Claim Missing Document
Check
Articles

Found 15 Documents
Search

Fully Convolutional Variational Autoencoder For Feature Extraction Of Fire Detection System Herminarto Nugroho; Meredita Susanty; Ade Irawan; Muhamad Koyimatu; Ariana Yunita
Jurnal Ilmu Komputer dan Informasi Vol 13, No 1 (2020): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (579.884 KB) | DOI: 10.21609/jiki.v13i1.761

Abstract

This paper proposes a fully convolutional variational autoencoder (VAE) for features extraction from a large-scale dataset of fire images. The dataset will be used to train the deep learning algorithm to detect fire and smoke. The features extraction is used to tackle the curse of dimensionality, which is the common issue in training deep learning with huge datasets. Features extraction aims to reduce the dimension of the dataset significantly without losing too much essential information. Variational autoencoders (VAEs) are powerfull generative model, which can be used for dimension reduction. VAEs work better than any other methods available for this purpose because they can explore variations on the data in a specific direction.
ETNOGRAFI KOMUNIKASI PADA TRADISI SIRIH TANYA DALAM ADAT PERNIKAHAN MASYARAKAT MELAYU DI KECAMATAN ROKAN IV KOTO KABUPATEN ROKAN HULU Ade Irawan; Noor Efni Salam
Jurnal Online Mahasiswa (JOM) Bidang Ilmu Sosial dan Ilmu Politik Vol. 7: Edisi I Januari - Juni 2020
Publisher : Fakultas Ilmu Sosial dan Ilmu Politik Universitas Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Sirih tanya tradition in Malay customary marriage in Rokan IV Koto District, is carried on from generation to generation which contains values and norms in Malay people's lives. Sirih tanya tradition is a procession of proposing a woman to use betel pat, because Malay people believe that by delivering betel pat in proposing is a form of seriousness of a man. This reseach aims to determine the ethnography of communication on the sirih tanya traditions in malay customary marriage in the Rokan IV Koto sub-district, Rokan Hulu district. To achieve these goals then questions are raised how communicative siuation on the sirih tanya traditions in malay customary marriage, communicative events on the sirih tanya traditions in malay customary marriage and communicative actions  on the sirih tanya traditions in malay customary marriage.The author uses qualitative research methods, with ethnographic communication approaches. The research location was in Rokan IV Koto sub-district, Rokan Hulu regency. The time of research in October 2019 to January 2020. The research subjects consisted of 11 people, determined using purposive techniques. The object of ethnography of communication on the sirih tanya tradition in malay customary marriage. Data collection techniques through observation, interviews and literature study. Test the validity of the data with triangulation techniques and extension of participation.Research results explain that communicative situation on the sirih tanya tradition in malay customary marriage in the Rokan IV Koto sub-distrct, Rokan Hulu district that is moadatkan tepak sirih tanya situation, mouluokan tepak sirih tanya situation and monoangkan tepak sirih tanya situation. Then, communicative events on the sirih tanya tradition in malay customari marriage in the Rokan IV Koto sub-distrct, Rokan Hulu district covering : event type, event topic, function and purpose, settings, participants, message form, message content, sequence of actions, rules of interaction and interpretation norms. Next, comunicative actions, ninik mamak really understands the values contained in the custom of marriage. The meaning and value of marriage will be lost if there is no traditional wedding ceremony in a culture. Keywords : Ethnography Of Communication, Sirih Tanya Tanya Tradition, Malay Wedding Custom.
SISTEM PENDETEKSI KALIMAT UMPATAN DI MEDIA SOSIAL DENGAN MODEL NEURAL NETWORK Sahrul Sahrul; Ahmad Fauzan Rahman; Muhammad Dzaky Normansyah; Ade Irawan
Computatio : Journal of Computer Science and Information Systems Vol 3, No 2 (2019): COMPUTATIO : JOURNAL OF COMPUTER SCIENCE AND INFORMATION SYSTEMS
Publisher : Faculty of Information Technology, Universitas Tarumanagara

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (418.739 KB) | DOI: 10.24912/computatio.v3i2.6032

Abstract

Governments and social media providers put high effort to tackle massive negative contents in social media. Those contents are mostly containing religion, race, and inter-group issues, cyberbullying, and also body shamming, which usually appears together with offensive languages. It becomes difficult to overcome because of a large number of internet users in Indonesia. Hence, we need a system that can automatically detect the negative contents. This paper utilizes Neural Network (NN) models for not only classifying the words as (non)offensive words but also considering the structure of the sentence to get its context. There are two NN models analyzed in this paper: Artificial Neural Network (ANN) and Recurrent Neural Network (RNN). The computer simulation results show that the RNN has better performances than the ANN with the accuracy of training, validation, and testing 94%, 84%, and 84%, respectively. Pemerintah dan penyedia layanan media sosial di Indonesia berusaha keras untuk mengatasi maraknya konten negatif di media sosial. Konten negatif yang sering ditemui diantaranya isu suku, agama, ras, dan antargolongan (SARA), cyberbullying, serta body shamming, yang biasanya muncul disertai kalimat-kalimat umpatan. Hal tersebut menjadi sulit untuk diatasi karena jumlah pengguna internet di Indonesia yang sangat besar, sehingga perlu adanya sebuah sistem yang dapat mendeteksinya secara otomatis. Penelitian ini mengusulkan sistem dengan model Neural Network untuk deteksi konten negatif di media sosial dengan cara mempertimbangkan konteks kalimat atau frasa, tidak hanya kata-per-kata. Ada dua model NN yang dianalisis di penelitian ini, yaitu Artificial Neural Network (ANN) dan Recurrent Neural Network (RNN). Model RNN menunjukkan performa yang lebih baik dibandingkan dengan model ANN dengan akurasi training, validasi, dan test masing-masing adalah 94%, 84%, dan 84%.  
ANALISIS FAKTOR-FAKTOR YANG MEMPENGARUHI KEBIJAKAN HUTANG DAN PENGARUHNYA TERHADAP NILAI PERUSAHAAN Ade Irawan; Hendro Setyono
Jurnal Fokus Manajemen Bisnis Vol. 3 No. 2 (2013)
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/fokus.v3i2.1338

Abstract

The purpose of this study was to analyze the effect of the variable firm size (Size), business risk (risk), and liquidity (CR) of the debt policy (DTA) and the effect of the debt policy on firm value (PBV) in the companies listed on the Indonesia Stock Exchange (BEI) the period of 2007-2011. This study uses purposive sampling method to take samples. The data obtained based on the publication of Indonesian Stock Exchange (IDX), obtained a total sample of 32 companies. The analysis technique used is multiple regression analysis stages. Hypothesis testing using the t test. Similarly, the business risk variable positive and significant effect on the debt policy because it has a significance value smaller than 5% level. While the liquidity variable and significant negative effect on the debt policy because it has significant value which is lower than the 5% significance level. And the debt policy itself has a positive and significant impact on firm value.
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.
Prediksi Energi Listrik Kincir Angin Berdasarkan Data Kecepatan Angin Menggunakan LSTM Muhammad Qubaisy Andiyantama; Iffah Zahira; Ade Irawan
JITCE (Journal of Information Technology and Computer Engineering) Vol 5 No 01 (2021): Journal of Information Technology and Computer Engineering
Publisher : Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/jitce.5.01.1-7.2021

Abstract

Fossil energy is well known as the most energy resource consumed by humans. However, the exploitation leads to damage both in the process of taking raw materials and in the use of those. Furthermore, the amount has become decreasing nowadays. Renewable energy could solve the energy crisis. One kind of renewable energy that has been successfully used by a human is by utilizing wind turbines. However, there are still many problems in its implementation and usage. One of the problems is the unstable generated electricity that is caused by instability of the wind speed. Inappropriate plans for utilizing wind turbines in such areas with varying wind speed could harm renewable energy investment. Therefore, forecasting the wind speed is necessary to anticipate the stability and embrace optimal produced energy. This study proposes the Long Short Term Memory (LSTM) algorithm to predict the generated energy by using the wind speed dataset. Thus, wind turbines can be utilized effectively and efficiently in the right area with sufficient average wind speed.
Model Penerjemah Bahasa Isyarat Indonesia (BISINDO) Menggunakan Pendekatan Transfer Learning Meredita Susanty; Riestiya Zain Fadillah; Ade Irawan
PETIR Vol 15 No 1 (2022): PETIR (Jurnal Pengkajian Dan Penerapan Teknik Informatika)
Publisher : Sekolah Tinggi Teknik - PLN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33322/petir.v15i1.1289

Abstract

Sistem Bahasa Isyarat Indonesia (SIBI) yang berasal dari bahasa isyarat Amerika (American Sign Language) dan lebih banyak dipakai pada situasi formal tidak terlalu familiar bagi insan tuli atau difabel rungu di Indonesia karena mereka umumnya menggunakan Bahasa Isyarat Indonesia (Bisindo). Sejak 1975 perwakilan Tuli melalui organisasi kemasyarakatan Gerakan untuk Kesejahteraan Tunarungu Indonesia (Gerkatin) telah meminta pemerintah untuk mengakui Bisindo sebagai bahasa pengantar resmi di Sekolah Luar Biasa namun upaya ini hingga kini belum berhasil. Untuk membantu meningkatkan aksesibilitas Tuli dengan menambah jumlah penerjemah serta memperluas pemahaman Bisindo di masyarakat luas, penelitian ini berupaya membangun mesin penerjemah bahasa isyarat menggunakan teknik machine learning dengan algoritma Convolutional Neural Network (CNN). Karena bukan merupakan bahasa isyarat format, ketersediaan dataset Bisindo di Internet terbatas. Metode transfer learning, yaitu dengan memanfaatkan model yang dilatih dengan dataset ASL kemudian disesuaikan untuk melakukan pekerjaan yang sama pada menggunakan dataset Bisindo digunakan dalam penelitian ini untuk mengatasi masalah keterbatasan dataset. Karena perbedaan karakteristik bahasa isyarat dan gestur dari masing-masing bahasa isyarat, pemindahan knowledge khususnya learning parameter dari Model ASL tidak dapat meningkatkan performa Model Bisindo dalam memprediksi seluruh huruf pada alfabet Bisindo sehingga model hasil transfer learning hanya mampu memprediksi huruf-huruf Bisindo yang memiliki kemiripan dengan ASL.
ANALISA PENGARUH VOLUME KENDARAAN TERHADAP KERUSAKAN JALAN RIGID DI TELUK KUANTAN Gusmulyani Gusmulyani; ade irawan; Yolanda yolanda
JURNAL PLANOLOGI DAN SIPIL (JPS) Vol 4 No 1 (2022): JPS, Volume 4 Nomor 1, April 2022
Publisher : LEMBAGA PENELITIAN DAN PENGABDIAN KEPADA MASYARAKAT (LPPM)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Volume kendaraan merupakan salah satu faktor penyebab kerusakan jalan, dan tidak adanya drainase memperparah kerusakan. Jalan Tuanku Tambusai, Rustam S Abrus dan Sudirman, merupakan jalan rigid di Kuantan Singingi.Jalan tersebut banyak di lalui kendaraan berat yang jumlahnya semakin meningkat sehingga sudah mulai rusak. Penelitian ini bertujuan untuk mengetahui pengaruh volume kendaraan dan drainase terhadap kerusakan jalan rigid. Penelitian ini menggunakan data primer data inventori jalan, yaitu lebar jalan dan panjang jalan, data kerusakan jalan, volume kendaraan dan drainase di sepananjang jalan. Metode yang digunakan untuk mengetahui pengaruh volume kendaraan terhadap tingkat kerusakan jalan rigid dilakukan dengan metode regresi linier. Kerusakan jalan sebagai variabel terikat (Y) dan volume kendaraan sebagai variabel bebas (kendaraan ringan (X1), kendaraan berat (X2) dan sepeda motor (X3) serta kendaraan tidak bermotor (X4). Hasil regresi di analisa dan di uji secara statistik. Dari hasil regresi di dapatkan persamaan yaitu Y = -8,060734 + 0,05922186.x1 + 1,24106192.x2 + (-0,0126309).x3, dengan R2 = 0,87679874. Dari hasil regersi ini dapat disimpulkan bahwa volume kendaraan (X) berpengaruh terhadap kerusakan jalan (Y) sebesar 87,68% dan sisanya dipengaruhi oleh faktor lain. Sedangkan dari drainase di dapatkan sangat kecil hubungan panjang drainase jalan dengan kerusakan jalan karena dari semua jalan rigid yang di teliti belum mempunyai drainase di sepanjang jalannya, hanya ada di beberapa lokasi saja.
PELELANGAN PENGADAAN BARANG DAN JASA KONSTRUKSI DALAM PERSPEKTIF ISLAM Ade Irawan; Surya Adinata; Chitra Hermawan; Dwi Visti Rurianti; Joko Triyanto
BHAKTI NAGORI (Jurnal Pengabdian kepada Masyarakat) Vol 2 No 2 (2022): BHAKTI NAGORI (Jurnal Pengabdian kepada Masyarakat) Desember 2022
Publisher : LPPM UNIKS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/bhakti_nagori.v2i2.2708

Abstract

Pelelangan Pengadaan Barang dan Jasa Konstruksi dilaksanakan dipemerintahan maupun swasta. Pihak penyelenggara dan peserta lelang diatur oleh aturan yang baku. Etika sangat diperlukan dalam pelaksanaan pelelangan ini. Namun, dalam pelaksanaannya terkadang masih ada kecurangan-kecurangan yang tidak terdeteksi oleh etika. Sehingga, hal yang tidak terdeteksi oleh etika diperlukan nilai-nilai islam bahwa ada aturan Allah SWT yang memperkuat etika pelelangan. LKPP LPSE adalah Lembaga Pemerintah Non-Kementerian (LPNK) yang berada di bawah naungan Presiden Republik Indonesia yang bertugas untuk melaksanakan pengadaan barang jasa Pemerintah. Sedangkan Layanan Pengadaan Secara Elektronik (LPSE) adalah sistem elektronik pengadaan barang jasa Pemerintah yang dikembangkan oleh LKPP. Materi Pelelangan Pengadaan Barang dan Jasa Konstruksi dalam Perspektif Islam yang disampaikan oleh Tim dosen Prodi Teknik Sipil diantaranya bahwa mata kuliah yang relevan terhadap pelelangan proyek yakni enggambar Struktur Bangunan di semester 1, Rencana anggaran Biaya serta Aspek Hukum dan Pembangunan serta manajemen proyek di semester 5, Etika Leadher Ship dan Kewirausahaan Konstruksi di semester 6. Proses pelelangan merujuk pada Perpres No. 12 Tahun 2021 tentang Perubahan Atas Peraturan Presiden Nomor 16 Tahun 2018 Tentang Pengadaan Barang/Jasa Pemerintah. Syariah Islam membolehkan jual beli barang/ jasa yang halal dengan cara lelang yang dalam fiqih disebut sebagai akad Bai’ Muzayadah. Titik berat Pelelangan Pengadaan Barang dan Jasa Konstruksi dalam Perspektif Islam adalah keadilan. Penyelenggara dan peserta lelang agar menjadikan etika berkeadilan bersumber dari Allah SWT sebagai basis keimanan dalam proses pelelangan untuk keselamatan dunia dan akhirat.
Determinan Akuntan Publik dalam Memberikan Opini Audit Going Concern pada Perusahaan Jasa Sub Sektor Transportasi di Bei Periode 2019-2021 Fitrawansyah Fitrawansyah; Ade Irawan; Udin Saepudin; Inggil Rahmawati
Journal on Education Vol 5 No 3 (2023): Journal on Education: Volume 5 Nomor 3 Tahun 2023
Publisher : Departement of Mathematics Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/joe.v5i3.1403

Abstract

This study aims to determine the effect of the company's financial condition and debt default on the going concern audit opinions on transportation service companies listed on the Indonesia Stock Exchange (IDX) in 2019-2021. This type of research is a quantitative research using secondary data that can be accessed from the personal website of a transportation sub-sector service company listed on the Indonesia Stock Exchange (IDX). This research uses the purposive sampling method, namely by taking samples from the population based on certain criteria. The research sample based on the criteria amounted to 12 companies with a research period of 3 years, so a total sample of 36 companies' financial statement data. The data analysis method used in this study is a statistical method using logistic regression equations. Data analysis begins with processing data with Microsoft Excel, then logistic regression testing is carried out using SPSS version 23 software. The results of this study indicate that the company's financial condition affects the going concern audit opinion; Debt default does not affect the going concern audit opinion; The company's financial condition and debt default simultaneously affect the going concern audit opinion.