Article Per Year (5 Year)
p-Index From 2020 - 2025
0.659
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Teknologi dan Rekayasa International Journal of Advances in Intelligent Informatics Jurnal Ilmiah KOMPUTASI Faktor Exacta
Setia Wirawan
Universitas Gunadarma
Automotive Engineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
IMPLEMENTASI METODE NOISE GATE, LOW PASS FILTER DAN SILENT REMOVAL UNTUK MENGHILANGKAN NOISE PADA FILE SUARA MENGGUNAKAN PARAMETER DINAMIS Prasetyo, Edy; Wirawan, Setia
Jurnal Ilmiah Teknologi dan Rekayasa Vol 21, No 3 (2016)
Publisher : Universitas Gunadarma

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

Abstract

Noise adalah suatu sinyal gangguan yang bersifat akustik (suara), elektris, maupun elektronis yang hadir dalam suatu sistem dalam bentuk gangguan yang bukan merupakan sinyal yang diinginkan. Rekaman suara yang terdistorsi noise menyebabkan terganggunya proses pengenalan suara terutama pada rekaman pembicaraan. Penulisan ini membahas mengenai implementasi metode noisegate untuk meredam bagian yang hanya dianggap noise, low pass filter untuk me-cutoffhigh frequencynoise dan silent removal untuk menghilangkan bagian diam pada file rekaman suara pembicaraan. Setiap file suara memiliki nilai dynamic range dan crest factor yang berbeda yang dijadikan sebagai acuan dalam pengisian parameter sehingga bersifat dinamis. Hasil yang didapat dari pembuatan aplikasi ini terdapat dua komparasi antara sinyal asli dengan sinyal asli + noise dan sinyal asli dengan output aplikasi, kedua komparasi tersebut menghasilkan peningkatan keberhasilan dalam pengenalan suara dari penggunaan metode noise gate, low pass filter dan silent removal untuk menghilangkan noise adalah 3,5 kali lipat dibandingkan dengan pengenalan suara tanpa dilakukan penghilangan noise pada file suara sebelumnya. Kata kunci : Noise gate, Low Pass Filter, Silent Removal, Dinamis, Matlab.
Prediksi Penjualan Kendaraan Niaga Berdasarkan Kinerja Purnajual dan Pertumbuhan Pasar Novika Ginanto; Setia Wirawan
Faktor Exacta Vol 14, No 4 (2021)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v14i4.9447

Abstract

Indonesia is one of the largest automotive market in South East Asia with highly demand of passenger and commercial vehicle. Commercial vehicle is used to distribute product to customers, then commercial vehicle strongly related with business growth. Gaikindo said that automotive business growth went down as 10.6%, it would effect to automotive company performance, especially vehicle stock ratio. Vehicle stock ratio can affect to financial and resources planning. Therefore, the forecasting was to be important to predict the market demand in future.  Basically, commercial vehicle would be used in along day due to business value, therefore aftersales services was critical point. In this case, sales forecasting of commercial vehicle (dependent variable) was approached by trend of aftersales performance and market growth (independent variable). Aftersales performance consist of aftersales revenue and unit served volume, then market growth using SAMSAT data. Prediction method used multiple linear regression due to forecasting capability with many variables. And the result using SPSS application was confirmed that independent variable affect to commercial vehicle sales volume and not multicollinearity. The result error of MAD was 3.80.  So that, sales forecasting of commercial vehicle can be predicted based on aftersales performance and market growth using multiple linear regression. Indonesia is one of the largest automotive market in South East Asia with highly demand of passenger and commercial vehicle. Commercial vehicle is used to distribute product to customers, then commercial vehicle strongly related with business growth. Gaikindo said that automotive business growth went down as 10.6%, it would effect to automotive company performance, especially vehicle stock ratio. Vehicle stock ratio can affect to financial and resources planning. Therefore, the forecasting was to be important to predict the market demand in future.  Basically, commercial vehicle would be used in along day due to business value, therefore aftersales services was critical point. In this case, sales forecasting of commercial vehicle (dependent variable) was approached by trend of aftersales performance and market growth (independent variable). Aftersales performance consist of aftersales revenue and unit served volume, then market growth using SAMSAT data. Prediction method used multiple linear regression due to forecasting capability with many variables. And the result using SPSS application was confirmed that independent variable affect to commercial vehicle sales volume and not multicollinearity. The result error of MAD was 3.80.  So that, sales forecasting of commercial vehicle can be predicted based on aftersales performance and market growth using multiple linear regression.  
Pembuatan Aplikasi Deteksi Objek Menggunakan TensorFlow Object Detection API dengan Memanfaatkan SSD MobileNet V2 Sebagai Model Pra - Terlatih: Array Prisky Ratna Aningtiyas; Agus Sumin; Setia Wirawan
Jurnal Ilmiah Komputasi Vol. 19 No. 3 (2020): Jurnal Ilmiah Komputasi Volume: 19 No. 3, September 2020
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32409/jikstik.19.3.68

Abstract

Deteksi objek merupakan salah satu teknik untuk menemukan objek dalam gambar atau video. Salah satu metode untuk membuat deteksi objek adalah menggunakan TensorFlow Object Detection API. Metode tersebut menyediakan model pra – terlatih yang dapat dimanfaatkan dalam pembuatan aplikasi deteksi objek. Model yang digunakan dalam penelitian ini adalah SSD Mobilenet V2. Model tersebut dapat melakukan deteksi objek dengan menghasilkan akurasi dan area terdeteksi untuk keberadaan setiap kategori objek pada suatu gambar. Oleh karena itu, penelitian ini akan membuat aplikasi deteksi objek dengan memanfaatkan metode tersebut. Penelitian ini bertujuan untuk membuat aplikasi deteksi objek menggunakan TensorFlow Object Detection API dengan memanfaatkan SSD Mobilenet V2 sebagai model pra – terlatih dalam penerapan ilmu Deep Learning. Aplikasi diharapkan dapat melakukan deteksi dan mengukur akurasi objek, yaitu Camera, Handphone, Headphone, Laptop, dan Mouse melalui input gambar. Dataset yang digunakan dibuat dengan mengumpulkan sebanyak 500 gambar dengan membagi menjadi tiga bagian, yaitu train set, validation set, dan test set dengan masing – masing perbandingan sebesar 70% : 20% : 10%. Pelatihan dilakukan dengan bantuan Google Research Colaboratory sebagai virtual machine. Penelitian ini menggunakan Python 3.6.8 sebagai bahasa pemrograman dan memakai beberapa library yang disediakan oleh Python. Dari uji coba yang dilakukan, aplikasi ini memiliki tingkat akurasi sebesar 93.02% pada test set.
Multidisciplinary classification for Indonesian scientific articles abstract using pre-trained BERT model Antonius Angga Kurniawan; Sarifuddin Madenda; Setia Wirawan; Ruddy J. Suhatril
International Journal of Advances in Intelligent Informatics Vol 9, No 2 (2023): July 2023
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/ijain.v9i2.1051

Abstract

Scientific articles now have multidisciplinary content. These make it difficult for researchers to find out relevant information. Some submissions are irrelevant to the journal's discipline. Categorizing articles and assessing their relevance can aid researchers and journals. Existing research still focuses on single-category predictive outcomes. Therefore, this research takes a new approach by applying a multidisciplinary classification for Indonesian scientific article abstracts using a pre-trained BERT model, showing the relevance between each category in an abstract. The dataset used was 9,000 abstracts with 9 disciplinary categories. On the dataset, text preprocessing is performed. The classification model was built by combining the pre-trained BERT model with Artificial Neural Network. Fine-tuning the hyperparameters is done to determine the most optimal hyperparameter combination for the model. The hyperparameters consist of batch size, learning rate, number of epochs, and data ratio. The best hyperparameter combination is a learning rate of 1e-5, batch size 32, epochs 3, and data ratio 9:1, with a validation accuracy value of 90.8%. The confusion matrix results of the model are compared with the confusion matrix results by experts. In this case, the highest accuracy result obtained by the model is 99.56%. A software prototype used the most accurate model to classify new data, displaying the top two prediction probabilities and the dominant category. This research produces a model that can be used to solve Indonesian text classification-related problems.
Co-Authors Agus Sumin Antonius Angga Kurniawan Edy Prasetyo Novika Ginanto Prisky Ratna Aningtiyas Ruddy J Suhatril Sarifuddin Madenda