Introduction: Terrorism Activity is the subject of the talks in various countries, especially in Indonesia. The activities of terrorism are carried out in various ways using suicide bombs, violent action that aimed to demoralize by creating fear to the society and national security. In Indonesia, according to Kompas news website recorded there were 10 suicide bombings occurred in the past 6 years and took many casualties in every event. With this, it certainly gives a threat to the people in Indonesia in terms of physical, moral and even in terms of national security
Methods: To overcome this problem, it is necessary to increase the national security so that terrorism can be prevented and it will not happen again. This study is aimed to conduct an exploratory data analysis and predict terrorist activity in Indonesia using K-Nearest Neighbor (KNN), and k-fold cross-validation. In this research, data selection, data cleaning, data reduction were carried out and feature selectionprocess which aimed to find out the most influential data attributes.
Results:According to the analysis, the researcher proved the result using the K-NN algorithm independentlyis different from the result of K-NN algorithm testing which added the use of k-fold cross-validationin predicting terrorist activity in Indonesia. The evidenced of the result obtained by doing a comparison between the best value of k, found that value of k = 8 values is the best in this study by generating the value of accuracyusing k-fold cross-validationof 88.86%, recall73.69%, precision 74.44% and RMSE 0.333. While independent testing with k = 8 produces an accuracy value of 88.82%, recall 64.29%, precision 72.42% and RMSE value (root mean square error)of 0.308.
Discussion:The results obtained in this study expected to be a reference for other researchers who will conduct further research related to terrorist activities in Indonesia either performing analytical activities or making an application to predict terrorist activities and additional information from the research that had performed will provide advice for security forces to enhance national security.
[1]
Yusuf Sulistyo Nugroho,et al.
PREDIKSI RATING FILM MENGGUNAKAN METODE NAIVE BAYES
,
2016
.
[2]
Irwan Budiman,et al.
PENERAPAN K-OPTIMAL PADA ALGORITMA KNN UNTUK PREDIKSI KELULUSAN TEPAT WAKTU MAHASISWA PROGRAM STUDI ILMU KOMPUTER FMIPA UNLAM BERDASARKAN IP SAMPAI DENGAN SEMESTER 4
,
2016
.
[3]
Fina Nasari,et al.
Penerapan Algoritma K-Means Clustering Untuk Pengelompokkan Penyebaran Diare Di Kabupaten Langkat
,
2016
.
[4]
Bambang Darmono.
Konsep Dan Sistem Keamanan Nasional Indonesia
,
2016
.
[5]
Yuli Asriningtias,et al.
Aplikasi Data Mining Untuk Menampilkan Informasi Tingkat Kelulusan Mahasiswa
,
2014
.
[6]
Wiyli Yustanti.
Algoritma K-Nearest Neighbour untuk Memprediksi Harga Jual Tanah
,
2018
.
[7]
Aang Alim Murtopo.
Prediksi Kelulusan Tepat Waktu Mahasiswa STMIK YMI Tegal Menggunakan Algoritma Naïve Bayes
,
2016
.
[8]
Green Arther Sandag,et al.
Klasifikasi Malicious Websites Menggunakan Algoritma K-NN Berdasarkan Application Layers dan Network Characteristics
,
2018,
CogITo Smart Journal.
[9]
A. Kandel,et al.
Using Data Mining Techniques for Detecting Terror-Related Activities on the Web
,
2004
.