Article Per Year (5 Year)
p-Index From 2020 - 2025
1.456
P-Index
This Author published in this journals
All Journal Indonesian Journal of Electronics and Instrumentation Systems Jurnal Transformatika JUKI : Jurnal Komputer dan Informatika Jurnal Teknik Informatika (JUTIF) Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) Jurnal Pengabdian Kepada Masyarakat (JPKM) J-Icon : Jurnal Komputer dan Informatika
Derwin Rony Sina, Derwin
Universitas Nusa Cendana
Agriculture, Biological Sciences & Forestry Computer Science & IT Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Social Sciences Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : J-Icon : Jurnal Komputer dan Informatika

 1 
KAJIAN MACHINE LEARNING DENGAN KOMPARASI KLASIFIKASI PREDIKSI DATASET TENAGA KERJA NON-AKTIF Derwin Rony Sina; NEUTRINO KUSRORONG SAE BELAUDIN KUSRORONG; Nelci Dessy Rumlaklak
J-Icon : Jurnal Komputer dan Informatika Vol 7 No 1 (2019): Maret 2019
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v7i1.880

Abstract

Comparative studies of machine learning are carried out with the aim of determining the best method base based on the ability to predict with true data. The study carried out on the labor dataset aims to extract information on the choice of agency employees to exit or not. The method used in the comparative study is K-Nearest Neighbors (KNN) from the basis of similarity, Naïve Bayes (NB) from the probability base, and C4.5 from the basis of the decision tree. Application design and construction is done by receiving input labor data, the dataset is divided into training data and test data, training data for training and models while the test data is used when classifying by model. The classification process is carried out using supply training scenarios and cross validation of 14,999 data. The initial hypothesis C4.5 is the best method with an accuracy measure. Proof of the initial hypothesis will be true if the best accuracy majority is owned by the C4.5 method with supply trainning scenarios and cross validation. The results of the classification data analysis found that the C4.5 accuracy was superior in each parameter of the inventory training scenario data distribution and the k-fold parameter was 3. 5. 7, and 9 of the cross validation scenario so that the best method of non-active labor classification was C4.5.
CASE BASED REASONINGUNTUK MENDIAGNOSIS GIZI BURUK PADA ANAKUSIA 0-5 TAHUN MENGGUNAKAN METODE COSINE SIMILARITY Derwin Rony Sina; Meiton Boru; Marselina Elisabeth Soinbala
J-Icon : Jurnal Komputer dan Informatika Vol 7 No 1 (2019): Maret 2019
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v7i1.885

Abstract

Case Based Reasoning (CBR) method is one method to build a system with new case decision based on solution from previous cases by calculating similarity level. The calculation of similarity values ​​using the Cosinr Similarity with threshold 80%. This system can diagnose 3 diseases based on 23 existing symptoms.Based on the results of the test case obtained the results: the system can take back the old case is appropriate and has used the formulation of Naïve Bayes method to distribution of disease class and used the formulation of Cosine Similarity method to calculation correctly indicated with 100% accuracy, and use 122 cases. . Based on the test of 40 new cases obtained system accuracy of 80%.
ALGORITMA MD5 DAN RC5 UNTUK PENGAMANAN FILE PDF Manuel Luis Belo; Derwin Rony Sina; Yelly Yosiana Nabuasa
J-Icon : Jurnal Komputer dan Informatika Vol 8 No 1 (2020): Maret 2020
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v8i1.2396

Abstract

Electronic documents are digital file types used to store the important data or information of a person or an institution. There are some of the most widely used document file formats that are. docx,. xlsx,. pptx, and. pdf. Issues that arise when a company, institution or organization that has confidential documents and important data in the form of document files can be accessed by persons or parties who have no authority. A document security solution can use cryptographic onsep. The document file types that can be encrypted are restricted to the Portable Document Format (. pdf) file. In this research is done lock security user input using the algorithm Message Digest 5 (MD5) and binary value multiplier in PDF files using Rivest Code algorithm (RC5). The test results using (i) the same key on a different PDF file indicate that the resulting binary chiperfile is different from the derived binary Plainfile, (ii) the key length of 1 to 8 characters on the same PDF file indicates that binary The chiperfile generated each key length differs from the binary plainfile taken, (iii) a change of 1 character at the beginning, in the middle, and at the end of the input key indicates that the method used is sensitive to the character changes on the key Input. It is known from the level of similarity of binary chiperfile and small/low binary plainfile based on the value of the collation generated per test is (i) 0.205795252, (ii) 0.24692765, (iii) 0.22421886.
Co-Authors Abineno, Patrisius Adriana Fanggidae Agus Harjoko Alokamating, Abath Timothy Bloemhard, Putri E Boru, Meiton Clarissa Elfira Amos Pah Fanggidae, Adriana Farhan, Ahmad Z. Juan Rizky Mannuel Ledoh Kalvein Rantelobo Kornelis Letelay Koroh, Vladimir Ivan Manuel Luis Belo Marselina Elisabeth Soinbala Mauk, Imanuel Brian Calvin Meiton Boru Nabuasa, Yelly Yosiana Nalle, Olsen Junior Nelci Dessy Rumlaklak NEUTRINO KUSRORONG SAE BELAUDIN KUSRORONG Pah, Clarissa Elfira Amos Pandie, Emerensye Sofia Yublina Polly, Yulianto Triwahyuadi Rumlaklak, Nelci Dessy Tagi Huma, Alexander William Tiwuk Widiastuti Yelly Yosiana Nabuasa