Rancang Bangun Sistem Monitoring Suhu, Kelembapan, pH, dan Kadar NPK Tanah Menggunakan Metode Decision Tree Terintegrasi Long Range (LoRa)

Utama, Ghofri Cendikia (2024) Rancang Bangun Sistem Monitoring Suhu, Kelembapan, pH, dan Kadar NPK Tanah Menggunakan Metode Decision Tree Terintegrasi Long Range (LoRa). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5009201064-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (2MB) | Request a copy

Abstract

Smart farming dapat membuat produktivitas petani meningkat dengan adanya monitoring kondisi tanah pertanian sehingga petani dapat mengambil keputusan secara tepat. Parameter kualitas tanah yang berpengaruh dalam pertumbuhan tanaman di antaranya yaitu kelembapan, pH, unsur hara, dan suhu tanah. Dalam penelitian ini dibangun sistem yang mampu memantau kondisi tanah dan mengklasifikasi kondisi tanah yang ideal untuk sawi dengan menggunakan decision tree. Sistem juga ditambahkan LoRa sehingga sistem dapat dipantau secara jarak jauh. Sensor, LoRa, dan decision tree yang digunakan dalam sistem telah diuji. Hasil Karakterisasi sensor suhu untuk nilai ketidakpastian diperluas, akurasi, presisi, dan linieritas secara berturut-turut yaitu ±1,168 ºC, 98,61%, 99,88%, dan 0,99. Hasil Karakterisasi sensor pH untuk nilai ketidakpastian diperluas, akurasi, presisi, dan linieritas secara berturut turut yaitu ±1,348, 95,11%, 98,65%, dan 0,95. Hasil Karakterisasi sensor kelembapan untuk nilai ketidakpastian diperluas, akurasi, presisi, dan linieritas secara berturut-turut yaitu ±2,893%, 98,76%, 99,32%, dan 0,99. Nilai perfomansi pengiriman data saat tidak ada penghalang untuk parameter received signal strength indicator (RSSI), packet delivery rate (PDR), dan signal to noise ratio (SNR) secara berturut-turut yaitu -84,59 dBm, 96,42%, dan 4,03 dB. Nilai perfomansi pengiriman data saat terdapat penghalang. untuk parameter RSSI, PDR, dan SNR secara berturut-turut yaitu -100,57 dBm, 100%, dan 1,76 dB. Model decision tree dengan gini criterion dan model decision tree dengan entropy criterion memiliki nilai akurasi yang sama sebesar 99%.
======================================================================================================================================
Smart farming can increase farmer productivity by monitoring agricultural soil conditions so that farmers can make the right decisions. Soil quality parameters that affect plant growth include humidity, pH, nutrients, and soil temperature. In this study, a system was built that is able to monitor soil conditions and classify ideal soil conditions for mustard greens using a decision tree. The system is also added with LoRa so that the system can be monitored remotely. The sensors, LoRa, and decision trees used in the system have been tested. The results of the temperature sensor characterization for the expanded uncertainty value, accuracy, precision, and linearity are respectively ±1.168 ºC, 98.61%, 99.88%, and 0.99. The results of the pH sensor characterization for the expanded uncertainty value, accuracy, precision, and linearity are respectively ±1.348, 95.11%, 98.65%, and 0.95. The results of the humidity sensor characterization for the expanded uncertainty value, accuracy, precision, and linearity are respectively ±2.893%, 98.76%, 99.32%, and 0.99. The data transmission performance value when there are no obstacles for the parameters received signal strength indicator (RSSI), packet delivery rate (PDR), and signal to noise ratio (SNR) are respectively -84.59 dBm, 96.42%, and 4.03 dB. The data transmission performance value when there are obstacles for the parameters RSSI, PDR, and SNR are respectively -100.57 dBm, 100%, and 1.76 dB. The decision tree model with the Gini criterion and the decision tree model with the entropy criterion have the same accuracy value of 99%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Decision Tree, LoRa, Smart Farming, Soil Monitoring.
Subjects:	S Agriculture > S Agriculture (General) T Technology > T Technology (General) > T58.62 Decision support systems T Technology > TS Manufactures > TS171 Product design
Divisions:	Faculty of Industrial Technology and Systems Engineering (INDSYS) > Physics Engineering > 30201-(S1) Undergraduate Thesis
Depositing User:	Ghofri Cendikia Utama
Date Deposited:	01 Aug 2024 06:28
Last Modified:	17 Sep 2024 08:50
URI:	http://repository.its.ac.id/id/eprint/109752

Actions (login required)

View Item