Claim Missing Document
Check
Articles

Found 36 Documents
Search

Kajian Penentuan Nilai Epsilon Optimal Pada Algoritma DMDBSCAN Dan Pemetaan Daerah Rawan Gempa Bumi Di Indonesia Tahun 2014-2020 Kamilia Wafa Pakuani; Robert Kurniawan
Seminar Nasional Official Statistics Vol 2021 No 1 (2021): Seminar Nasional Official Statistics 2021
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (538.426 KB) | DOI: 10.34123/semnasoffstat.v2021i1.847

Abstract

Area pengawasan gempa bumi dapat dilakukan dengan menemukan penyebaran poin gempa atau pengelompokan gempa acak. Density-Based Spatial Clustering of Applications with Noise (DBSCAN) adalah salah satu algoritma clustering yang disegel dari sejumlah data besar yang mengandung noise atau outlier. Penelitian sebelumnya mengubah Algoritma DBSCAN untuk secara otomatis menemukan nilai Epsilon (Eps) optimal dengan menggunakan metode Algoritma Dynamic Method DBSCAN (DMDBSCAN). Nilai parameter Eps diperoleh dari perhitungan perubahan slope atau kemiringan garis maksimum pada 3 jarak dari tetangga paling dekat dalam distribusi data. Namun, cara ini rentan terhadap perubahan kemiringan garis yang sangat jauh. Maka dari itu, penelitian ini melakukan modifikasi cara tersebut dengan mencari nilai minimal pada rentang slope antara 10% hingga 20%. Nilai Eps yang dihasilkan setelah modifikasi menunjukkan angka yang lebih baik. Oleh karena itu, cara ini diharapkan dapat menjadi referensi untuk pencarian parameter Eps dalam Algoritma DMDBSCAN yang lebih cocok dan mengetahui distribusi titik gempa di Indonesia.
Determinan Produktivitas Tenaga Kerja Industri Mikro dan Kecil (IMK) di Provinsi Bali Tahun 2020 Kadek Angga Wicaksana; Robert Kurniawan
Seminar Nasional Official Statistics Vol 2022 No 1 (2022): Seminar Nasional Official Statistics 2022
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (540.12 KB) | DOI: 10.34123/semnasoffstat.v2022i1.1436

Abstract

Labor productivity is an important variable that is closely related to economic growth, competitiveness, and standard of living. However, it turns out that the manufacturing sector in Bali Province has a relatively low level of labor productivity. Therefore, this study aims to identify the variables that affect labor productivity. The analytical method used is a descriptive analysis using tables and graphs inferential analysis using robust regression analysis. The results of the analysis showed that the variable percentage of the workforce who graduated from high school and equivalent, the variable percentage of the male workforce, the variable working hours, the innovation variable, and the raw material variable showed a significant effect affecting the productivity of the IMK business workforce.
The impact of the basic dose of the COVID-19 vaccine and the number of COVID-19 patients on Google searches for vaccines Ignatius Sandyawan; Robert Kurniawan; Victor Trismanjaya Hulu; Frans Judea Samosir
International Journal of Public Health Science (IJPHS) Vol 12, No 1: March 2023
Publisher : Intelektual Pustaka Media Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijphs.v12i1.22175

Abstract

Indonesia has distributed the COVID-19 vaccinations to its people starting from January 2021 based on certain priorities to deal with COVID-19 pandemic. News of deaths after the COVID-19 vaccination has made some people hesitate to get vaccinated. This study aims to depict the pattern and determinant of public interest in COVID-19 vaccine information using Google Trends data. The pattern can be used as a suggestion to the government to conduct a campaign on the COVID-19 vaccine. Several topics related to the COVID-19 vaccine were collected from Google Trends and then clustered by the province using K-Means. By total within sum of square, best number of clusters is two. Then, a logistic regression analysis was done with cluster as response variable to find out what factors made people interested in the COVID-19 vaccine topic. As a result, percentage of people who received the first dose of the COVID-19 vaccine and the rate of COVID-19 patients who were treated had influenced public interest in the COVID-19 vaccine. Hence, the campaign must be transparent so that the public can see both the good and bad effects of vaccination. It will help to reduce the number of people dying after receiving vaccinations.
Pengelompokkan Toko Kaus Termurah E-Commerce Shopee berdasarkan Reputasi Toko Menggunakan Metode Clustering K-Medoids dan K-Means Singrapati, Lalu Riza; Dora, Rika; Kurniawan, Robert
JUSTIN (Jurnal Sistem dan Teknologi Informasi) Vol 12, No 1 (2024)
Publisher : Jurusan Informatika Universitas Tanjungpura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/justin.v12i1.69067

Abstract

Kaus merupakan salah satu jenis pakaian yang paling diminati saat ini. Terutama setelah hadirnya toko e-commerce yang memudahkan pembeli untuk bertransaksi dengan cepat tanpa harus pergi ke tokonya secara langsung. Banyak toko online yang menawarkan kaus dengan harga yang terjangkau. Namun, pembeli harus selektif dalam melakukan transaksi jual beli melalui e-commerce karena banyaknya risiko yang bisa timbul. Untuk mengatasi hal tersebut, salah satu hal yang dapat dilakukan yaitu mengelompokkan toko pada platform e-commerce Shopee berdasarkan reputasi menggunakan metode K-Means dan K-Medoids. Penelitian ini menggunakan data dari tiga ratus akun toko kaus dengan harga termurah di Shopee. Tahapan dalam penelitian ini meliputi pengumpulan data, preprocessing data, penentuan jumlah cluster optimum, analisis cluster menggunakan K-Means dan K-Medoids, evaluasi model, interpretasi output, dan penarikan Kesimpulan. Berdasarkan hasil evaluasi, diperoleh metode terbaik ialah K-Means dengan k optimum sebanyak tiga cluster. Kemudian, cluster yang direkomendasikan kepada customer ialah cluster pertama.
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.
Pemanfaatan Data Citra Satelit Untuk Memprediksi Produksi Padi Tahun 2018-2022 dengan Membandingkan Metode Machine Learning dan Ekonometrik Hidayat, Arief Ramadhan Rifky; Parina, Okta; Kurniawan, Robert
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.v2023i1.1779

Abstract

This study aims to evaluate and compare the prediction accuracy of rice production in East Java in 2018-2022 using three methods namely Support Vector Regression (SVR), Autoregressive Integrated Moving Average With Exogenous Variable (ARIMAX), and Autoregressive Distributed Lag (ARDL). The dependent variable is rice production with the independent variables Normalized Difference Water Index (NDWI), Soil Adjusted Vegetation Index (SAVI), and Farmer's Exchange Rate (NTP) derived from satellite imagery and the Central Bureau of Statistics. The best model of this research is SVR with Radial Basis Function (RBF) because it has Mean Absolute Percentage Error (MAPE) and Mean Squared Error (MSE) values of 35.42% and 46.93. The parameters cost (C), gamma (γ), epsilon (ε), and number of support vectors used in the SVR model are 1; 0.33; 0.1; and 43. SAVI is the variable that best describes rice production because it has the same distribution pattern and is the only significant variable in the long-term model.
Urban traffic congestion and its association with gas station density: insights from Google Maps data Hasabi, Rafif; Kurniawan, Robert; Sugiarto, Sugiarto; Tri Wahyuni, Ribut Nurul; Nurmawati, Erna
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 3: September 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i3.pp1618-1626

Abstract

Analyzing air pollution caused by traffic conditions requires appropriate indicators. Currently, air pollution indicators are approximated by the number of vehicles and gas station density. However, this approach cannot provide information at a smaller level. This study aims to identify traffic congestion distribution from Google Maps data as an alternative air pollution indicator at smaller level using map digitization method. In addition, this study examines its relationship with the existing indicator called gas station density. The results show that the digitization method can map the traffic congestion distribution where most areas in West, North, and Central Jakarta are classified as high traffic. In addition, this study found that there is a strong and significant relationship of 0.58277 between traffic congestion distribution and gas station density. Thus, traffic congestion distribution and gas station density data from Google Maps can be used as an indicator of traffic-related air pollution, especially land transportation. Furthermore, this research is expected to serve as a basis for the government in determining mitigation strategies related to traffic congestion and the resulting emissions.
Analisis Kecenderungan Sosio-Demografi pada Kemiskinan Multidimensi di Provinsi Bengkulu Tahun 2015 Murti, Sartika Andari; Kurniawan, Robert
Prosiding Konferensi Nasional Penelitian Matematika dan Pembelajarannya 2019: Prosiding Konferensi Nasional Penelitian Matematika dan Pembelajarannya
Publisher : Universitas Muhammadiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (577.242 KB)

Abstract

Digitalisasi industri melalui Revolusi Industri 4.0 mampu meningkatkan efisiensi dan kualitas produk. Kebijakan ini dapat berdampak negatif jika tidak didukung oleh kualitas masyarakat terutama melalui kondisi kemiskinan dalam berbagai dimensi. Misalkan kondisi kemiskinan di Provinsi Bengkulu yang masih menempati peringkat pertama dengan angka kemiskinan tertinggi di kawasan Indonesia Barat. Pengukuran yang digunakan untuk melihat kondisi kemiskinan dalam berbagai dimensi secara mikro adalah dengan kemiskinan multidimensi. Penelitian ini dilakukan untuk mengetahui kecenderungan karakteristik sosio-demografi masyarakat terhadap kemiskinan multidimensi di Provinsi Bengkulu. Pengukuran kemiskinan multidimensi ini menggunakan Metode Alkire Foster. Sedangkan untuk menganalisis kecenderungan sosio demografi digunakan regresi logistik biner dengan variabel independennya adalah klasifikasi wilayah tinggal, jumlah anggota rumah tangga, jenis kelamin dan pendidikan tertinggi kepala rumah tangga. Hasil yang didapatkan adalah keempat variabel independen tersebut signifikan mempengaruhi status kemiskinan multidimensi dan rumah tangga dengan jumlah anggota lebih dari empat orang dan kepala rumah tangga berpendidikan tertinggi SD kebawah yang berjenis kelamin perempuan di perdesaan memiliki kecenderungan lebih besar untuk berstatus miskin secara multidimensi.
Deteksi Sampah di Permukaan Sungai menggunakan Convolutional Neural Network dengan Algoritma YOLOv8 Hutabarat, Rizky Theofilus; Kurniawan, Robert
Seminar Nasional Official Statistics Vol 2024 No 1 (2024): Seminar Nasional Official Statistics 2024
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2024i1.2099

Abstract

The increase in solid wastes floating on surface of rivers has become a big problem in the urban environment, such as floods and diseases. The goal of this research is to build an object detection model using Convolutional Neural Network (CNN) with YOLOv8 (You Only Look Once v8) algorithm, and to implement that model to detect floating wastes on the surface of Ciliwung River. The model used in this research is YOLOv8, because of its high speed and accuracy. The data used are obtained from online sources (Google Images and YouTube), and directly from Ciliwung River obtained with smartphone camera. The best epoch is the 177th epoch. The Precision value is 84.02%, the Recall value is 91.03%, the Accuracy value is 77.6%, and the F1-Score is 87.38%. The conclusion is that the model built with YOLOv8 algorithm can be used to detect floating wastes on the surface of Ciliwung River.
Measuring Well-Being Index with Environmental in Mind: Evidence Forest Land Use in Indonesia Wahyuni, Krismanti Tri; Purwanto, Agung; Sumargo, Bagus; Sitorus, Agnes Vera Yanti; Kurniawan, Robert; Nugroho, Yoga Dwi; Syaifudin, Syaifudin
International Journal of Business, Law, and Education Vol. 5 No. 2 (2024): International Journal of Business, Law, and Education
Publisher : IJBLE Scientific Publications Community Inc.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56442/ijble.v5i2.873

Abstract

This project aims to create an objective composite wellbeing index from the point of view of the whole by using a complete welfare methodology and suggested weightings to take into account the differences between the components. Forestry total productivity (TFP) was also compared because of the importance of the environmental component in preparing the well-being index. This study examined 64 social, economic, environmental, and institutional indicators from the BPS-Statistics Indonesia, the Ministry of Environment and Forestry, and the National Disaster Management Agency. Three primary analysis elements were highlighted in this investigation. First, PCA created a weighted index of eleven important domains. Second, it creates a well-being index model for Indonesia's environmental sustainability. Third, comparing forestry's environmental dimension to its TFP. This study found that the Indonesian wellbeing model under construction weighs environmental quality, living conditions, including housing, and happiness. Indonesia's disaster-prone locations make environmental quality important, unlike other wellbeing indices. Forest degradation has decreased the composite wellbeing index, notwithstanding other socio-economic improvements. This study stands out from past research by being the first to compare the environmental dimension with forestry total factor productivity (TFP). Deforestation significantly affects the well-being index in Indonesia.