Skripsi

PENERAPAN METODE RANDOM FOREST DALAM SISTEM PERINGATAN BANJIR BERBASIS INTERNET OF THINGS

---

Flooding is one of the most common natural disasters and can cause significant losses. This study aims to design and develop an Internet of Things (IoT)-based flood warning system using the Random Forest algorithm. The system utilizes BMP280 sensors to measure water level and an optocoupler sensor to measure water flow velocity. Sensor data are processed by an ESP32 microcontroller and sent to a Flask-based local server to determine flood conditions. The results are then displayed in real time through the Blynk dashboard. The Random Forest model was trained using 393 datasets, with water level and water flow velocity as input variables. The testing results showed that the model achieved an accuracy of 98.73%, while the water level sensor testing produced an average error of 3.9% compared to manual measurements. The results indicate that the developed system is capable of providing real-time flood warnings with high accuracy by classifying conditions into Safe, Alert, and Flood categories.

---

Availability

Detail Information

Series Title

-

Call Number

T2012592026

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xvi, 97 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

621.382 07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Prodi Sistem Komputer
Teknologi Telekomunikasi/Jaringan

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment