Garuda - Garba Rujukan Digital

Visualisasi Aturan Asosiasi Berbasis Graph untuk Data Tindak Kejahatan Atmaja, Eduardus Hardika Sandy
Media Teknika Vol 12, No 1 (2017)
Publisher : Sanata Dharma University

Â Criminality is a social problem causing negative impacts on society welfare. Police as law enforcement officer was required to take actions to prevent criminality which was increasingly widespread. Such efforts could be realized by analizing criminal data to obtain useful information for the preparation of criminal prevention strategies. However, extracting knowledge from criminal data effectively was a problematique for them. In this study, data mining was used to solve knowledge extraction problem from the dataset. The technique was aimed to get information about crime patternsby analyzing criminal activity habits. Association rule mining and apriori algorithm were used to find crime patterns. Generating crime patterns in data mining was difficult to understand when there were too many rules. Graph based visualization of association rules designed to solve that problem. Generated visualization showed relationship between crimes. That visualization was expected to help the police to understand the crime pattern so they could do prevention efforts more effectively. The results showed that the visualization of association rules could present association rules in more interesting way and described the crime pattern.

Application of CT-Pro Algorithm For Crime Analysis Atmaja, Eduardus Hardika Sandy; Simaremare, Risky; Rosa, Paulina Heruningsih Prima
SENATIK STT Adisutjipto Vol 5 (2019): Peran Teknologi untuk Revitalisasi Bandara dan Transportasi Udara [ISBN XXX-XXX-XXXXX-
Publisher : Sekolah Tinggi Teknologi Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/senatik.v5i0.360

The large amount of crime data generally becomes a pile of data that lacks of information. Data mining can be implemented in various fields such as crime. Data mining techniques can be used to find information from crime data that has been collected by the police. This study analyzed 3.198 crime data of Polresta Yogyakarta in 2016-2018. This study was conducted to determine the pattern of interrelationships between regions with potential crime in the region using association rule mining with CT-PRO algorithm. System testing was done by changing support and confidence values to find best crime patterns. The results were support and confidence values that can produce association rules are 8,59% and 70% with one rule, namely: "If the committed crime is CURAT then the crime occures in MUKIM." The rule has 70,5% confidence, 275 support count and 1,66 lift ratio which means the rule were in the strong category.

Implementation of k-Medoids Clustering Algorithm to Cluster Crime Patterns in Yogyakarta Atmaja, Eduardus Hardika Sandy
International Journal of Applied Sciences and Smart Technologies Volume 01, Issue 01, June 2019
Publisher : Universitas Sanata Dharma

The increase in crime from day to day needs to be a concern for the police, as the party responsible for security in the community. Crime prevention effort must be done seriously with all knowledge that they have. To increase police performance of crime prevention effort, it is necessary to analyze crime data so that relevant information can be obtained.This study tried to analyze crime data to obtain relevant information using clustering in data mining.Clustering is a data mining method that can be used to extract valuable information by grouping data into groups that have similar characters.The data used in this study were crime patterns which were then grouped using K-medoids clustering algorithm.The obtained results in this study were three crime groups, namely high crime levelwith 4 members, medium crimelevel with 6 members and low crime level with 8 members.It is expected that this information can be used as material for consideration in crime prevention effort

PREDIKSI KEMENANGAN ESPORT DOTA 2 BERDASARKAN DATA PERTANDINGAN Atmaja, Eduardus Hardika Sandy
AVITEC Vol 2, No 1 (2020): Februari 2020
Publisher : Sekolah Tinggi Teknologi Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/avitec.v2i1.612

DOTA 2 is one of the eSports that are in great demand both by the general society and the game professional communities. They compete with each other to develop the best strategy to defeat all enemies they faced. In order to develop the best strategy, a good and accurate analysis system is needed. Data mining can be used to solve these problems by digging valuable information from dataset using certain method. Prediction method is one of the methods in data mining that is most appropriate for finding the winning predictions for the DOTA 2 game. One method that is quite simple and can be used is Naive Bayes. The results of this study indicate that Naive Bayes can make predictions well with an accuracy of 98,804 %. The data used in this research as much as 50000 that obtained from open data. It is expected that this research can assist players in providing information for developing game strategies.

Unjuk Kerja Selection Sort Hybrid Atmaja, Eduardus Hardika Sandy; Pinaryanto, Kartono
Jurnal Buana Informatika Vol 11, No 1 (2020): Jurnal Buana Informatika Volume 11 - Nomor 1 - April 2020
Publisher : Universitas Atma Jaya Yogyakarta

Abstract. Sorting is the most basic and important process in data processing. The sorting process on large data causes large computation. Some existing sorting algorithms need to be improved to further improve their performance. This study tried to develop an existing selection sort algorithm, into a selection sort hybrid algorithm that is expected to have better performance. Selection sort hybrid algorithm is an algorithm that combines both minimum and maximum searching techniques. It can find minimum and maximum values in the same time to sort from the both side of the data. Since it can be done separately, multithreading is used to do this job. So the sorting process can be done simultaneously. Several tests using different amounts of data have been conducted to compare the performance of the algorithms. The result is selection sort hybrid algorithm more efficient than the origin selection sort. Henceforth, the result obtained from the research can be used for various purposes related to data processing in informatics area.Keywords: sorting, selection sort, selection sort hybrid, computingAbstrak. Sorting atau pengurutan adalah proses yang paling mendasar dan penting dalam pemrosesan data. Proses pengurutan pada data yang besar menyebabkan komputasi menjadi tinggi. Maka beberapa algoritme pengurutan perlu ditingkatkan kinerjanya. Penelitian ini mencoba mengembangkan algoritme selection sort, menjadi algoritme selection sort hybrid yang diharapkan memiliki kinerja yang lebih baik. Algoritme selection sort hybrid adalah algoritme yang menggabungkan teknik pencarian minimum dan maksimum. Algoritme tersebut dapat menemukan nilai minimum dan maksimum dalam waktu yang bersamaan untuk mengurutkan data dari kedua sisinya. Karena dapat dikerjakan secara terpisah, maka teknik multithreading digunakan untuk melakukan pekerjaan ini. Jadi proses pengurutan data bisa dilakukan secara simultan. Beberapa pengujian menggunakan jumlah data yang berbeda telah dilakukan untuk membandingkan kinerja kedua algoritme ini. Hasilnya adalah algoritme selection sort hybrid lebih efisien daripada algoritme selection sort untuk semua kasus yang diberikan. Diharapkan hasil yang diperoleh dari penelitian ini dapat digunakan untuk berbagai keperluan terkait dengan pengolahan data di bidang informatika.Kata kunci: Pengurutan, selection sort, selection sort hybrid, komputasi

Visualisasi Aturan Asosiasi Berbasis Graph untuk Data Tindak Kejahatan Eduardus Hardika Sandy Atmaja
Media Teknika Vol 12, No 1 (2017)
Publisher : Sanata Dharma University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/mt.v12i1.946

Criminality is a social problem causing negative impacts on society welfare. Police as law enforcement officer was required to take actions to prevent criminality which was increasingly widespread. Such efforts could be realized by analizing criminal data to obtain useful information for the preparation of criminal prevention strategies. However, extracting knowledge from criminal data effectively was a problematique for them. In this study, data mining was used to solve knowledge extraction problem from the dataset. The technique was aimed to get information about crime patternsby analyzing criminal activity habits. Association rule mining and apriori algorithm were used to find crime patterns. Generating crime patterns in data mining was difficult to understand when there were too many rules. Graph based visualization of association rules designed to solve that problem. Generated visualization showed relationship between crimes. That visualization was expected to help the police to understand the crime pattern so they could do prevention efforts more effectively. The results showed that the visualization of association rules could present association rules in more interesting way and described the crime pattern.

Prediksi Kemenangan eSport DOTA 2 Berdasarkan Data Pertandingan Eduardus Hardika Sandy Atmaja
Aviation Electronics, Information Technology, Telecommunications, Electricals, Controls (AVITEC) Vol 2, No 1 (2020): February
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/avitec.v2i1.612

DOTA 2 is one of the eSports that are in great demand both by the general society and the game professional communities. They compete with each other to develop the best strategy to defeat all enemies they faced. In order to develop the best strategy, a good and accurate analysis system is needed. Data mining can be used to solve these problems by digging valuable information from dataset using certain method. Prediction method is one of the methods in data mining that is most appropriate for finding the winning predictions for the DOTA 2 game. One method that is quite simple and can be used is Naive Bayes. The results of this study indicate that Naive Bayes can make predictions well with an accuracy of 98,804 %. The data used in this research as much as 50000 that obtained from open data. It is expected that this research can assist players in providing information for developing game strategies.

Unjuk Kerja Selection Sort Hybrid Eduardus Hardika Sandy Atmaja; Kartono Pinaryanto
Jurnal Buana Informatika Vol. 11 No. 1 (2020): Jurnal Buana Informatika Volume 11 - Nomor 1 - April 2020
Publisher : Universitas Atma Jaya Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24002/jbi.v11i1.2699

Abstract. Sorting is the most basic and important process in data processing. The sorting process on large data causes large computation. Some existing sorting algorithms need to be improved to further improve their performance. This study tried to develop an existing selection sort algorithm, into a selection sort hybrid algorithm that is expected to have better performance. Selection sort hybrid algorithm is an algorithm that combines both minimum and maximum searching techniques. It can find minimum and maximum values in the same time to sort from the both side of the data. Since it can be done separately, multithreading is used to do this job. So the sorting process can be done simultaneously. Several tests using different amounts of data have been conducted to compare the performance of the algorithms. The result is selection sort hybrid algorithm more efficient than the origin selection sort. Henceforth, the result obtained from the research can be used for various purposes related to data processing in informatics area.Keywords: sorting, selection sort, selection sort hybrid, computingAbstrak. Sorting atau pengurutan adalah proses yang paling mendasar dan penting dalam pemrosesan data. Proses pengurutan pada data yang besar menyebabkan komputasi menjadi tinggi. Maka beberapa algoritme pengurutan perlu ditingkatkan kinerjanya. Penelitian ini mencoba mengembangkan algoritme selection sort, menjadi algoritme selection sort hybrid yang diharapkan memiliki kinerja yang lebih baik. Algoritme selection sort hybrid adalah algoritme yang menggabungkan teknik pencarian minimum dan maksimum. Algoritme tersebut dapat menemukan nilai minimum dan maksimum dalam waktu yang bersamaan untuk mengurutkan data dari kedua sisinya. Karena dapat dikerjakan secara terpisah, maka teknik multithreading digunakan untuk melakukan pekerjaan ini. Jadi proses pengurutan data bisa dilakukan secara simultan. Beberapa pengujian menggunakan jumlah data yang berbeda telah dilakukan untuk membandingkan kinerja kedua algoritme ini. Hasilnya adalah algoritme selection sort hybrid lebih efisien daripada algoritme selection sort untuk semua kasus yang diberikan. Diharapkan hasil yang diperoleh dari penelitian ini dapat digunakan untuk berbagai keperluan terkait dengan pengolahan data di bidang informatika.Kata kunci: Pengurutan, selection sort, selection sort hybrid, komputasi

Implementation of k-Medoids Clustering Algorithm to Cluster Crime Patterns in Yogyakarta Eduardus Hardika Sandy Atmaja
International Journal of Applied Sciences and Smart Technologies Volume 01, Issue 01, June 2019
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v1i1.1859

The increase in crime from day to day needs to be a concern for the police, as the party responsible for security in the community. Crime prevention effort must be done seriously with all knowledge that they have. To increase police performance of crime prevention effort, it is necessary to analyze crime data so that relevant information can be obtained.This study tried to analyze crime data to obtain relevant information using clustering in data mining.Clustering is a data mining method that can be used to extract valuable information by grouping data into groups that have similar characters.The data used in this study were crime patterns which were then grouped using K-medoids clustering algorithm.The obtained results in this study were three crime groups, namely high crime levelwith 4 members, medium crimelevel with 6 members and low crime level with 8 members.It is expected that this information can be used as material for consideration in crime prevention effort

Application of CT-Pro Algorithm For Crime Analysis Atmaja, Eduardus Hardika Sandy; Simaremare, Risky; Rosa, Paulina Heruningsih Prima
SENATIK STT Adisutjipto Vol 5 (2019): Peran Teknologi untuk Revitalisasi Bandara dan Transportasi Udara [ISBN 978-602-52742-
Publisher : Institut Teknologi Dirgantara Adisutjipto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28989/senatik.v5i0.360

The large amount of crime data generally becomes a pile of data that lacks of information. Data mining can be implemented in various fields such as crime. Data mining techniques can be used to find information from crime data that has been collected by the police. This study analyzed 3.198 crime data of Polresta Yogyakarta in 2016-2018. This study was conducted to determine the pattern of interrelationships between regions with potential crime in the region using association rule mining with CT-PRO algorithm. System testing was done by changing support and confidence values to find best crime patterns. The results were support and confidence values that can produce association rules are 8,59% and 70% with one rule, namely: "If the committed crime is CURAT then the crime occures in MUKIM." The rule has 70,5% confidence, 275 support count and 1,66 lift ratio which means the rule were in the strong category.

Title

Found 10 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 10 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 10 Documents
Search