Sistem Prakiraan Cuaca Berbasis Android dengan Metode Jaringan Syaraf Tiruan Backpropagation
In one sentence. An Arduino and Android weather station uses a backpropagation neural network on temperature and humidity, reaching a 78.6% forecast success rate on 14 trials.
Abstract
This research aims to develop a weather forecasting system using an Android-based mobile device combined with a microcontroller platform. The device built consists of a DHT11 sensor, Arduino UNO microcontroller, HC-05 Bluetooth module, and an Android phone that is used by users to view weather information. The Neural Network Backpropagation method is useful as a learning algorithm in obtaining appropriate weights so that the system is able to make weather forecasts correctly. Temperature and humidity data from the Padang City BMKG are used as input data to the Matlab application to be trained to find accurate patterns and weights. This appropriate weight is useful as a weighing factor in the Backpropagation testing process on Arduino Uno. In the process, the system works to measure temperature and humidity with the DHT11 sensor, then Arduino processes the input from the sensor to then send the results to the Android application. The test results with 14 trial data revealed that the system with the Neural Network Backpropagation learning method had a success rate of 78.6% for measuring and forecasting the weather.
Labels
- Topic
- Local & station forecasting, Software, scaling & compression
- Type
- Application study
- Method
- Classical ML (trees, GP, linear, kernels)
- Time scale
- 0–6 h
- Domain
- Local / station
- Data
- Station / in-situ
- Status
- Pre-operational / experimental
- Identifiers
- DOI:10.37595/mediainfo.v22i2.180 OpenAlex:W4386468014
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.