Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)

Prototype Alat Pengendali Lampu dengan Perintah Suara menggunakan Arduino Uno Berbasis Web Nurul Isna Ganggalia; Apri Junaidi; Fahrudin Mukti Wibowo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 3 No 3 (2019): Desember 2019
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (408.435 KB) | DOI: 10.29207/resti.v3i3.1124

Abstract

The use of electric power for lights often less considered, a lot of lights are on continuously even though it's not used. As a result, a lot of electricity is wasted. This motivated researchers to create innovations of creating a light control system. The light controller system is designed to simplify and benefit the user. For this reason, researchers make light controllers on the web use voice commands that can be done anywhere and anytime using the internet. Making a prototype of a light control system with voice commands utilizes speech to text on the Web Speech API that converts sound into text, then it will be processed into a command of light controllers by the Arduino Uno microcontroller. The researcher used the prototype development method, where through 3 stages starting from Listen to Customer, Design and Building, and Test Drive Evaluations. The testing results are Internet speed and noise level affect the success rate on the use of light control using sound. At 9.9 Mbps internet speed has a success rate of 86% with response time 2.01 second, while at internet speed 1.9 Mbps has a success rate of 65% with response time 2.50 second. At the noise level of 34.5 dB room has a success rate of 86% with response time 2.02 second, while the noise level of 62 dB has a success rate of 72% with response time 2.21 second.
Optimasi Akurasi Metode Convolutional Neural Network untuk Identifikasi Jenis Sampah Rima Dias Ramadhani; Afandi Nur Aziz Thohari; Condro Kartiko; Apri Junaidi; Tri Ginanjar Laksana; Novanda Alim Setya Nugraha
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 5 No 2 (2021): April 2021
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (417.185 KB) | DOI: 10.29207/resti.v5i2.2754

Abstract

Waste is goods / materials that have no value in the scope of production, where in some cases the waste is disposed of carelessly and can damage the environment. The Indonesian government in 2019 recorded waste reaching 66-67 million tons, which is higher than the previous year, which was 64 million tons. Waste is differentiated based on its type, namely organic and anorganic waste. In the field of computer science, the process of sensing the type waste can be done using a camera and the Convolutional Neural Networks (CNN) method, which is a type of neural network that works by receiving input in the form of images. The input will be trained using CNN architecture so that it will produce output that can recognize the object being inputted. This study optimizes the use of the CNN method to obtain accurate results in identifying types of waste. Optimization is done by adding several hyperparameters to the CNN architecture. By adding hyperparameters, the accuracy value is 91.2%. Meanwhile, if the hyperparameter is not used, the accuracy value is only 67.6%. There are three hyperparameters used to increase the accuracy value of the model. They are dropout, padding, and stride. 20% increase in dropout to increase training overfit. Whereas padding and stride are used to speed up the model training process.