Claim Missing Document
Check
Articles

Found 19 Documents
Search

Statistical Inference for Modeling Neural Network in Multivariate Time Series Urwatul Wutsqa, Dhoriva; Subanar, Subanar; Guritno, Suryo; Soejoeti, Zanzawi
Jurnal ILMU DASAR Vol 9 No 1 (2008)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (136.781 KB)

Abstract

We present a statistical procedure based on hypothesis test to build neural networks model in multivariate time series case. The method involved strategies for specifying the number of hidden units and the input variables in the model using inference of R2 increment. We draw on forward approach starting from empty model to gain the optimal neural networks model. The empirical study was employed relied on simulation data to examine the effectiveness of inference procedure. The result showed that the statistical inference could be applied successfully for modeling neural networks in multivariate time series analysis.
Probit Model on Multivariate Binary Response Using Simulated Maximum Likelihood Estimator Nugraha, Jaka; Guritno, suryo; Haryatmi, Sri
Jurnal ILMU DASAR Vol 11 No 1 (2010)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (114.339 KB)

Abstract

In this paper, we discuss probit model on multivariate binary response. We assume that each of n individuals is observed in T responses. Yit is tth response on ith individual/subject and each response is binary. Each subject has covariate Xi (individual characteristic) and covariate Zijt (characteristic of alternative j). Response on individual ith can be represented by Yi = (Yi1,....,YiT), Yit is tth response on ith individual/subject and each response is multinomial. In order to simplify, we choose one of individual characteristics and alternative characteristics. We use simulated maximum likelihood estimator (SMLE) methods to estimate the parameter based on Geweke-Hajivassiliou-Keane (GHK) simulator. We find the first derivative of likelihood function for multivariate binary probit. Then, we expand to multivariate multinomial response. The first derivative is used in the BHHH (Berndt, Hall, Hall, Hausman) iteration to obtain estimators. 
Visualization of Iris Data Using Principal Component Analysis and Kernel Principal Component Analysis Djakaria, Ismail; Guritno, suryo; Kartiko, Sri Haryatmi
Jurnal ILMU DASAR Vol 11 No 1 (2010)
Publisher : Fakultas Matematika dan Ilmu Pengetahuan Alam Universitas Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (358.886 KB)

Abstract

Principal component analysis (PCA) is a method used to reduce dimentionality of the dataset. However, the use of PCA failed to carry out the problem of non-linear and non-separable data. To overcome this problem such data is more appropriate to use PCA method with the kernel function, which is known as the kernel PCA (KPCA). In this paper, Iris dataset visualized with PCA and KPCA, that contains are the length and the width of sepal and petal. 
Fuzzy Simple Additive Weighting Untuk Diagnosis Penyakit Pneumonia Syaukani, Muhammad; Guritno, Suryo
Jurnal Buana Informatika Vol 4, No 1 (2013): Jurnal Buana Informatika Volume 4 Nomor 1 Januari 2013
Publisher : Universitas Atma Jaya Yogyakarta

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

Abstract

Abstract. Pneumonia is an infection of the lungs that is caused by bacteria, viruses, fungi, or parasites. It is characterized primarily by inflammation of the alveoli in the lungs or by alveoli that are filled with fluid (alveoli are microscopic sacs in the lungs that absorb oxygen). The shortage of medical personnel at health community centers to serve a population often results in care delays for pneumonia patients. The purpose of this research is to make a modelling of group decision support system in diagnosing pneumonia in adult patients. The system is designed as a tool for medical personnel in diagnosing pneumonia patients.Group Decision Support System (GDSS) is developed by using Fuzzy Simple Additive weighting methods. The preference scoring of three experts i.e. a pulmonary specialist, an internist and a pharmacist is carried out by applying triangular fuzzy numbers. In the aggregation stage, preferences makes use of Fuzzy Linguistic quantifier, stage rangking employs Simple Additive Weighting while Forward Chaining is employed in the inference process. The system is tested by inputting the symptoms of pneumonia without the involvement of an expert. The results shows that the system is capable in diagnosing pneumonia.Keywords: GDSS, Fuzzy, Simple Additive Weighting, Pneumonia Abstrak. Pneumonia adalah infeksi paru-paru yang disebabkan oleh bakteri, virus, jamur, atau parasit. Hal ini ditandai terutama oleh peradangan alveoli di paru-paru atau alveoli yang berisi cairan (alveoli adalah kantung mikroskopis di paru-paru yang menyerap oksigen), terbatasnya tenaga medis di puskesmas disbanding dengan jumlah penduduk berakibat sering terlambatnya pelayanan terhadap pasien pneumonia. Tujuan penelitian ini adalah membuat pemodelan sistem pendukung keputusan kelompok untuk mendiagnosis pasien pneumonia pada orang dewasa. Sistem ini dirancang sebagai alat bantu tenaga medis dalam mendiagnosis pasien pneumonia. Sistem Pendukung Keputusan Kelompok (SPKK) dikembangkan menggunakan metode Fuzzy Simple Additive Weighting. Pemberian nilai preferensi tiga orang pakar antara lain ahli paru-paru, ahli internis dan ahli farmasi menggunakan bilangan fuzzy segitiga. Pada tahap agregasi preferensi digunakan Fuzzy Linguistic Quantifier, tahap perangkingan menggunakan Simple Additive Weighting dan proses inferensi menggunakan Forward Chaining. Sistem diuji dengan cara memasukkan gejala-gejala pneumonia tanpa melibatkan seorang pakar. Hasil penelitian menunjukkan bahwa sistem dapat mendiagnosis penyakit pneumonia.Kata Kunci: SPKK, Fuzzy, Simple Additive Weighting, Pneumonia
Statistical Significance Test for Neural Network Classification Rezeki, Sri; Subanar, Subanar; Guritno, Suryo
Jurnal Natur Indonesia Vol 11, No 1 (2008)
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (102.606 KB) | DOI: 10.31258/jnat.11.1.64-69

Abstract

Model selection in neural networks can be guided by statistical procedures, such as hypothesis tests, informationcriteria and cross validation. Taking a statistical perspective is especially important for nonparametric models likeneural networks, because the reason for applying them is the lack of knowledge about an adequate functionalform. Many researchers have developed model selection strategies for neural networks which are based onstatistical concepts. In this paper, we focused on the model evaluation by implementing statistical significancetest. We used Wald-test to evaluate the relevance of parameters in the networks for classification problem.Parameters with no significance influence on any of the network outputs have to be removed. In general, theresults show that Wald-test work properly to determine significance of each weight from the selected model. Anempirical study by using Iris data yields all parameters in the network are significance, except bias at the firstoutput neuron.
Asimtotik Model Multivariate Adaptive Regression Spline Otok, Bambang Widjanarko; Guritno, Suryo; Subanar, Subanar
Jurnal Natur Indonesia Vol 10, No 2 (2008)
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (153.379 KB) | DOI: 10.31258/jnat.10.2.112-119

Abstract

Parameter estimation in MARS model executed by minimizing penalized least-squarer (PLS). Through somerequirement, asymtotic estimator characteristic from MARS prediction model has been successfully proven. Theresearch result shows that GCV can work properly to determine the best model that applied on MARS model. Solar’s vehicles produce opacity that exceed the standard limit of emition quality which was adjusted in Kepmen LH No.35 Year 1993, as large as 88 percent from 408 percent. Applying years, cylinder volume, type of machine, andvehicle’s radius are the variables that influences the opacity.
Faktor-faktor yang Mempengaruhi Volume Perdagangan Saham Menggunakan Multivariate Adaptive Regression Splines Otok, Bambang Widjanarko; Guritno, Suryo; Subanar, .
Jurnal Widya Manajemen & Akuntansi Vol 6, No 3 (2006)
Publisher : Fakutas Ekonomi Unika Widya Mandala Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (0.036 KB)

Abstract

This research aims to know influence the Composite Index on price Share (IHSG), Right Issue, Dollar Rate and interest rate storey level of Singapore International Bonk Offered Rate (SIBOR) to on trading volume stock in Effect Exchange Surabaya. This matter ii- oftentimes studied with regression analysis, and at this article introduce approach which relative n"erly in oy regression analysis that is Multivariate Adaptive Regression Splines (MARS). Modet U)nS, a model selection of MARSwith metho'l of stepwise. Forward Stepwise conducted to get afunction with amount of maximum basis .function. To .fulfitl conception parsemony lsimple i modet) conducted by bachtard stepwise lhat is cho.sening yielded basis .function of forwaid srepwise by minimizing value of Ceneralized Cross Validation (GCn. Result of research show with approach of MARS, important variable in influencing volume commerce of share is Right Issue with importance storey level t00%o, price Index Share Aliance (IHSG) with importance storey tevet 38,986%, and Dollar Rate with importance storey level equal to 6,477%. Ll/hile a SIBOR not such an important variable in influencing commerce volume. Right Issue happened change of volume commerce o f share at value qf , = O i-t tOOOE+10 and t = 0.63000E+ll. The change have tendencl,g o up slrnlt,front | = 20024704 .r.re.s/ .s= 0. l1l000E+10 and have tendency go up incisively.fron t : 0.ttt000E+10 up to t : 0.63000E+I 1.
Mengatasi Penyimpangan Asumsi Normalitas pada Pemodelan Persamaan Struktural Menggunakan Bootstrap Otok, Bambang Widjanarko; Guritno, Suryo; Subanar, .; Haryatmi, Sri
Jurnal Widya Manajemen & Akuntansi Vol 7, No 2 (2007)
Publisher : Fakutas Ekonomi Unika Widya Mandala Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (4751.36 KB)

Abstract

All important assumption which must fulfill in Structural Equation Modelling (SEM) is data of continue and distribution multivariate normal. If do not fulfill will affect at result of analysis, that is failure in conducting convergence or yield the solving of inappropriate. One of the way of to overcome the mentioned is bootstrap method. So that this is research more focused in overcoming deviation of assumption of normality at SEM model with bootstrop method at case influence of commitment to performance through behavior. Or equally look for appropriate solution at data which below par with bootstrap method at case. Result of research, indicating that parameter coefficient of bootstrap can overcome deviation of assumption normality, yielding solution matching with data. Professional commitment have an effect on to behavioral and organizational commitment of activity. Wile organizational commitment have an effect on to behavior work and activity performance, behavioral and organizational commitment of activity represent variable having an effect on indirectly at professional commitment in influencing performance.
NON AUTOMATICALLY EXERCISED (NAE) EUROPEAN CAPPED CALL PRICING THEORY ., Subanar; Guritno, Suryo; S., Zanzawi; ., Abdurakhman
Journal of the Indonesian Mathematical Society Volume 13 Number 2 (October 2007)
Publisher : IndoMS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22342/jims.13.2.69.215-221

Abstract

The objective of this paper is to present a methodology for deriving Black Scholes formulae via a simple lognormal distribution approach and introduce European capped non automatically exercise (NAE) call option pricing theory. DOI : http://dx.doi.org/10.22342/jims.13.2.69.215-221
PEMODELAN B-SPLINE DAN MARS PADA NILAI UJIAN MASUK TERHADAP IPK MAHASISWA JURUSAN DISAIN KOMUNIKASI VISUAL UK. PETRA SURABAYA Budiantara, I Nyoman; Suryadi, Fredi; Otok, Bambang Widjanarko; Guritno, Suryo
Jurnal Teknik Industri Vol 8, No 1 (2006): JUNE 2006
Publisher : Institute of Research and Community Outreach - Petra Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (128.513 KB) | DOI: 10.9744/jti.8.1.pp. 1-13

Abstract

Regression analysis is constructed for capturing the influences of independent variables to dependent ones. It can be done by looking at the relationship between those variables. This task of approximating the mean function can be done essentially in two ways. The quiet often use parametric approach is to assume that the mean curve has some prespecified functional forms. Alternatively, nonparametric approach, .i.e., without reference to a specific form, is used when there is no information of the regression function form (Haerdle, 1990). Therefore nonparametric approach has more flexibilities than the parametric one. The aim of this research is to find the best fit model that captures relationship between admission test score to the GPA. This particular data was taken from the Department of Design Communication and Visual, Petra Christian University, Surabaya for year 1999. Those two approaches were used here. In the parametric approach, we use simple linear, quadric cubic regression, and in the nonparametric ones, we use B-Spline and Multivariate Adaptive Regression Splines (MARS). Overall, the best model was chosen based on the maximum determinant coefficient. However, for MARS, the best model was chosen based on the GCV, minimum MSE, maximum determinant coefficient. Abstract in Bahasa Indonesia : Analisa regresi digunakan untuk melihat pengaruh variabel independen terhadap variabel dependent dengan terlebih dulu melihat pola hubungan variabel tersebut. Hal ini dapat dilakukan dengan melalui dua pendekatan. Pendekatan yang paling umum dan seringkali digunakan adalah pendekatan parametrik. Pendekatan parametrik mengasumsikan bentuk model sudah ditentukan. Apabila tidak ada informasi apapun tentang bentuk dari fungsi regresi, maka pendekatan yang digunakan adalah pendekatan nonparametrik. (Haerdle, 1990). Karena pendekatan tidak tergantung pada asumsi bentuk kurva tertentu, sehingga memberikan fleksibelitas yang lebih besar. Tujuan penelitian ini adalah mendapatkan model terbaik mengenai nilai ujian masuk terhadap nilai IPK (Indek Prestasi Kumulatif) mahasiswa jurusan Disain Komunikasi Visual tahun 1999 di Universitas Kristen Petra Surabaya dengan analisis regresi, baik parametrik maupun nonparametrik. Pendekatan regresi parametrik menggunakan regresi linear sederhana, kuadratik dan kubik, sedangkan regresi nonparametrik digunakan B-Spline dan Multivariate Adaptive Regression Splines (MARS). Secara keseluruhan, model terbaik dipilih berdasarkan koefisien determinasi terbesar. Namun demikian untuk MARS, model terbaik dipilih berdasarkan pada GCV, minimum MSA dan koefisien determinasi terbesar. Kata kunci: regresi nonparametrik, B-Spline, MARS, koefisien determinasi.