Claim Missing Document
Check
Articles

Found 2 Documents
Search

Otomatisasi Pengoperasian Alat Elektronik Berdasarkan Hasil Prediksi Algoritma Long Short Term Memory Afriansyah Afriansyah; Ade Irawan
JITCE (Journal of Information Technology and Computer Engineering) Vol 4 No 02 (2020): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jitce.4.02.83-89.2020

Abstract

Excessive use of household electricity is one of the causes of the largest amount of national electricity consumption coming from households. One way to reduce the amount of household electricity consumption is to automate the operation of electronic devices. This research proposes utilizing Long Short Term Memory (LSTM) algorithm to predict the habit of operating an electronic device. The prediction is then applied to automate the operation of that by exploiting the time series data from the usage. A series of experiments are conducted to capture the data of operating a manual lamp. Then, an LSTM model is built by training the data. The experiment results show the prediction accuracy of 99,28% and Root Mean Square Error of 0,091. Furthermore, the LSTM model is used to automatically operate a lamp in a month. The electricity cost from the automation is 36,38% lower than the manual.
Rancang Bangun Aplikasi Mobile Pemeriksaan Kendaraan Operasional Afriansyah Afriansyah; Meredita Susanty
IJCIT (Indonesian Journal on Computer and Information Technology) Vol 7, No 1 (2022): IJCIT Mei 2022
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (552.576 KB) | DOI: 10.31294/ijcit.v7i1.11833

Abstract

Pemeriksaan harian kendaraan adalah cara sederhana dan efektif untuk menemukan masalah atau cacat yang berpotensi berbahaya sebelum kendaraan digunakan. Tindakan ini diharapkan menjadi tindakan pencegahan terhadap resiko terjadinya kecelakaan kerja. Pencatatan umumnya dilakukan pada formulir fisik kemudian dipindahkan ke sistem informasi Kesehatan dan keselamatan kerja untuk kemudian dilaporkan. Untuk meningkatkan efisiensi pencatatan data pemeriksaan kendaraan, diusulkan penggunaan aplikasi mobile yang dapat digunakan oleh pengemudi di lapangan untuk mencatat penilaian kondisi keadaan kendaraan harian yang terhubung dengan sistem informasi keamanan dan keselamatan yang sudah ada saat ini. Pengembangan aplikasi dilakukan menggunakan pendekatan waterfall. Aplikasi yang dikembangkan menggunakan React Native, Node.js dan REST API ini dapat digunakan para perangkat Android. Keberadaan aplikasi sederhana ini diharapkan mengurangi pekerjaan rutin pengguna dan membuat data pemeriksaan kondisi kendaraan dapat diakses secara near real time oleh tim kesehatan dan keselamatan kerja. Daily vehicle inspections are a simple and effective way to spot potentially dangerous issues or defects before the vehicle are used. This routine is a preventive measure against the risk of work accidents. The Health and Safety Authority requires drivers to fill checklist form before performing their job then input the data from that physical form to Health and Safety information system web after their shift.  A mobile application is proposed to help drivers record daily vehicle conditions so that they do not need to input the data at the end of their shift—the mobile application stores data to the Health and Safety information system directly. The application is developed using a waterfall approach using React Native, Node.js, and the REST API as a technology stack. The application is ready to be used on Android-based devices. This simple application reduces users' routine tasks and makes vehicle condition inspection data accessible in near real-time by the occupational health and safety team.