Claim Missing Document
Check
Articles

Found 5 Documents
Search

Perbandingan Model Estimasi Artificial Neural Network Optimasi Genetic Algorithm dan Regresi Linier Berganda Sebayang, Jimmy Saputra; Yuniarto, Budi
MEDIA STATISTIKA Vol 10, No 1 (2017): Media Statistika
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (515.163 KB) | DOI: 10.14710/medstat.10.1.13-23

Abstract

Multiple Linear Regression is a statistical approach most commonly used in performing predictive data modeling. One of the methods that can be used in estimating the parameters of the model on Multiple Linear Regression is Ordinary Least Square. It has classical assumptions requirements and often the assumptions are not satisfied. Another method that can be used as an alternative data modeling is Artificial Neural Network. It is  a free-distribution estimator because there's no assumptions that have to be satisfied.  However, modeling data using ANN has some problems such as selection of network topology, learning parameters and weight initialization. Genetic Algorithm method can be used to solve those problems. A set of simulation data was generated to test the reliability of ANN-GA model compared to Multiple Linear Regression model. Model comparison experiments indicate that ANN-GA model are better than Multiple Linear Regression model for estimating simulation data both on the data training and data testing.Keywords:Neural Network, Genetic Algorithm, Ordinary Least Square
Implementing deep learning-based named entity recognition for obtaining narcotics abuse data in Indonesia Azhar, Daris; Kurniawan, Robert; Marsisno, Waris; Yuniarto, Budi; Sukim, Sukim; Sugiarto, Sugiarto
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 1: March 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i1.pp375-382

Abstract

The availability of drug abuse data from the official website of the National Narcotics Board of Indonesia is not up-to-date. Besides, the drug reports from Indonesian National Narcotics Board are only published once a year. This study aims to utilize online news sites as a data source for collecting information about drug abuse in Indonesia. In addition, this study also builds a named entity recognition (NER) model to extract information from news texts. The primary NER model in this study uses the convolutional neural network-long short-term memory (CNNs-LSTM) architecture because it can produce a good performance and only requires a relatively short computation time. Meanwhile, the baseline NER model uses the bidirectional long short-term memory-conditional random field (Bi-LSTMs-CRF) architecture because it is easy to implement using the Flair framework. The primary model that has been built results in a performance (F1 score) of 82.54%. Meanwhile, the baseline model only results in a performance (F1 score) of 69.67%. Then, the raw data extracted by NER is processed to produce the number of drug suspects in Indonesia from 2018-2020. However, the data that has been produced is not as complete as similar data sourced from Indonesian National Narcotics Board publications.
Analisis Pola Kecelakaan Lalu Lintas Menggunakan Algoritma Decision Tree Berdasarkan Ekstraksi Informasi dari Berita Online Menggunakan Named Entity Recognition (NER) Susanto, Hardi Dwi; Yuniarto, Budi
Seminar Nasional Official Statistics Vol 2023 No 1 (2023): Seminar Nasional Official Statistics 2023
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2023i1.1751

Abstract

Toll roads as freeways do not make toll roads free from traffic accidents. In 2020, West Java Province had a total of 20 toll roads spanning a length of 521,15 km. The Cipali Toll Road is one of the sections with the highest fatalities in the world. Prevention of traffic accidents is important as an effort to reduce the incidence of traffic accidents. However, official data regarding traffic accidents on toll roads by official agencies is not available in detail, so alternative data sources such as online news are used. NER with Bi-LSTM-CNN is used to extract accident data. The results of news extraction are analyzed by making decision rules to determine the pattern of accidents that occur. This decision rule is in the form of a decision tree with a dataset that uses data from three toll roads with the highest fatality with the mode by concept imputation feature as a missing value handling method and toll roads as attributes, resulting in an f1-score value of 67,76% and an accuracy value of 75,49 %.
Early Study of LLM Implementation in Survey Interviews Lailatul Hasanah; Yuniarto, Budi
Jurnal Aplikasi Statistika & Komputasi Statistik Vol 17 No 1 (2025): Jurnal Aplikasi Statistika & Komputasi Statistik
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/jurnalasks.v17i1.792

Abstract

Introduction/Main Objectives: This research aims to conduct a preliminary study into the use of LLMs for extracting information to fill out questionnaires in survey interviews. Background Problems: BPS-Statistics Indonesia used paper-based questionnaires for interviews and is recently utilizing the Computer Assisted Personal Interviewing (CAPI) method. However, the CAPI method has some drawbacks. Enumerators must input data into the device, which can be burdensome and prone to errors. Novelty: This study uses a large language model (LLM) to extract information from survey interviews. Research Methods: This study utilizes a text-to-speech application to translate interview results into text. Translation accuracy is measured by the Word Error Rate (WER). Then the text was extracted using the ChatGPT 3.5 Turbo model. GPT-3.5 Turbo is part of the GPT family of algorithms developed by OpenAI. Finding/Results: The extraction results are formatted into a JSON file, which is intended to be used for automatic filling into the database and then evaluated using precision, recall, and F1-score. Based on research conducted by utilizing the Speech Recognition API by Google and the ChatGPT 3.5 Turbo model, an average WER of 10% was obtained in speech recognition and an average accuracy of 76.16% in automatic data extraction.
Deep Learning and Remote Sensing for Agricultural Land Use Monitoring: A Spatio-Multitemporal Analysis of Rice Field Conversion using Optical Satellite Images Wijayanto, Arie Wahyu; Zalukhu, Bill Van Ricardo; Putri, Salwa Rizqina; Wilantika, Nori; Yuniarto, Budi; Kurniawan, Robert; Pratama, Ahmad R.
International Journal of Advances in Data and Information Systems Vol. 6 No. 2 (2025): August 2025 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v6i2.1385

Abstract

Rice is a staple food for over half of the global population, making its production crucial for food security, especially in Indonesia, the world's third-largest rice consumer. Population growth and urban expansion have led to agricultural land conversion, necessitating efficient monitoring methods. Traditional approaches, such as area sample frameworks and tile surveys, are costly and time-consuming, prompting the need for remote sensing and deep learning solutions. This study utilizes medium-resolution Sentinel-1, Sentinel-2, and Landsat-8 optical satellite imagery from 2013 and 2021 to analyze land cover changes in West Bandung and Purwakarta Regencies, key agricultural regions in Indonesia. A deep learning model is developed to classify land cover, validated through ground-truth evaluation, and applied to assess spatio-multitemporal land use conversion, paddy field estimation, and conversion rates. Results show that deep learning models effectively classify land cover with high accuracy, revealing significant agricultural land loss due to urban expansion. This research contributes to artificial intelligence (AI)-driven land monitoring, particularly in tropical regions, and supports policymakers in sustainable food agriculture land management. The findings highlight the potential of integrating remote sensing and deep learning for cost-effective agricultural monitoring, ensuring food security and sustainable land use. Future research should explore higher-resolution imagery and advanced AI techniques to enhance predictive accuracy and decision-making.