techniques has been proven accurate in many studies, but each method in data mining techniques has different accuracy depending on the type of data that is the object of research. Methods in data mining techniques are divided into several functions, namely: clustering, association, classification, and prediction, where each data mining technique objective has a superior method. Therefore, in this case the author will compare the performance of the multiple linear regression method, and neural networks with fuzzy mamdani in predicting the income of PLN Unit Takengon. In several studies, the Backpropagation method shows the highest accuracy compared to other methods. Then the prediction model with multiple linear regression also has the highest accuracy as well as the Fuzzy Mamdani method has high accuracy too. Therefore, the purpose of this study is to compare the three methods, so that it can be determined which method has a higher accuracy value. The results of this study indicate that the Back propagation method has the highest accuracy and the lowest average error, namely a MAPE value of 5.9% with an accuracy of 94.1% and an RMSE of 14398.14, followed by the multiple linear regression method obtaining a MAPE value of 6.9% with an accuracy of 93.1% and an RMSE of 15527.41, then for Fuzzy Mamdani obtaining a MAPE value of 7% with an accuracy of 93% and an RMSE of 16077.76.