Garuda - Garba Rujukan Digital

Question Classification Menggunakan Support Vector Machines dan Stemming Abdiansah Abdiansah Abdiansah; Edi Winarko
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2015
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Abstract—Question Classification (QC) merupakan salah satukomponen penting dalam Question Answering System (QAS)karena akan berpengaruh langsung terhadap kinerjakeseluruhan QAS. Sejauh ini metode yang disarankan olehkomunitas QAS untuk QC adalah menggunakan SupportVector Machines (SVM). Untuk melakukan klasifikasi teksdibutuhkan fitur berdimensi tinggi, banyaknya fitur dapatmengurangi performa SVM. Stemming adalah teknik yangdigunakan untuk mereduksi term suatu dokumen.Penggunaan stemming akan berpengaruh terhadap sintaksisdan semantik suatu pertanyaan. Penelitian ini bertujuan untukmengetahui pengaruh stemming terhadap akurasi SVM. Telahdilakukan dua percobaan klasifikasi pertanyaan, yaitu denganmenggunakan SVM dan SVM+stemming. Hasil rata-rataakurasi dari percobaan diperoleh sebesar 86.75% untuk SVMdan 87.48% SVM+stemming sehingga telah terjadi kenaikanakurasi sebesar 0.73%. Walaupun peningkatan akurasi tidaksignifikan tetapi stemming dapat mereduksi fitur tanpamenurunkan akurasi SVM.Keywords—question classification, question answering system,support vector machines, stemming

KAJIAN MODEL DAN PROTOTIPE SCHEMA MATCHING (Studi untuk Menemukan Peluang Pengembangan Model dan Prototipe Baru) Edhy Sutanta; Retantyo Wardoyo; Khabib Mustofa; Edi Winarko
Seminar Nasional Aplikasi Teknologi Informasi (SNATI) 2015
Publisher : Jurusan Teknik Informatika, Fakultas Teknologi Industri, Universitas Islam Indonesia

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

Abstract—Schema matching is critical problem within manyapplications to integration of data / information, to achieveinteroperability, and other cases caused by schematic heterogeneity.Models and the schema matching methods evolved from manualway on a specific domain, leading to a new models and methodsthat are semi-automatic and more general, so it is able to effectivelydirect the user within generate a mapping among elements of twothe schema or ontologies better. This paper is a summary ofliterature review on research and publication on models, methods,and prototypes on schema matching within the last 25 years todescribe the progress of and research opportunities on a newmodels, methods, and prototypes.Keywords—model, hybrid model, prototipe, schema matching

ZONASI DAERAH BAHAYA KEGEMPAAN DENGAN PENDEKATAN PEAK GROUND ACCELERATION (PGA) Edy Irwansyah; Edi Winarko
Seminar Nasional Informatika (SEMNASIF) Vol 1, No 5 (2012): Geoinformatic And GIS
Publisher : Jurusan Teknik Informatika

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

Penelitian ini bertujuan untuk menyusun zonasi daerah bahaya kegempaan pada infrastruktur bangunan di kota Banda Aceh menggunakan pendekatan nilai peak ground acceleration (PGA) dari fungsi atenuasi global dan lokal. PGA dihitung menggunakan fungsi antenuasi yang menggambarkan korelasi antara intensitas gerakan tanah setempat, magnitude gempa dan jarak dari sumber gempa. Data yang digunakan bersumber dari katalog gempa merusak badan meteorologi, klimatologi dan geofisika rentang tahun 1973 – 2011. Metode penelitian terdiri dari enam tahapan yaitu pembuatan grid, perhitungan jarak dari sumber gempa ke centroid grid, perhitungan nilai PGA, pengembangan aplikasi komputer, ploting nilai PGA di centroid grid, dan penyusunan zona bahaya kegempaan dengan algoritma kriging. Kesimpulan penelitian adalah bahwa fungsi atenuasi global yang dikembangkan oleh Youngs et al, 1997 dapat diaplikasikan dengan baik untuk menghitung nilai PGA di Kota Banda Aceh. Kota Banda Aceh secara mikro dapat dibagi dalam dalam tiga zona bahaya kegempaan yaitu zona bahaya kegempaan rendah dengan nilai PGA 0.8767 gals hingga 0.8780 gals, zona bahaya kegempaan menengah dengan nilai PGA 0.8781 gals hingga 0.8793 dan zona bahaya kegempaan tinggi dengan nilai PGA 0.8794 gals hingga 0.8806 gals

Design And Implementation of Document Similarity Search System For WEB-Based Medical Journal Management Mardi Siswo Utomo; Edi Winarko
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 5, No 1 (2011): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.2000

Abstract— Document similarity can be used as a reference for other information searches similar. So as to reduce the time-re-appointment for information following a similar document. Document similarity search capability is usually implemented on the features 'related articles'.Similarity of documents can be measured with a cosine, with preprosesing conducted prior to the document that will be measured. The indexing process and the measurement takes a relatively long excecution time. Problems with a web-based application to conduct the process and measuring the similarity index is a limited execution time, so the processing index and similarity measure in web-based application needs its own programming techniques.Problems with a web-based application to conduct the process and measuring the similarity index is a limited execution time, so the processing index and similarity measure in web-based application needs its own programming techniques.The purpose of this research is to design and create a software that give capability for web-based database management system of medical journals in Indonesian language to find other documents similar to the current document in reading at the time.The results of this research is the mechanism autoreload javascript and session cookies and can break down the process and measurement index similaritas into several small sections, so the process can be performed on web-based applications and the number of relatively large documents.Results with the cosine similarity measure in the case of Indonesian-language medical journal “Media medika Indonesiana” has a fairly high accuracy of 90%. Keywords— document similarity, cosine measure, web-based application.

Analisis Fitur Kalimat untuk Peringkas Teks Otomatis pada Bahasa Indonesia Badrus Zaman; Edi Winarko
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 5, No 2 (2011): July
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.2019

Abstract— Automatic Text Summarization (ATS) is a technique to create a summary of the document automatically by using computer applications to produce the most important information from the original document. Features are required to perform weighting of sentences, including Log-TFISF (term frequency index sentence frequency), sentence location, sentence overlap, title overlap and sentence relative length. This research conducted an analysis of five features in order to determine the weights of each feature that will get the results of a coherent summary. The five features are implemented in automated text summarization system in Indonesian language that was developed using the method of relative importance of topics. Results from experiments show that sentence location feature has the highest F-Measures namely 0.46 and then consecutive sentence overlap, title overlap, sentence relative length and Log-TFISF, with a value of 0.42, 0.42, 0.35 and 0.32. Relative weights of feature extraction consecutive from the largest are sentence location, sentence overlap, title overlap, sentence relative length and Log-TFISF with a value of 0.25, 0.22, 0.22, 0.19 and 0.12. These relative weights are implemented on ATS, so we get accuracy of 70.62%. It is more accurate 2,86% than without relative weights which accuracy of 67,72%.. .Keywords— Automatic Text Summarization (ATS), Log-TFISF, sentence location, sentence overlap, title overlap, sentence relative length, bahasa Indonesia

Klasifikasi Posting Twitter Kemacetan Lalu Lintas Kota Bandung Menggunakan Naive Bayesian Classification Sandi Fajar Rodiyansyah; Edi Winarko
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 6, No 1 (2012): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.2144

AbstrakSetiap hari server Twitter menerima data tweet dengan jumlah yang sangat besar, dengan demikian, kita dapat melakukan data mining yang digunakan untuk tujuan tertentu. Salah satunya adalah untuk visualisasi kemacetan lalu lintas di sebuah kota.Naive bayes classifier adalah pendekatan yang mengacu pada teorema Bayes, dengan mengkombinasikan pengetahuan sebelumnya dengan pengetahuan baru. Sehingga merupakan salah satu algoritma klasifikasi yang sederhana namun memiliki akurasi tinggi. Untuk itu, dalam penelitian ini akan membuktikan kemampuan naive bayes classifier untuk mengklasifikasikan tweet yang berisi informasi dari kemacetan lalu lintas di Bandung.Dari hasil uji coba, aplikasi menunjukan bahwa nilai akurasi terkecil 78% dihasilkan pada pengujian dengan sampel sebanyak 100 dan menghasilkan nilai akurasi tinggi 91,60% pada pengujian dengan sampel sebanyak 13106. Hasil pengujian dengan perangkat lunak Rapid Miner 5.1 diperoleh nilai akurasi terkecil 72% dengan sampel sebanyak 100 dan nilai akurasi tertinggi 93,58% dengan sampel 13106 untuk metode naive bayesian classification. Sedangkan untuk metode support vector machine diperoleh nilai akurasi terkecil 92% dengan sampel sebanyak 100 dan nilai akurasi tertinggi 99,11% dengan sampel sebanyak 13106. Kata kunci— Twitter, tweet, klasifikasi, naive bayesian classification, support vector machine AbstractEvery day the Twitter server receives data tweet with a very large number, thus, we can perform data mining to be used for specific purpose. One of which is for the visualization of traffic jam in a city.Naive bayes classifier is an approach that refers to the bayes theorem, is a combination of prior knowledge with new knowledge. So that is one of the classification algorithm is simple but has a high accuracy. With this, in this research will prove the ability naive bayes classifier to classify the tweet that contains information of traffic jam in Bandung.The testing result, the program shows that the smallest value of the accuracy is 78% on testing by using a sample 100 record and generate high accuracy is 91,60% on the testing by using a sample 13106 record. The testing results with Rapid Miner 5.1 software obtained the smallest value of the accuracy is 72% by using a sample 100 records and the high accuracy is 93.58% by using a sample 13.106 records for naive bayesian classification. And for the method of support vector machine obtained the smallest value is 92% accuracy by using a sample 100 records and the high accuracy of 99.11% by using a sample 13.106 records. Keywords—Twitter, tweet, classification, naive bayesian classification, support vector machine

Klasifikasi Posting Twitter Kemacetan Lalu Lintas Kota Bandung Menggunakan Naive Bayesian Classification Sandi Fajar Rodiyansyah; Edi Winarko
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 7, No 1 (2013): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.3048

AbstrakSetiap hari server Twitter menerima data tweet dengan jumlah yang sangat besar, dengan demikian, kita dapat melakukan data mining yang digunakan untuk tujuan tertentu. Salah satunya adalah untuk visualisasi kemacetan lalu lintas di sebuah kota.Naive bayes classifier adalah pendekatan yang mengacu pada teorema Bayes, dengan mengkombinasikan pengetahuan sebelumnya dengan pengetahuan baru. Sehingga merupakan salah satu algoritma klasifikasi yang sederhana namun memiliki akurasi tinggi. Untuk itu, dalam penelitian ini akan membuktikan kemampuan naive bayes classifier untuk mengklasifikasikan tweet yang berisi informasi dari kemacetan lalu lintas di Bandung.Dari hasil uji coba, aplikasi menunjukan bahwa nilai akurasi terkecil 78% dihasilkan pada pengujian dengan sampel sebanyak 100 dan menghasilkan nilai akurasi tinggi 91,60% pada pengujian dengan sampel sebanyak 13106. Hasil pengujian dengan perangkat lunak Rapid Miner 5.1 diperoleh nilai akurasi terkecil 72% dengan sampel sebanyak 100 dan nilai akurasi tertinggi 93,58% dengan sampel 13106 untuk metode naive bayesian classification. Sedangkan untuk metode support vector machine diperoleh nilai akurasi terkecil 92% dengan sampel sebanyak 100 dan nilai akurasi tertinggi 99,11% dengan sampel sebanyak 13106. Kata kunci— Twitter, tweet, klasifikasi, naive bayesian classification, support vector machine AbstractEvery day the Twitter server receives data tweet with a very large number, thus, we can perform data mining to be used for specific purpose. One of which is for the visualization of traffic jam in a city.Naive bayes classifier is an approach that refers to the bayes theorem, is a combination of prior knowledge with new knowledge. So that is one of the classification algorithm is simple but has a high accuracy. With this, in this research will prove the ability naive bayes classifier to classify the tweet that contains information of traffic jam in Bandung.The testing result, the program shows that the smallest value of the accuracy is 78% on testing by using a sample 100 record and generate high accuracy is 91,60% on the testing by using a sample 13106 record. The testing results with Rapid Miner 5.1 software obtained the smallest value of the accuracy is 72% by using a sample 100 records and the high accuracy is 93.58% by using a sample 13.106 records for naive bayesian classification. And for the method of support vector machine obtained the smallest value is 92% accuracy by using a sample 100 records and the high accuracy of 99.11% by using a sample 13.106 records. Keywords—Twitter, tweet, classification, naive bayesian classification, support vector machine

Penerapan Metode Support Vector Machine pada Sistem Deteksi Intrusi secara Real-time Agustinus Jacobus; Edi Winarko
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 8, No 1 (2014): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.3491

AbstrakSistem deteksi intrusi adalah sebuah sistem yang dapat mendeteksi serangan atau intrusi dalam sebuah jaringan atau sistem komputer, umum pendeteksian intrusi dilakukan dengan membandingkan pola lalu lintas jaringan dengan pola serangan yang diketahui atau mencari pola tidak normal dari lalu lintas jaringan. Pertumbuhan aktivitas internet meningkatkan jumlah paket data yang harus dianalisis untuk membangun pola serangan ataupun normal, situasi ini menyebabkan kemungkinan bahwa sistem tidak dapat mendeteksi serangan dengan teknik yang baru, sehingga dibutuhkan sebuah sistem yang dapat membangun pola atau model secara otomatis.Penelitian ini memiliki tujuan untuk membangun sistem deteksi intrusi dengan kemampuan membuat sebuah model secara otomatis dan dapat mendeteksi intrusi dalam lingkungan real-time, dengan menggunakan metode support vector machine sebagai salah satu metode data mining untuk mengklasifikasikan audit data lalu lintas jaringan dalam 3 kelas, yaitu: normal, probe, dan DoS. Data audit dibuat dari preprocessing rekaman paket data jaringan yang dihasilkan oleh Tshark.Berdasar hasil pengujian, sistem dapat membantu sistem administrator untuk membangun model atau pola secara otomatis dengan tingkat akurasi dan deteksi serangan yang tinggi serta tingkat false positive yang rendah. Sistem juga dapat berjalan pada lingkungan real-time. Kata kunci— deteksi intrusi, klasifikasi, preprocessing, support vector machine AbstractIntrusion detection system is a system for detecting attacks or intrusions in a network or computer system, generally intrusion detection is done with comparing network traffic pattern with known attack pattern or with finding unnormal pattern of network traffic. The raise of internet activity has increase the number of packet data that must be analyzed for build the attack or normal pattern, this situation led to the possibility that the system can not detect the intrusion with a new technique, so it needs a system that can automaticaly build a pattern or model.This research have a goal to build an intrusion detection system with ability to create a model automaticaly and can detect the intrusion in real-time environment with using support vector machine method as a one of data mining method for classifying network traffic audit data in 3 classes, namely: normal, probe, and DoS. Audit data was established from preprocessing of network packet capture files that obtained from Tshark. Based on the test result, the system can help system administrator to build a model or pattern automaticaly with high accuracy, high attack detection rate, and low false positive rate. The system also can run in real-time environment. Keywords— intrusion detection, classification, preprocessing, support vector machine

Peramalan KLBCampakMenggunakanGabunganMetode JST Backpropagationdan CART Sulistyowati Sulistyowati; Edi Winarko
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 8, No 1 (2014): January
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.3495

Forecasting Measles Outbreak in an area is necessary because to prevent widespread occurrence in an area. One way that is done in this study is to predict the incidence of measles by using a combination of backpropagation ANN and CART. Backpropagation ANN is used to predict the incidence of measles periodic data, then the CART method used to perform the determination of an outbreak or non-outbreak area.Backpropagation neural network is one of the most commonly used methods for forecasting which can result in a better level of accuracy than other ANN methods. While the methods of CART is a binary tree method is also popular for the classification, which can produce models or classification rules.Results of this study show that the number of the best window for backpropagation neural network to forecast the outcome affect forecasting accuracy. Determination of the number of windows of a backpropagation neural network forecasting on each attribute gives different results and directly affects the forecasting results. ANN can do the forecasting in time series using siliding window with accuracy 90.01% and then CART method can be use for classification with accuracy 83.33%.

Data Mining Untuk Mengetahui Tingkat Loyalitas Konsumen Terhadap Merek Kendaraan Bermotor dan Pola Kecelakaan Lalulintas di DIY Agus Sasmito Ariwibowo; Edi Winarko
IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Vol 5, No 3 (2011): November
Publisher : IndoCEISS in colaboration with Universitas Gadjah Mada, Indonesia.

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ijccs.5205

Abstract— The data of vehicle sales and traffic accident can be processed into information that is important for vehicle dealers and the Police Department. Those important information researched are the level of consumer loyalty to the vehicle brands and to predict the vehicle’s brands that will be purchased by a consumer. The study also tries to analyze the traffic accident data to find out is there any link between the occurrence of an accident to a certain brand of vehicle. This research implementing data mining method called ‘rule based classification’ to establish the sales of vehicles rules by which can be used to classify consumer into group level of brand loyalty and also estimate the brand of the next vehicle’s brand that will be purchased by the consumer. This research will process the data traffic accident by using data mining techniques called Apriori Method. Apriori Method is used to identify a pattern of accidents based on brand, type of vehicles, and the vehicle’s color. The results are used to estimate whether there is any correlation between the occurrences of a traffic accident to a particular brand. The result can help companies or vehicle dealers to obtain information about the level of the consumer’s brand loyalty to the dealer’s brand and to predict the brand that the consumer would be buy for the next vehicle. The result can also help the Police Department to find out whether there is any correlation between the occurrence of traffic accidents to the brand, type and the color of vehicle. Keywords— rule based classification, apriori, brand loyalty, traffic accident.

Title

Found 17 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 17 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 17 Documents
Search