Article Per Year (5 Year)
p-Index From 2020 - 2025
3.748
P-Index
This Author published in this journals
All Journal Media Statistika Jurnal Gaussian Jurnal Statistika Universitas Muhammadiyah Semarang
Tatik Widiharih
Departemen Statistika, Fakultas Sains Dan Matematika, Universitas Diponegoro
Decision Sciences, Operations Research & Management Other

Published : 42 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 42 Documents
Search

 1   2   3   4   5 
Perancangan Multidimensional Scalling Metrik dengan GUI PYTHON 3.8 untuk Klasifikasi Program Keluarga Berencana Bramesa Winanda Nugraha; Tatik Widiharih; Puspita Kartikasari
Jurnal Statistika Universitas Muhammadiyah Semarang Vol 8, No 2 (2020): Jurnal Statistika Universitas Muhammadiyah Semarang
Publisher : Department Statistics, Faculty Mathematics and Natural Science, UNIMUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jsunimus.8.2.2020.114-120

Abstract

Program KB (Keluarga Berencana) merupakan suatu bentuk upaya yang dilakukan oleh pemerintah untuk mengendalikan banyaknya kuota penduduk. Program KB selalu dikaitkan dengan alat kontrasepsi sebagai kendaraan untuk menyukseskan program tersebut. Metode kontrasepsi dibagi menjadi dua yaitu jangka panjang (MKJP) yang meliputi Intra Uterine Device, Implan, Metode Operasi Wanita dan Metode Operasi Pria dan jangka pendek (Non MKJP) yang meliputi Suntik, Kondom, dan Pil. Penelitian ini bertujuan untuk memetakan Kabupaten/Kota di Jawa Tengah berdasarkan metode kontrasepsi yang digunakan oleh peserta KB dalam dua dimensi. Metode pemetaan yang digunakan adalah Multidimensional Scaling Metrik dengan membangun suatu program berbasis Graphical User Interface (GUI) Python. Hasil penelitian ini memvisualisasikan karakteristik dari peserta KB pada Kabupaten/Kota berdasarkan jenis dan metode kontrasepsi yang digunakan. Pada kuadran I memiliki karakteristik penggunaan Non MKJP. Kuadran II memiliki karakteristik penggunaan PIL. Kuadran III merupakan kelompok dengan tingkat penggunaan kontrasepsi yang rendah baik MKJP maupun Non MKJP. Kuadran IV memiliki karakteristik penggunaan IUD. Dengan kriteria perceptual map yang dihasilkan sempurna, ditunjukan oleh nilai stress sebesar 0.4%.
ANALISIS SENTIMEN PT TIKI JALUR NUGRAHA EKAKURIR (PT TIKI JNE) PADA MEDIA SOSIAL TWITTER MENGGUNAKAN MODEL FEED FORWARD NEURAL NETWORK Salma Farah Aliyah; Hasbi Yasin; Suparti Suparti; Budi Warsito; Tatik Widiharih
Jurnal Statistika Universitas Muhammadiyah Semarang Vol 8, No 2 (2020): Jurnal Statistika Universitas Muhammadiyah Semarang
Publisher : Department Statistics, Faculty Mathematics and Natural Science, UNIMUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26714/jsunimus.8.2.2020.103-113

Abstract

In the 2000s until now, e-commerce systems have continued to develop throughout the world and even in Indonesia. PT Tiki Jalur Nugraha Ekakurir (PT Tiki JNE) is a freight forwarding company that provides convenience for the public in carrying out online shopping activities, and shipping other goods. The large volume of shipments makes PT Tiki JNE have several problems in service that have led to several kinds of responses from users. Sentiment analysis on Twitter social media can be an option to see how PT Tiki JNE’s users respond to services that have been provided. These responses are classified into positive sentiments and negative sentiments. In this research data processing is performed using text mining as the initial source of numerical data from document data which will later be classified using the Artificial Neural Network model with the Resilient Backpropagation algorithm. Data labeling is done manually and sentiment scoring. The test results show that the best model obtained is FFNN 867-7-1 by using the evaluation model 10-Fold Cross Validation to get an overall accuracy performance of 80.27%, kappa accuracy of 39.13%, precision of 69.04%, recall of 70.56%, and f-measure of 69.8% which can be interpreted that the model used is quite good. Analysis of the results using wordcloud shows the tendency of opinion sentiment categories depending on the words used in the tweet.
PEMODELAN REGRESI HURDLE POISSON DALAM MENGATASI EXCESS ZEROS UNTUK KASUS PENYAKIT TETANUS NEONATORUM PADA NEONATAL DI JAWA TIMUR Cylvia Evasari Margaretha; Dwi Ispriyanti; Tatik Widiharih
Jurnal Gaussian Vol 8, No 3 (2019): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (747.686 KB) | DOI: 10.14710/j.gauss.v8i3.26683

Abstract

Tetanus Neonatorum is one of the infectious diseases that occur in newborns caused by Clostridium Tetani bacteria through cuts or scratches. The number of Tetanus Neonatorum cases in East Java Province in 2017 is discrete data Poisson distribution with a proportion of zero value of 73,7 percent. The amount of zero value data can result in overdispersion where the variance is greater than the mean. To overcome this problem, Hurdle Poisson regression model is a solution. To estimation of regression parameters for Hurdle Poisson regression is using the Maximum Likelihood Estimation (MLE) method and Broyden Fletcher Goldfarb Shanno (BFGS) iteration. Hurdle Poisson regression produces predictor variables that affect the number of Tetanus Neonatorum cases in East Java Province in the logit model are the percentage of pregnant women administered the K4 program, population density per  and in the truncated Poisson model are the percentage of labor assisted by health workers the percentage of pregnant women administered the K4 program, population density per  with the Akaike Information Criterion (AIC) value of 78,422.Keywords: Tetanus Neonatorum, Excess Zeros, Overdispersion, Hurdle Poisson Regression
PENGELOMPOKAN TITIK GEMPA DI PULAU SULAWESI MENGGUNAKAN ALGORITMA ST-DBSCAN (Spatio Temporal-Density Based Spatial Clustering Application with Noise) Denny Jales Manalu; Rita Rahmawati; Tatik Widiharih
Jurnal Gaussian Vol 10, No 4 (2021): 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.v10i4.29499

Abstract

Earthquake is a natural disaster which is quite serious in Indonesia, especially on Sulawesi Island. Earthquake is fearful because it can’t be predicted when it will come, where it will come, and how strong the vibration, that often causes fatal damage and casualties. In effort to minimize losses caused by earthquake, it is necessary to divide areas which are easily affected by earthquake. One of the methods that can be used in dividing the area is by using the clustering technique. This research by using a clustering method with the ST-DBSCAN (Spatial Temporal-Density Based Spatial Clustering Application with Noise) algorithm on dataset of earthquake points in Sulawesi Island in 2019. This method by using the spatial distance parameters (Eps1 = 0.45), the temporal distance parameters (Eps2 = 7), and minimum number of cluster members (MinPts = 4), resulting in a total of 60 clusters with 8 large clusters and 216 noises 
PREDIKSI HARGA EMAS MENGGUNAKAN FEED FORWARD NEURAL NETWORK DENGAN METODE EXTREME LEARNING MACHINE Nisa Afida Izati; Budi Warsito; Tatik Widiharih
Jurnal Gaussian Vol 8, No 2 (2019): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1250.218 KB) | DOI: 10.14710/j.gauss.v8i2.26641

Abstract

The prediction of gold price aims to find out the gold price in the future on the basis of historical data on gold prices in the past, so it can be used as a consideration by gold investors to investing in gold. Prediction methods that do not require assumptions, one of which is Artificial Neural Networks. In this study, using Artificial Neural Networks, Feed Forward Neural Network with Extreme Learning Machine (ELM). ELM is a non-iterative algorithm so ELM has advantages in process speed. The input weight and bias for this method are determined randomly. After that, to find the final weight using the Moore-Penrose Generalized Inverse calculation on the hidden layer output matrix. The best model selection criteria uses the Mean Absolute Percentage Error (MAPE). This study shows that the results of the training and testing process from the model 1 input neuron and 7 hidden neurons are very good, because it produces MAPE training = 0.6752% and MAPE testing = 0.8065%. Also gives a very good prediction result because it has MAPE = 0.5499% Keywords: gold price, Extreme Learning Machine, MAPE
PENERAPAN METODE GENERALIZED STRUCTURED COMPONENT ANALYSIS PADA KEPUASAN KONSUMEN (Studi Kasus: Pasien Klinik Q) Farisiyah Fitriani; Agus Rusgiyono; Tatik Widiharih
Jurnal Gaussian Vol 9, No 4 (2020): 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.v9i4.29416

Abstract

Customer satisfaction is used by a company to evaluate products or services whether it is sufficient with customer’s expectations. Satisfaction is influenced by factors that cannot be measured directly are called latent variables and can be measured through indicators used to measure satisfaction with Structural Equation Modeling (SEM). Generalized Structured Component Analysis (GSCA) method is part of a SEM based on a variant that does not require the assumption of a multivariate normal distribution and has a measure overall goodness of fit. The parameters used are factor loading, coefficients parameter, and weight of indicators and estimated with alternating least square. The type of data used primary data from the results of the questionnaire with stratified proportional random sampling and number of samples 286. This research using indicators as measurable variables as many 32 indicators and 8 latent variable. Considering to the evaluation of the structural model, it is found there are 5 variables that influence satisfaction, they are prices, quality yield, cleanliness, doctor's services, and employee services with a large influence of 77.18% and the impact of satisfaction on loyalty is 48.63 %. For the overall goodness of fit measure, it is known that the FIT value is 63.75% and the adjusted FIT (AFIT) value is 63.47%. The goodness of fit (GFI) produced the value in the amount of 96.43%, indicating that the general model has the good level of compatibility.Keywords: Generalized Structured Component Analysis, Structural Equation Modeling, Overall goodness of fit, Alternating Least Square, Stratified Proportional Random Sampling
PEMODELAN VOLATILITAS RETURN PORTOFOLIO SAHAM MENGGUNAKAN FEED FORWARD NERURAL NETWORK (Studi Kasus :PT Bumi Serpong Damai Tbk. Dan PT H.M Sampoerna Tbk.) Rizki Pradipto Widyantomo; Abdul Hoyyi; Tatik Widiharih
Jurnal Gaussian Vol 7, No 2 (2018): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (660.038 KB) | DOI: 10.14710/j.gauss.v7i2.26654

Abstract

Time series analysis is an analysis used to predict a time-observed data, one of which is the ARIMA model. ARIMA model assumes a constant residual variance (homogeneous). While financial data usually produce ARIMA model with variance error that is not constant. If the assumption of homogeneity of the residual variance is not met, then the method that can be used is ARCH or GARCH model. Another method that can be used on the data assuming the homogeneity of the variance error is not met is the Neural Network model. In this model we use Neural Network model with variance and residual as the input variables that obtained from ARCH / GARCH model. The data used are BSDE and HMSP asset portfolio returns from November 14, 2016 to January 18, 2018. In this study the selected input variables are from ARIMA (1.0.1) GARCH (1,1) model. The best Neural Network model obtained is Neural Network model with 10 hidden layers with MSE value 6.58 x10-10 with model train evaluation which is MAPE value 1.14441%.Keywords: Time series Analysis, ARCH / GARCH, Neural Network, Return.
KETAHANAN HIDUP PASIEN GAGAL GINJAL DENGAN METODE KAPLAN MEIER (Studi Kasus di Rumah Sakit Umum Daerah dr. R. Soedjati Soemodiarjo Purwodadi) Immawati Ainun Habibah; Tatik Widiharih; Suparti Suparti
Jurnal Gaussian Vol 7, No 3 (2018): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (301.083 KB) | DOI: 10.14710/j.gauss.v7i3.26660

Abstract

Chronic Kidney Disease (CKD) is a failure of kidney function that which get slowly and can not recover. Most of the patients CKD get death sudden becuse of cardiovascular complications (related to the heart and blood vessels) however only minor part can reach terminal phase (CKD stage 5) which need replacement therapy of Kidney. Replacement therapy of Kidney are hemodialysis, peritoneal dialysis, and Kidney transplant. Because of that, the importance to study how long the patient opportunity is life endurance analysis.  Survival analysis methods to life depend from the life time and status of individual life time. Survival analysis uses Kaplan-Meier method. During the observation process, there is different observations so censor type III is choosen. Censor type III is censoring type which research is done to individual in and out for determine time, because of that estimation value of survival can be caunted using Kaplan Meier method with censor type III. This research uses medical records data from the patients with kidney failure period 1 January 2014 until 30 November 2017 in RSUD dr.R. Soedjati Soemodiarjo Purwodadi Grobogan Regency. The results of the analysis and discussion are known that if hemodialysis getting longer done, estimation value of survival. With an average estimate of survival is 776 days. Keywords: Chronic Kidney Disease, Survival Analysis, Kaplan Meier
PERAMALAN MENGGUNAKAN METODE WEIGHTED FUZZY INTEGRATED TIME SERIES (Studi Kasus: Harga Beras di Indonesia Bulan Januari 2011 s/d Desember 2017) Setya Adi Rahmawan; Diah Safitri; Tatik Widiharih
Jurnal Gaussian Vol 8, No 4 (2019): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (813.883 KB) | DOI: 10.14710/j.gauss.v8i4.26752

Abstract

Fuzzy Time Series (FTS) is a time series data forecasting technique that uses fuzzy theory concepts. Forecasting systems using FTS are useful for capturing patterns of past data and then to using it to produce information in the future. Initially in the FTS each pattern of relations formed was considered to have the same weight besides using only the first order. In its development the Weighted Fuzzy Integrated Time Series (WFITS) which gave a difference in the weight of each relation and high order usage has been appeared. Measuring the accuracy of forecasting results is used the value of Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). In this study both the first-order and high-order WFITS methods were applied to forecast rice prices in Indonesia based on data from January 2011 to December 2017. In this regard, the results of the analysis obtained data forecasting using Lee's high-order model WFITS algorithm (1,2,3) giving the value of RMSE and MAPE on the data testing in a row as many as 69,898 and 0.47% while for the RMSE and MAPE on the training data is as many as 70.4039 and 0.54%. Keywords: Fuzzy Time Series, Weighted Fuzzy Integrated Time Series, RMSE, MAPE, High-Order, Rice Prices
PERBANDINGAN METODE SMOTE RANDOM FOREST DAN SMOTE XGBOOST UNTUK KLASIFIKASI TINGKAT PENYAKIT HEPATITIS C PADA IMBALANCE CLASS DATA Muhamad Syukron; Rukun Santoso; Tatik Widiharih
Jurnal Gaussian Vol 9, No 3 (2020): 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.v9i3.28915

Abstract

Hepatitis causes around 1.4 million people die every year. This number makes hepatitis to be the largest contagious disease in the number of deaths after tuberculosis. Liver biopsy is still the best method for diagnosing the stage of hepatitis C, but this method is an invasive, painful, expensive, and can cause complications. Non-invasively method needs to be developed, one of non-invasif method is machine learning. Random Forest and XGboost are classification methods that are often used, since they have many advantages over classical classification methods. The SMOTE algorithm can be used to improve the accuracy of predictions from imbalanced data. the data in this study have 24 independent variables in the form of patients self-data, hepatitis C symptoms, and laboratory test results. The dependent variable in this study is a binary category, namely the level of hepatitis C disease (fibrosis and cirrhosis). The results showed that the random forest and XGboost had an accuracy of around 74% but the recall value was less than 2%. SMOTE random forest dan SMOTE XGboost have an accuracy & recall value more than 75%. SMOTE random forest has a higher accuracy for predicting fibrosis class while SMOTE XGboost is better in cirrhosis class. Variables that are more influental in determining hepatitis C stage are variables from laboratory test. Keyword : Fibrosis, Cirrhosis, Random Forest, SMOTE, XGboost
Co-Authors Abdiyasti Nurul Arifa Abdul Hoyyi Ade Irma Pramudita Agus Rusgiyono Amalina Sari Dewi Anestasya Nur Azizah Arief Rachman Hakim Aulia Resti Bramesa Winanda Nugraha Budi Warsito Chalimatus Sa'diah Cylvia Evasari Margaretha Delsy Nurutsaniyah Denny Jales Manalu Dheanisa Widyanti Di Asih I Maruddani Diah Aliyatus Saidah Diah Safitri Dilla Retno Deswita Dinda Virrliana Ramadhanti Dwi Ispriyanti Eka Lestari Farisiyah Fitriani Fath Ezzati Kavabilla Fithroh Oktavi Awalullaili Genisia Pramestiloka Aulia Ghina Nabila Saputro Putri Gunardi . Hasbi Yasin Immawati Ainun Habibah Irma Dwi Tyana Isna Wulandari Iut Tri Utami Moch. Abdul Mukid Muhamad Syukron Mustafid Mustafid Nesari Nesari Nisa Afida Izati Puspita Ayu Utami Puspita Kartikasari Qorina Rara Sartika Rita Rahmawati Rizki Pradipto Widyantomo Rukun Santoso Ryan Anugrah Salma Farah Aliyah Salma Innassuraiya Sensiani Sensiani Setya Adi Rahmawan Silvy ‘Aina Salsabila Sintia Rizki Aprilianti Sisca Indah Pratiwi Sri Haryatmi sudarno sudarno Sudarno Sudarno Sugito Sugito Suparti Suparti Syavhana Yusricha Zuhri Putri Tita Aulia Edi Putri Winahyu Handayani