Abstrak -Data mining merupakan teknik pengolahan data dalam jumlah besar untuk pengelompokan. Teknik Data mining mempunyai beberapa metode dalam mengelompokkan salah satu teknik yang dipakai penulis saat ini adalah K-Means. Dalam hal ini penulis mengelompokan data daftar program SDP tahun 2017 untuk mengetahui manakah pegawai yang layak lolos dalam program SDP sehingga dapat melakukan Registrasi Asessment Center. Pengelompokan tersebut berdasarkan kriteria -kriteria data Program SDP. Pada penelitian ini, penulis menerapkan algoritma K-Means Clustering untuk pengelompokan data Program SDP di PT.Bank Syariah. Dalam hal ini, pada umumnya untuk memamasuki program SDP tersebut disesuaikan dengan ketentuan dan parameter Program SDP saja, namun dalam penelitian ini pengelompokan disesuaikan dengan kriteria -kriteria Program SDP seperti kedisiplinan pegawai, Target Kerja Pegawai, Kepatuhan Program SDP. Penulis menggunakan beberapa kriteria tersebut agar pengelompokan yang dihasilkan menjadi lebih optimal. Tujuan dari pengelompokan ini adalah terbentuknya kelompok SDP pada Program SDP yang menggunakan algoritma K-Means clustering. Hasil dari pengelompokan tersebut diperoleh tiga kelompok yaitu kelompok Lolos, Hampir Lolos dan Tidak Lolos. Terdapat pusat cluster dengan Cluster -1= 8;66;13, Cluster-2= 10;71;14 dan Cluster-3=7;60;12. Pusat cluster tersebut didapat dari beberapa iterasi sehingga mengahasilakan pusat cluster yang optimal.
Natural disasters are natural events that have a large impact on the human population. Located on the Pacific Ring of Fire (an area with many tectonic activities), Indonesia must continue to face the risk of volcanic eruptions, earthquakes, floods, tsunamis. Application of Clustering Algorithm in Grouping the Number of Villages / Villages According to Anticipatory / Natural Disaster Mitigation Efforts by Province With K-Means. The source of this research data is collected based on documents that contain the number of villages / kelurahan according to natural disaster mitigation / mitigation efforts produced by the National Statistics Agency. The data used in this study is provincial data consisting of 34 provinces. There are 4 variables used, namely the Natural Disaster Early Warning System, Tsunami Early Warning System, Safety Equipment, Evacuation Line. The data will be processed by clustering in 3 clushter, namely clusther high level of anticipation / mitigation, clusters of moderate anticipation / mitigation levels and low anticipation / mitigation levels. The results obtained from the assessment process are based on the Village / Kelurahan index according to the Natural Disaster Anticipation / Mitigation Efforts with 3 provinces of high anticipation / mitigation levels, namely West Java, Central Java, East Java, 9 provinces of moderate anticipation / mitigation, and 22 other provinces including low anticipation / mitigation. This can be an input to the government, the provinces that are of greater concern to the Village / Village According to the Natural Health Disaster Mitigation / Mitigation Efforts based on the cluster that has been carried out.Keywords: Data Mining, Natural Disaster, Clustering, K-Means
-1 and 12-75-1 with best architectural models 12-70-1 with an accuracy of 92%. In contrast to previous research concentrating on finding accuracy using backpropagation, this study will optimize the backpropagation with Conjugate Gradient Beale-Powell Restart, which not only focuses on accuracy but also the convergence of the two algorithms and the translation of predicted results, which is not done in a previous study. This research will use the same architectural model as the previous research and will get the result with the accuracy of 92% with the best architectural model that is 12-70-1 (same as previous research). Thus, this model is good enough for prediction even with different algorithms, since the accuracy of converging backpropagation with Conjugate Gradient Beale-Powell Restarts.
KATA KUNCI
The Internet today has become a primary need for its users. According to market research company e-Marketer, there are 25 countries with the largest internet users in the world. Indonesia is in the sixth position with a total of 112.6 million internet users. With the increasing number of internet users are expected to help improve the economy and also education in a country. To be able to increase the number of internet users, especially in Indonesia, it is necessary to predict for the coming years so that the government can provide adequate facilities and pre-facilities in order to balance the growth of internet users and as a precautionary step when there is a decrease in the number of internet users. The data used in this study focus on data on the number of internet users in 25 countries in 2013-2017. The algorithm used is Artificial Neural Network Backpropagation. Data analysis was processed by Artificial Neural Network using Matlab R2011b (7.13). This study uses 5 architectural models. The best network architecture generated is 3-50-1 with an accuracy of 92% and the Mean Squared Error (MSE) is 0.00151674.Abstrak-Internet saat ini sudah menjadi kebutuhan primer untuk para penggunanya. Menurut lembaga riset pasar e-Marketer, ada 25 negara teratas dengan pengguna internet terbanyak di dunia. Indonesia berada pada posisi keenam dengan jumlah pengguna internet sebanyak 112,6 juta jiwa. Dengan semakin meningkatnya jumlah pengguna internet diharapkan dapat ikut memajukan perekonomian dan juga pendidikan di suatu negara. Untuk dapat meningkatankan jumlah pengguna internet, khususnya di Indonesia maka perlu dilakukan prediksi untuk tahun-tahun mendatang sehingga pemerintah dapat menyediakan sarana dan pra-sarana yang memadai guna untuk mengimbangi pertumbuhan jumlah pengguna internet dan sebagai langkah antisipasi saat terjadi penurunan jumlah pengguna internet. Data yang digunakan pada penelitian ini fokus pada data jumlah pengguna internet di 25 negara tahun 2013-2017. Algoritma yang digunakan yaitu Jaringan Syaraf Tiruan Backpropagation. Analisa data dilakukan dengan metode Jaringan Syaraf Tiruan menggunakan software Matlab R2011b (7.13). Penelitian ini menggunakan 5 model arsitektur. Arsitektur jaringan terbaik yang dihasilkan adalah 3-50-1 dengan tingkat akurasi 92% dan nilai Mean Squared Error (MSE) adalah 0,00151674.
Measles is one of the causes of death in children around the world which always increases every year. Although measles immunization programs have been implemented, the incidence of measles in children is still quite high. This study discusses the Implementation of Rapidminer with the K-Means Method (Case Study: Measles Immunization in Toddlers by Province). The increase in cases of measles in toddlers in Indonesia is a case that has never been separated from the government's attention. Data sources and research were obtained from the Central Statistics Agency (BPS). The data used in this study are data from 2004-2017 which consists of 34 provinces. The cluster process is divided into 3 (three) clusters, namely high cluster level (C1), medium cluster level (C2) and low cluster level (C3). So that the assessment for cases of immunization against measles based on high cluster province (C1) is 21 provinces for medium cluster (C2) of 12 provinces and for low cluster (C3) of 1 province. The results of the cluster can be used as input for the government, especially the provinces, so that provinces that enter the high cluster receive more attention and increase the socialization of measles immunization against children under five. Keywords: Data Mining, Measles, Clustering, K-means
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.