http://commdis.telkomuniversity.ac.id/jdsa/index.php/jdsa/issue/feed Journal of Data Science and Its Applications 2019-07-18T03:11:21+00:00 Dr. Kemas Muslim L. jdsa@telkomuniversity.ac.id Open Journal Systems <p>Journal of Data Science and Its Applications (JDSA)</p> http://commdis.telkomuniversity.ac.id/jdsa/index.php/jdsa/article/view/18 Soccer Players Detection Using GDLS Optimization and Spatial Bitwise Operation Filter 2019-07-18T03:11:19+00:00 Adhi Dharma Wibawa wibawa.adhi@yahoo.co.id Atyanta Nika Rumaksari atyanta.rumaksari@uksw.edu <p>Advancement computer vision technology in order to help coach creates strategy has been affecting the sport industry evolving very fast. Players movement patterns and other important behavioral activities regarding the tactics during playing the game are the most important data obtained in applying computer vision in Sport Industry. The basic technique for extracting those information during the game is player detection. Three fundamental challenges of computer vision in detecting objects are random object’s movement, noise and shadow. Background subtraction is an object’s detection method that used widely for separating moving object as foreground and non moving object as background. This paper proposed a method for removing shadow and unwanted noise by improving traditional background subtraction technique. First, we employed GDLS algorithm to optimize background-foreground separation. Then, we did filter shadows and crumbs-like object pixels by applying digital spatial filter which is created from implementation of digital arithmetic algorithm (bitwise operation). Finally, our experimental result demonstrated that our algorithm outperform conventional background subtraction algorithms. The experiments result proposed method has obtained 80.5% of F1-score with average 20 objects were detected out of 24 objects.</p> 2019-04-12T00:00:00+00:00 ##submission.copyrightStatement## http://commdis.telkomuniversity.ac.id/jdsa/index.php/jdsa/article/view/15 Geo-additive Models in Small Area Estimation of Poverty 2019-07-18T03:11:20+00:00 Novi Hidayat Pusponegoro novie@stis.ac.id Anik Djuraidah anikdjuraidah@gmail.com Anwar Fitrianto anwarstat@gmail.com I Made Sumertajaya imsjaya@gmail.com <p>Spatial data contains of observation and region information, it can describe spatial patterns such as disease distribution, reproductive outcome and poverty. The main flaw in direct estimation especially in poverty research is the sample adequacy fulfilment otherwise it will produce large estimate parameter variant. The Small Area Estimation (SAE) developed to handle that flaw. Since, the small area estimation techniques require “borrow strength” across the neighbor areas thus SAE was developed by integrating spatial information into the model, named as Spatial SAE. SAE and spatial SAE model require the fulfilment of covariate linearity assumption as well as the normality of the response distribution that is sometimes violated, and the geo-additive model offers to handle that violation using the smoothing function. Therefore, the purpose of this paper is to compare the SAE, Spatial SAE and Geo-additive model in order to estimate at sub-district level mean of per capita income of each area using the poverty survey data in Bangka Belitung province at 2017 by Polytechnic of Statistics STIS. The findings of the paper are the Geo-additive is the best fit model based on AIC, and spatial information don't influence the estimation in SAE and spatial SAE model since they have the similar estimation performance.</p> 2019-04-12T00:00:00+00:00 ##submission.copyrightStatement## http://commdis.telkomuniversity.ac.id/jdsa/index.php/jdsa/article/view/19 Analysis Characteristics of Car Sales In E-Commerce Data Using Clustering Model 2019-07-18T03:11:18+00:00 Puspita Kencana Sari puspitakencana@telkomuniversity.ac.id Adelia Purwadinata adel.haztika@gmail.com <p>The&nbsp;number&nbsp;of&nbsp;car&nbsp;sales&nbsp;in&nbsp;e-commerce&nbsp;is&nbsp;currently&nbsp;increase&nbsp;along&nbsp;with&nbsp;the&nbsp;increasing&nbsp;use&nbsp;of&nbsp;the&nbsp;Internet&nbsp;in&nbsp;Indonesia.&nbsp;Purchases&nbsp;of&nbsp;Car&nbsp;in&nbsp;Indonesia&nbsp;are&nbsp;currently&nbsp;get&nbsp;higher,&nbsp;especially&nbsp;in&nbsp;used&nbsp;cars,&nbsp;which&nbsp;are&nbsp;a&nbsp;necessity&nbsp;for&nbsp;the&nbsp;community&nbsp;based&nbsp;on&nbsp;the&nbsp;odd-even&nbsp;system&nbsp;of&nbsp;car&nbsp;traffic&nbsp;policies&nbsp;currently&nbsp;applied&nbsp;in&nbsp;Jakarta.&nbsp;This&nbsp;research&nbsp;aims&nbsp;to&nbsp;study&nbsp;characteristics&nbsp;of&nbsp;clusters&nbsp;formed&nbsp;in&nbsp;e-commerce&nbsp;site&nbsp;to&nbsp;predict&nbsp;how&nbsp;are&nbsp;the&nbsp;car&nbsp;sales&nbsp;segmentation.&nbsp;Data&nbsp;is&nbsp;collected&nbsp;from&nbsp;big-two&nbsp;e-commerce&nbsp;site&nbsp;about&nbsp;car&nbsp;selling&nbsp;and&nbsp;buying&nbsp;in&nbsp;Indonesia.&nbsp;Clustering&nbsp;model&nbsp;is&nbsp;build&nbsp;using&nbsp;K-Means&nbsp;method&nbsp;and&nbsp;Davies&nbsp;Bouldin&nbsp;Index&nbsp;as&nbsp;evaluation&nbsp;of&nbsp;the&nbsp;clusters&nbsp;formed.&nbsp;The&nbsp;results&nbsp;show&nbsp;for&nbsp;both&nbsp;clusters,&nbsp;the&nbsp;first&nbsp;cluster&nbsp;has&nbsp;characteristic&nbsp;lowers&nbsp;sale&nbsp;price&nbsp;and&nbsp;older&nbsp;production&nbsp;year.&nbsp;The&nbsp;second&nbsp;cluster&nbsp;has&nbsp;higher&nbsp;price&nbsp;with&nbsp;latest&nbsp;production.&nbsp;From&nbsp;the&nbsp;model&nbsp;performance,&nbsp;evaluation&nbsp;from&nbsp;Davies&nbsp;Bouldin&nbsp;Index&nbsp;&nbsp;is&nbsp;quite&nbsp;good&nbsp;for&nbsp;both&nbsp;models.</p> <p><strong>Keywords&nbsp;</strong>:&nbsp;Big&nbsp;Data,&nbsp;Clustering,&nbsp;K-Means,&nbsp;E-Commerce</p> 2019-04-12T00:00:00+00:00 ##submission.copyrightStatement## http://commdis.telkomuniversity.ac.id/jdsa/index.php/jdsa/article/view/12 Classification of Electrocardiogram Signals using Principal Component Analysis and Levenberg Marquardt Backpropagation for Detection Ventricular Tachyarrhythmia 2019-07-18T03:11:21+00:00 Astrima Manik astrimamanik01@gmail.com Adiwijaya Adiwijaya adiwijaya@telkomuniversity.ac.id Dody Qori Utama dodyqori@telkomuniversity.ac.id <p><strong>Abstract</strong></p> <p>Ventricular Tachyarrhythmia (VT) are the primary arrhythmias which are cause of sudden death. For someone who already has symptoms of VT should immediately perform an examination of one of them by using an electrocardiogram (ECG). An electrocardiogram is a recording of the heart's electrical results in a waveform. However, limited ability in analysis and diagnosis of ECG reading is still difficult to do. Therefore, the classification of ECG signals is needed to detect a person, especially those with VT or not. In this research focuses on the classification of VT heartbeats from ECG signals by using median filter method in preprocessing, Principal Component Analysis (PCA) as feature extraction and modified Backpropagation (MBP) as classification. This research used machine learning method that is a neural network with backpropagation modification that is Levenberg Marquardt to speed up network training process. The best VT detection performance results were based on the average accuracy of the overall scheme of 91.67% with the best parameters that principal component=10 and 20, hidden neuron=4, and µ value=0.001 as well training time 1 seconds with a comparison of train data and test data that is 80:20 percent.</p> <p><strong>Keywords: </strong>Electrocardiogram, Levenberg Marquardt Backpropagation, Median filter, Principal Component Analysis, and Ventricular Tachyarrhythmia</p> 2019-04-12T00:00:00+00:00 ##submission.copyrightStatement## http://commdis.telkomuniversity.ac.id/jdsa/index.php/jdsa/article/view/20 Sentiment Analysis of Cyberbullying on Instagram User Comments 2019-07-18T03:11:17+00:00 Muhammad Zidny Naf'an zidny@ittelkom-pwt.ac.id Alhamda Adisoka Bimantara 15102007@st3telkom.ac.id Afiatari Larasati 15102083@st3telkom.ac.id Ezar Mega Risondang 15102016@st3telkom.ac.id Novanda Alim Setya Nugraha novanda@ittelkom-pwt.ac.id <p>Instagram is a social media for sharing images, photos and videos. Instagram has many active users from various circles. In addition to sharing submissions, Instagram users can also give likes and comments to other users' posts. However, the comment feature is often misused, for example it is used for cyberbullying which includes one act against the law. But until now, Instagram still does not provide a feature to detect cyberbullying. Therefore, this study aims to create a system that can classify comments whether they contain elements of cyberbullying or not. The results of the classification will be used to detect cyberbullying comments. The algorithm used for classification is Naïve Bayes Classifier. Then for each comment will pass the preprocessing and feature extraction stages with the TF-IDF method. For evaluation and testing using the K-Fold Cross Validation method. The experiment is divided into two, namely using stemming and without stemming. The training data used is 455 data. The best experimental results obtained an accuracy of 84% both with stemming, and without stemming.</p> 2019-04-12T00:00:00+00:00 ##submission.copyrightStatement##