Article Per Year (5 Year)
p-Index From 2021 - 2026
1.006
P-Index
This Author published in this journals
All Journal IJCIT (Indonesian Journal on Computer and Information Technology) Jurnal Komputer Terapan JTERA (Jurnal Teknologi Rekayasa) Indonesian Journal of Artificial Intelligence and Data Mining JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI Infotekmesin
Christina Juliane
STMIK LIKMI Bandung
Civil Engineering, Building, Construction & Architecture Computer Science & IT Electrical & Electronics Engineering Industrial & Manufacturing Engineering Mechanical Engineering

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
Algoritma Algoritma K-Means Clustering untuk Mengklasifikasi Tingkat Kepuasan Layanan Informasi Hukum di Provinsi Jawa Barat: Algoritma K-Means Clustering untuk Mengklasifikasi Tingkat Kepuasan Layanan Informasi Hukum di Provinsi Jawa Barat Beny Ruhiman; Ade Ramdan; Christina Juliane
Jurnal Komputer Terapan Vol. 8 No. 1 (2022): Jurnal Komputer Terapan
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (401.864 KB) | DOI: 10.35143/jkt.v8i1.5209

Abstract

Legal Documentation and Information Network (JDIH) is one of the government agencies in the field of law, which is regulated by Presidential Regulation Number 33 of 2012. JDIH consists of central and regional levels, at the provincial level the Bureau of Law and Human Rights is the center of JDIH in its territory. JDIH at the provincial level has the duties and functions to provide guidance and evaluation at the members. To measure the level of community satisfaction with JDIH members in West Java, a survey was conducted using the 360 review ​​method on the website https://jdih.jabarprov.go.id/review.php/. The results contained 18,045 raw data. After preprocessing, 46 datasets and 11 attributes were generated. Cluster modeling uses the K-Means algorithm, the results are evaluated by the Davies Boulding Index (DBI) method. Evaluation results show a low level of similarity so that the distance between clusters is getting higher. On this study is classified into 4 clusters, the lowest satisfaction indicator is known to be in cluster 3 which consists of 10 regions. In this research can be used to determining policies for the government of West Java Province.
Implementasi Data Mining untuk Klasterisasi dan Prediksi Kelompok Keluarga Imam Sapuan; Muhammad Hilmi Fauzan; Christina Juliane
JTERA (Jurnal Teknologi Rekayasa) Vol 7, No 1: June 2022
Publisher : Politeknik Sukabumi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31544/jtera.v7.i1.2022.149-156

Abstract

Pengelompokkan keluarga ke dalam cluster mampu dan tidak mampu sangat diperlukan untuk acuan berbagai kegiatan di masa depan seperti bantuan pemerintah atau pihak terkait lainnya. Data mining merupakan salah satu pendekatan yang dapat digunakan untuk menyelesaikan masalah ini. Metode data mining yang cocok adalah clustering dan prediksi. Penelitian ini bertujuan untuk mengimplementasikan data mining untuk klasterisasi dan prediksi kelompok keluarga. Terdapat dua algoritma yang digunakan pada penelitian ini, yaitu kModes dan decision tree. Algoritma kModes berfungsi untuk menghasilkan cluster yang akan digunakan pada tahap selanjutnya, sedangkan metode decision tree digunakan sebagai algoritma prediksinya. Hasil penelitian menunjukkan bahwa kedua metode ini berhasil menyelesaikan masalah dengan tingkat akurasi yang sangat tinggi yaitu sebesar 95,3%, presisi sebesar 95,4%, dan recall sebesar 95,3%.
Model Prediksi Penjualan Jenis Produk Tekstil Menggunakan Algoritma K-Nearest Neighbor (K-NN) Wiyana Yusuf; Rahma Witri; Christina Juliane
IJCIT (Indonesian Journal on Computer and Information Technology) Vol 7, No 1 (2022): IJCIT Mei 2022
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (277.593 KB) | DOI: 10.31294/ijcit.v7i1.11973

Abstract

Indonesia merupakan negara yang memiliki industri tekstil yang besar, mulai dari industri pembuatan serat sintetis (fiber making), industri pemintalan benang (spinning), industri pertenunan (weaving), industri perajutan (knitting), industri pencelupan, pencetakan dan penyempurnaan sampai dengan industri pakaian jadi (garment). Dalam dunia perstekstilan kita perlu memperhatikan pasar terhadap jenis kain yang akan diproduksi secara luas kepada masyarakat. Akan tetapi, tidak ada proses survey pasar pada perusahaan ini yang diakibatkan oleh kurangnya karyawan sehingga perusahaan hanya memproduksi barang tergantung dengan pesanan dari customer. Oleh karena itu diperlukan pemantauan terhadap permintaan oleh customer menggunakan klasifikasi data mining sehingga perusahaan dapat menentukan jenis produk mana yang akan tinggi permintaan dengan cara mengolah data penjualan perusahaan tersebut. Penelitian ini bertujuan untuk membantu perusahaan dalam menentukan arah untuk produksi serta penjualan di masa yang akan datang. Dalam penelitian ini algoritma yang dipilih adalah klasifikasi data mining dengan K-Nearest Neighbor dengan mengklaster data dari nilai k=1 hingga k=5. Hasil yang diperoleh dengan nilai k=1 mendapatkan akurasi 86.9% dengan RMSE 0.362. Serta nilai class recall & class precision pada confussion matrix yang didapat cukup baik sehingga model algoritma yang digunakan pada penelitian ini bekerja dengan baik. Indonesia is a country that has a large textile industry, ranging from the synthetic fiber manufacturing industry (fiber making), the yarn spinning industry (spinning), the weaving industry (weaving), knitting industry (knitting), dyeing, printing and refinement industries to the clothing industry. so (garments). In the world of textiles, we need to pay attention to the market for the types of fabrics that will be widely produced to the public. However, there is no market survey process at this company which is caused by a lack of employees so that the company only produces goods depending on orders from customers. Therefore, it is necessary to monitor demand by customers using data mining classification so that companies can determine which types of products will be in high demand by processing the company's sales data. This study aims to assist the company in determining the direction for production and sales in the future. In this study, the algorithm chosen is data mining classification with K-Nearest Neighbor by clustering data from values k=1 to k=5. The results obtained with a value of k = 1 get an accuracy of 86.9% with an RMSE of 0.362. And the value of class recall & class precision in the confusion matrix is quite good so that the algorithm model used in this study works well.
Implementasi Manajemen Pengetahuan Pada Perusahaan Web Hosting Dengan Web Hosting Management Complete Solution Angga Pramudianto; Christina Juliane
Infotekmesin Vol 13 No 2 (2022): Infotekmesin: Juli, 2022
Publisher : P3M Politeknik Negeri Cilacap

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35970/infotekmesin.v13i2.1537

Abstract

The implementation of knowledge management in a company has become a necessity in the current 4.0 era. Therefore, the company's ability to manage existing knowledge is needed to survive the onslaught of competition. To implement knowledge management in one of the Web Hosting companies towards service to consumers is the aim of this research, as well as a solution to the problems experienced in the Customer Support division. Due to this, the problem-solving process is often hampered and the existing problems are not properly archived. In this study, knowledge of the organization is figured out by analyzing the support of existing information technology. Focus Group Discussion (FGD) method is used as a tool to find out the abilities and skills that exist in each of them, in order to figure out the extent to which a person's perspective is to see and assess something he observes. In this study, Web Hosting Management Complete Solution (WHMCS) is a system used in applying knowledge to web hosting companies for the knowledge-sharing process between customer support and consumers.
Identification of Diabetes Mellitus Risk Factors With a Data Mining Classification Approach Ade Agustina; Galih Ady Permana; Christina Juliane
Indonesian Journal of Artificial Intelligence and Data Mining Vol 5, No 2 (2022): September 2022
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v5i2.18841

Abstract

Diabetes mellitus is a chronic disease characterized by an increase in the frequency of eating, drinking and urinating due to the failure of the process of sugar entering the body to be converted into energy due to the pancreas function not being able to produce enough insulin or not producing insulin at all. The purpose of writing this paper is to test the accuracy of the decision tree and rules generated by the ID3 algorithm and correlate it with literature studies from research that has been carried out by researchers in the health sector related to diabetes and the results of this classification are expected to be used as a reference. For everyone to be able to change their lifestyle to avoid the risk of developing diabetes mellitus by looking at the attributes of the dataset. In this study, the application of data mining with the classification method with the ID3 algorithm using datasets from the BRFSS survey results was carried out. The results of data testing can be obtained from the accuracy of the rules generated by the ID3 algorithm with an accuracy rate of 85.95%. The rules generated by the ID3 algorithm are also correlated with the literature from research that has been carried out by researchers in the health sector, and the results are that the rules generated from the attribute indicators of the dataset have relevance and suitability
Klasifikasi Penerima Bansos Menggunakan Algoritma Naive Bayes Hamzah Nurrifqi Fakhri Fikrillah; Sigit Hudawiguna; Christina Juliane
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 10 No 1 (2023): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v10i1.3624

Abstract

Bansos (bantuan sosial) merupakan sebuah program yang dikeluarkan oleh pemerintah untuk membantu masyarakat yang kurang mampu dalam ekonomi. Tujuan dari penelitian ini untuk memberikan klasifikasi dan rekomendasi terhadap program bansos yang diberikan oleh pemerintah pusat. Hasil dari penelitian ini akan memberikan informasi serta gambaran klasifikasi penerima bansos yang sesuai dengan kriteria umur dan pekerjaan. Untuk mencapai tujuan tersebut, penelitian ini menggunakan Algoritma Naive Bayes untuk memprediksi nilai probabilitas terbesar berdasarkan data masa lalu. Tahapan penelitian yang dilakukan meliputi pengumpulan data, pembersihan data, transformasi data, pemodelan dan evaluasi. Data yang digunakan untuk kebutuhan analisis menggunakan Data Terpadu Kesejahteraan Sosial di Kecamatan Malangbong Kabupaten Garut dengan jumlah data yang telah bersihkan dan di transformasi sebanyak 100.445. Hasil pemodelan menggunakan Algoritma Naive Bayes memberikan nilai akurasi sebesar 62,51%. Penelitian ini diharapkan dapat memberikan rekomendasi terhadap masyarakat atau orang orang penerima bansos dan sebagai acuan pada penyaluran bansos untuk memperkecil adanya salah sasaran penyaluran bansos.
Co-Authors Ade Agustina Ade Ramdan Angga Pramudianto Beny Ruhiman Galih Ady Permana Hamzah Nurrifqi Fakhri Fikrillah Imam Sapuan Muhammad Hilmi Fauzan Rahma Witri Sigit Hudawiguna Wiyana Yusuf