Agus Rusgiyono
Departemen Statistika, Fakultas Sains Dan Matematika, Universitas Diponegoro

Published : 107 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 77 Documents
Search
Journal : Jurnal Gaussian

PEMODELAN MIXED GEOGRAPHICALLY WEIGHTED REGRESSION (MGWR) DENGAN JARAK EUCLIDEAN DAN JARAK MANHATTAN (STUDI KASUS : KEMATIAN BAYI NEONATAL DI JAWA TENGAH TAHUN 2018-2020) Riszki Bella Primasari; Agus Rusgiyono; Dwi Ispriyanti
Jurnal Gaussian Vol 11, No 4 (2022): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.11.4.478-487

Abstract

Neonatal is a condition of babies from birth to 28 days. Data on Indonesia's health profile in 2020 showed that 72% of the number of deaths of toddlers occurred during the neonatal period and Central Java became the highest province of cases. Factors that are suspected to influence are the number of low birth weight babies (X1), the number of obstetric complications (X2), the number of Puskesmas (X3), the number of Posyandu (X4), the number of exclusive breastfeeding babies 0-6 months (X5), the number of pediatricians (X6), the number of ambulance cars (X7). Linear regression modeling on the number of neonatal infant deaths in Central Java has a heteroskedasticity problem so that Geographically Weighted Regression (GWR) is used. The distances used are Euclidean and Manhattan as well as the weighting function using Exponential and Tricube Kernel with Fixed Bandwidth. GWR modeling shows that not all independent variables are local, so Mixed Geographically Weighted Regression (MGWR) is used. The results of the GWR analysis with both distances and the two variable weighting functions are not local, including X2, X5, and X7. MGWR distance Manhattan Fixed Tricube Kernel became the better model, as the AICC value was smaller.
ANALISIS SUPPORT VECTOR REGRESSION (SVR) DENGAN ALGORITMA GRID SEARCH TIME SERIES CROSS VALIDATION UNTUK PREDIKSI JUMLAH KASUS TERKONFIRMASI COVID-19 DI INDONESIA Anindita Nur Safira; Budi Warsito; Agus Rusgiyono
Jurnal Gaussian Vol 11, No 4 (2022): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.11.4.512-521

Abstract

Coronavirus Disease 2019 or Covid-19 is a group of types of viruses that interfere with the respiratory tract associated with the seafood market that emerged in Wuhan City, Hubei Province, China at the end of 2019. The first confirmed cases of Covid-19 in Indonesia on March 2, 2020, were 2 cases and until the end of 2021, it continues to grow every day. The purpose of this study was to predict the number of confirmed cases of Covid-19 in Indonesia using the Support Vector Regression (SVR) method with linear kernel functions, radial basis functions (RBF), and polynomials. Support Vector Regression (SVR) is the application of a support vector machine (SVM) in regression cases that aims to find the dividing line in the form of the best regression function. The advantage of the SVR model is can be used on time series data, data that are not normally distributed and data that is not linear. Parameter selection for each kernel used a grid search algorithm combined with time series cross validation. The criteria used to measure the goodness of the model are MSE (Mean Square Error), MAPE (Mean Absolute Percentage Error) and R2 (Coefficient of Determination). The results of this study indicate that the best model is Support Vector Regression (SVR) with a polynomial kernel and the parameters used include Cost = 1, degree = 1, and coefficient = 0.1. The polynomial kernel SVR model produces a MAPE value of 0.4946215%, which means the model has very good predictive ability. The prediction accuracy obtained with an R2 value of 85.65011% and an MSE value of 161606.1.
PENGGUNAAN SELEKSI FITUR CHI-SQUARE DAN ALGORITMA MULTINOMIAL NAÏVE BAYES UNTUK ANALISIS SENTIMEN PELANGGGAN TOKOPEDIA Tri Ernayanti; Mustafid Mustafid; Agus Rusgiyono; Arief Rachman Hakim
Jurnal Gaussian Vol 11, No 4 (2022): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.11.4.562-571

Abstract

E-commerce is a medium for online shopping that is popular among the public. Ease of access for all internet users and the completeness of products offered by e-commerce are new alternatives in meeting the needs of the community. This causes stiff competition in the e-commerce, so e-commerce need to carry out the right marketing strategy in order to compete in obtaining, retaining, and partnering with customers, one of which is by reviewing aspects of customer satisfaction. Tokopedia is an e-commerce buying and selling online that connects sellers and buyers throughout Indonesia for free. In this study, an analysis of Tokopedia's customer sentiment was carried out with the Multinomial Naïve Bayes classification. Algorithm Multinomial Nave Bayes is a model development of the Nave Bayes. The difference lies in the selection of data, if Naïve Bayes uses a Gaussian that is suitable for continue, while Multinomial Naïve Bayes is suitable for discrete data such as the number of words in a document. Multinomial Naïve Bayes is the simplest method of probability classification but is sensitive to feature selection, so the amount of data is determined by the results of Chi-Square.Multinomial Naïve Bayes is used to classify customer opinions that are positive and negative so that they can form customer satisfaction factors Tokopedia, while the Chi-Square used to measure the level of feature dependence with class (positive and negative) so as to eliminate disturbing features in the classification process. Classification performance results using Multinomial Naïve Bayes without Chi-Square obtained accuracy and kappa statistics of 88% and 75.95%, while using Chi-Square obtained accuracy and kappa statistics of 95% and 89.99%, respectively. This means that Multinomial Naïve Bayes has quite effective performance and results in analyzing Tokopedia customer satisfaction sentiment and the use of Chi-Square for feature selection can improve the accuracy of the classification process. 
PERBANDINGAN MODEL ARIMA DENGAN MODEL NONPARAMETRIK POLINOMIAL LOKAL DAN SPLINE TRUNCATED UNTUK PERAMALAN HARGA MINYAK MENTAH WEST TEXAS INTERMEDIATE (WTI) DILENGKAPI GUI R Salsabila Rizkia Gusman; Suparti Suparti; Agus Rusgiyono
Jurnal Gaussian Vol 12, No 1 (2023): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.12.1.20-29

Abstract

Crude oil as one of the most important natural resources experiences price fluctuations from time to time, even the spot price of West Texas Intermediate (WTI) world crude oil on 20th April 2020 reached -36,98 USD/barrel due to the Covid-19 pandemic. WTI oil price data was modeled using the ARIMA method, local polynomial, and spline truncated nonparametric regression then compared and obtained the best model and formed R Graphical User Interface (GUI). The ARIMA model and nonparametric time series models can be used to model time series data, but in the ARIMA model there are assumptions that must be fulfilled. Nonparametric time series models, which include local polynomial model and truncated spline do not need to fulfill these assumptions. The ARIMA model obtained did not fulfilled the assumptions of normality and residual homoscedasticity, so the modeling was stopped and modeling was only carried out using nonparametric regression methods. Based on the minimum MSE criteria, the best nonparametric model was obtained, namely nonparametric truncated spline model with degrees 3 and 3 knot points which was categorized as a strong model based on R-squared in sample value and having a very good forecasting ability based on MAPE out sample value.
GLUE VALUE AT RISK UNTUK MENGUKUR RISIKO PADA PORTOFOLIO OPTIMAL DENGAN METODE MULTI INDEX MODEL Nur Khofifah; Agus Rusgiyono; Di Asih I Maruddani
Jurnal Gaussian Vol 12, No 1 (2023): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.12.1.116-125

Abstract

Creating a portfolio is one method of reducing risk. One of the best portfolio decisions is made by Multi Index Model. Multi Index Model is a method that makes use of multiple variables that impact stock returns. Before making an investment, risk measurement must be considered. Calculation of risk on a portfolio will be more accurate if it is calculated using Glue Value at Risk, because it satisfies the property of subadditivity, which is one of the coherence properties of a risk measure that reflects the idea that risk can reduce by diversification. The stocks used in this study are 4 stocks that are members of SRI-KEHATI stock group in the period January 2017 – December 2021. The factors used are Composite Stock Price Index (JCI), and Rupiah to USD exchange rate. According to the study's findings, the best portfolio consist of four stocks: BBRI (Bank Rakyat Indonesia Tbk.) (17.82%), KLBF (Kalbe Farma Tbk.) (56.66%), UNTR (United Tractors Tbk.) (24.13%), and WIKA (Wijaya Karya Tbk.) (1.39%). The confidence levels of  and , the distortion function height is  and  are used, the GlueVaR value for the stock portfolio is 10.476%. 
K-NEAREST NEIGHBOR DENGAN ADAPTIVE BOOSTING DAN SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE UNTUK KLASIFIKASI DATA TIDAK SEIMBANG Ria Sulistyo Yuliani; Agus Rusgiyono; Rukun Santoso
Jurnal Gaussian Vol 12, No 2 (2023): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.12.2.231-241

Abstract

Breast cancer is non-skin cancer that is caused by several factors, including glandular ducts, cells, and breast support tissue, except for the skin of the breast. Breast cancer if not treated immediately will be fatal for the sufferer, so early detection of breast cancer is important for the patient's safety. The success of breast cancer detection depends on the right diagnosis. Measurement of the accuracy of a breast cancer diagnosis can be assisted by statistical methods, namely classification. K-Nearest Neighbor is a classification algorithm based on the nearest neighbor that is easy to implement. In the classification process, there are several problems including when faced with imbalanced data. Imbalanced data can cause classification algorithms to tend to focus on the majority class. Data imbalance can be overcome by using Synthetic Minority Oversampling Technique (SMOTE). Ensemble methods can be applied to improve the performance of imbalanced data classification, one of which is Adaptive Boosting. This study applies K-Nearest Neighbor combined with Adaptive Boosting and SMOTE for handling imbalanced data classification. The results of this study are, SMOTE can handle the problem of imbalanced data and the application of K-Nearest Neighbor with Adaptive Boosting can produce an accuracy of 80%, a sensitivity of 83,33%, a specificity of 66,67%, and a G-Mean value of 74,54%. So it can be concluded that K-Nearest Neighbor combined with Adaptive Boosting and SMOTE can be applied for handling imbalanced data classification. 
ANALISIS TINGKAT KEPENTINGAN DAN KINERJA (IMPORTANCE-PERFORMANCE ANALYSIS) NILAI KEGUNAAN APLIKASI M-COMMERCE Elyasa, Fatiya Rahmita; Sugito, Sugito; rusgiyono, agus
Jurnal Gaussian Vol 13, No 1 (2024): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.13.1.70-78

Abstract

Good application quality can bring user satisfaction to form user’s loyalty and trust in the company. The level of user satisfaction is different between Gojek and Grab even though each them has similarities in application features. Gojek and Grab are trying to make position as the most popular by the community in getting people's needs quickly and efficiently with huge competitive. This study aims to analyze and compare the usability qualities of Gojek and Grab based on the User Experience Questionnaire (UEQ) approach on the dimensions of attractiveness, perception, efficiency, dependability, stimulation and novelty. Measurements are made using Importance-Performance Analysis to graphically measure customer satisfaction so that service quality improvement priorities can be established. The data was collected by questionnaire to 32 selected respondents who accessed the Gojek and Grab applications in the Greater Jakarta area in August-December 2022. Based on the results of the study, the position of the usability quality attributes in Gojek and Grab was visually almost the same for each IPA quadrant. The Gojek application is superior in 5 dimensions to Grab, in terms of attractiveness, perception, dependability, stimulation, and novelty. Grab has one dimension that is superior to Gojek, in terms efficiency.
Co-Authors Abdul Hoyi Abdul Hoyyi Agustina Sunarwatiningsih Alan Prahutama Alan Prahutama Andreanto Andreanto Anggita, Esta Dewi Anifa Anifa Anindita Nur Safira ANNISA RAHMAWATI Annisa Rahmawati Arief Rachman Hakim Aulia Putri Andana Aulia Rahmatun Nisa Bagus Arya Saputra Bayu Heryadi Wicaksono Bellina Ayu Rinni Besya Salsabilla Azani Arif Bramaditya Swarasmaradhana Budi Warsito Dede Zumrohtuliyosi Dermawanti Dermawanti Desy Tresnowati Hardi Di Asih I Maruddani Diah Safitri Diah Safitri Dian Mariana L Manullang Dini Anggreani Diyah Rahayu Ningsih Dwi Asti Rakhmawati Dwi Ispriyansti Dwi Ispriyanti Eis Kartika Dewi Ely Fitria Rifkhatussa'diyah Elyasa, Fatiya Rahmita Enggar Nur Sasongko Etik Setyowati Etik Setyowati, Etik Farisiyah Fitriani fatimah Fatimah Febriana Sulistya Pratiwi Feby Kurniawati Heru Prabowo Fitriani Fitriani Hana Hayati Hanik Malikhatin Hanik Rosyidah, Hanik Hasbi Yasin Hasbi Yasin Hildawati Hildawati Hindun Habibatul Mubaroroh Ika Chandra Nurhayati Ilham Muhammad Imam Desla Siena Inas Husna Diarsih Iwan Ali Sofwan Kevin Togos Parningotan Marpaung Listifadah Listifadah M. Afif Amirillah M. Atma Adhyaksa Marthin Nosry Mooy Maryam Jamilah An Hasibuan Maulana Taufan Permana Merlia Yustiti Moch. Abdul Mukid Moch. Abdul Mukid Muhammad Rizki Muhammad Taufan Mustafid Mustafid Mustafid Mustafid Mustofa, Achmad Nabila Chairunnisa Nor Hamidah Noveda Mulya Wibowo Novie Eriska Aritonang Nur Khofifah Nur Walidaini Octafinnanda Ummu Fairuzdhiya Puji Retnowati Puspita Kartikasari Putri Fajar Utami Rengganis Purwakinanti Revaldo Mario Ria Sulistyo Yuliani Riana Ikadianti Riszki Bella Primasari Rita Rahmawati Rita Rahmawati Rizal Yunianto Ghofar Rizky Aditya Akbar Rosita Wahyuningtyas Rukun Santoso Salsabila Rizkia Gusman Setiyowati, Eka Shella Faiz Rohmana Siti Lis Ina Atul Hidayah Sudargo Sudarno Sudarno Sudarno Sudarno Sudarno Sudarno Sudarno Sudarno Sugito - Sugito Sugito Sugito Sugito Suparti Suparti Suparti Suparti Susi Ekawati sutimin sutimin Tarno Tarno Tarno Tarno Tarno Tarno Tatik Widiharih Tatik Widiharih Tiani Wahyu Utami Tika Dhiyani Mirawati Tika Nur Resa Utami, Tika Nur Resa Titis Nur Utami Tri Ernayanti Tri Yani Elisabeth Nababan Triastuti Wuryandari Triastuti Wuryandari Tyas Ayu Prasanti Tyas Estiningrum Ulfi Nur Alifah Ungu Siwi Maharunti Uswatun Hasanah Vierga Dea Margaretha Sinaga Viliyan Indaka Ardhi Winastiti, Lugas Putranti Yogi Isna Hartanto Yuciana Wilandari Yuciana Wilandari Yuciana Wilandari