cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota pematangsiantar,
Sumatera utara
INDONESIA
J-SAKTI (Jurnal Sains Komputer dan Informatika)
ISSN : 25489771     EISSN : 25497200     DOI : -
Core Subject : Science,
JSAKTI adalah jurnal yang diterbitkan oleh LPPM STIKOM Tunas Bangsa Pematangsiantar yang bertujuan untuk mewadahi penelitian di bidang Manajemen Informatika. JSAKTI (Jurnal Sains Komputer dan Informatika) adalah wadah informasi berupa hasil penelitian, studi kepustakaan, gagasan, aplikasi teori dan kajian analisis kritis dibidang Ilmu Komputer terbit 2 kali setahun.
Arjuna Subject : -
Articles 314 Documents
Penerapan K-Nearest Neighbor Berbasis Genetic Algorithm Untuk Penentuan Pemberian Kredit Ester Arisawati
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (614.67 KB) | DOI: 10.30645/j-sakti.v1i1.24

Abstract

Consumer financing is financing activities for the procurement of goods based on the needs of consumers with payment in installments. While the Financing Company is a business entity specifically set up to conduct leasing, factoring, consumer finance, or business credit card. The finance company will approve the proposed consumer credit after a credit analysis of the feasibility of providing consumer financing, if approved and not disetujui.Dalam analysis process for consumers, there are some that are not accurate, therefore consumers can not afford to pay in a timely manner resulting in bad debts , To solve the problem we need a model that is able to classify and predict consumer data is problematic and not problematic. In this research, testing ie k-Nearest Neighbor and k-Nearest Neighbor optimized genetic algorithm is applied to the data consumer that gets better the consumer credit financing is problematic or not. From the test results by measuring the performance of the three algorithms using Cross Validation testing methods, Confusion Matrix and ROC curves, it is known that the k-Nearest Neighbor algorithm optimized Genetic Algorithm has the AUC value and highest accuracy.
Implementasi JST Dalam Menentukan Kelayakan Nasabah Pinjaman KUR Pada Bank Mandiri Mikro Serbelawan Dengan Metode Backpropogation Agus Perdana Windarto
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (668.735 KB) | DOI: 10.30645/j-sakti.v1i1.25

Abstract

The purpose of this study was to develop a decision support system that can facilitate in determining the eligibility of borrowers KUR (Kredit Usaha Rakyat) through predictive use based on existing data and presents various alternative solutions in the selection of a feasibility customers in KUR loan. This study uses Artificial Neural Network applications using Backpropogation method. Criteria used as an assessment in this study is Collateral, Capacity, Loan Application Form, Income and Establishment Business License (Business License). The decision making process consists of two (2) phases where the first phase and pattern recognition, the second phase is forecast feasibility KUR customers. pattern recognition and predictive feasibility KUR customers using different data with the same process using training and testing. The conclusion by the two architectural models 5-2-1 and 5-3-1, obtained 93% accuracy with 0.0009995807 MSE is the 5-2-1 model architecture. This model is used to predict the feasibility of KUR customers with accuracy> 90% and MSE truth 0.0009566280.
Jaringan Saraf Tiruan Untuk Memprediksi Tingkat Pemahaman Sisiwa Terhadap Matapelajaran Dengan Menggunakan Algoritma Backpropagation Solikhun Solikhun; M. Safii; Agus Trisno
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (807.706 KB) | DOI: 10.30645/j-sakti.v1i1.26

Abstract

Prediction of students 'understanding of the subject is important to know the extent to which the students' understanding of the subjects presented by educators when teaching and learning activities and to determine the ability of educators in delivering subjects. Artificial Neural Network to predict the level of students' understanding of subjects using backpropagation learning algorithm uses several variables: Knowledge, skills / abilities, assessment and workload and guidance and counseling. Backpropagation learning algorithm is applied to train eight indicators to predict the level of students' understanding of the subjects. The test results obtained by the student's understanding level prediction accuracy rate of 90% with a 6-5-1 architecture.
Analisa Kemanfaatan Dan Kemudahan Terhadap Penerimaan Sistem OPAC Menggunakan Metode TAM Citra Kharismaya; Linda Sari Dewi; Ester Arisawati; Frisma Handayanna
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (804.684 KB) | DOI: 10.30645/j-sakti.v1i1.27

Abstract

This study describes the reception OPAC Davis 1989 TAM variables namely perceived usefulness (perceived benefit), perceived ease of use (ease perceived) and accepted (acceptance) OPAC. In this study, data were collected through a questionnaire using Likert scale to 100 users siĀ¬stem den response OPAC (Online Public Access Catalog). Sampling technique used is purposive sampling to determine the level of acceptance of the system OPAC (Online Public Access Catalog). Quantitative analysis includes the validity, reliability. In the classic assumption test, used test for normality, multicollinearity and heterokedastisitas with F and t hypothesis testing. Multiple linear regression analysis is used to determine the effect of the independent variables with the dependent variable. The results showed that perceived usefulness and perceived ease have a significant effect on the acceptance by the user system (R Square) amounted to 40.8%.
Penentuan Penilaian Kredit Menggunakan Metode Naive Bayes Berbasis Particle Swarm Optimization Rinawati Rinawati
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (851.253 KB) | DOI: 10.30645/j-sakti.v1i1.28

Abstract

Bad credit is one of the credit risk faced by the financial and banking industry. Bad credit can be avoided by means of an accurate credit analysis of the debtor. The accuracy of credit ratings is crucial to the profitability of financial institutions. Improved accuracy of credit ratings can be done by doing the selection of attributes, because the selection of attributes reduce the dimensionality of the data so that operation of the data mining algorithms can be run more effectively and more cepat.Banyak research has been conducted to determine credit ratings. One of the methods most widely used method of Naive Bayes. In this study will be used method Naive Bayes and will do the selection of attributes by using particle swarm optimization to determine credit ratings. After testing the results obtained are Naive Bayes produce accuracy value of 72.40% and AUC value of 0.765. Then be optimized by using particle swarm optimization results show values higher accuracy is equal to 75.90% and AUC value of 0.773. So as to achieve the increased accuracy of 3.5%, and increased the AUC of 0.008. By looking at the accuracy and AUC values, the Naive Bayes algorithm based on particle swarm optimization into the classification category enough.
Sistem Penyeleksi Warna Dan Berat Barang Menggunakan Pergerakan Lengan Robot Empat DOF (Degree Of Freedom) Abdullah Abdullah
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (985.265 KB) | DOI: 10.30645/j-sakti.v1i1.29

Abstract

The use of robot arm in the system of colour and weight box selection has been done to integrate control system of robot arm moving with colour sensor TCS3200 and weight sensor load cell. The research was conducted by analyzing efficiency and accuracy system of robot arm moving to select colour and weight goods like box. The robot arm moving work suitable instruction of colour and weight sensor reading. At the most important from this system is how to accuracy of colour and weight sensor to detect colour ang weight and accuracy of robot arm moving system can positioning degree moving to take colour with different weight box suitable the place. The result of the analysis proved that robot arm moving had inregrated with colour and weight sensor efficient and effective to do this work as colour and weight box selection accurately.
Metode Hybrid Particle Swarm Optimization - Neural Network Backpropagation Untuk Prediksi Hasil Pertandingan Sepak Bola Muhammad Ridwan Lubis
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (809.3 KB) | DOI: 10.30645/j-sakti.v1i1.30

Abstract

Hybrid is using two methods to a problem with the aim to improve their approach towards the specified target data. Hybrid PSO-ANN one optimal algorithm to solve such predictions in football matches. The process begins with determining the outcome of test dataset with the neural network architecture, specify the input parameters, the value of weight up to the value of hidden layer and output layer. Then the optimization of the results of the first test on a training dataset optimized by Particle Swarm Optimization. Testing will continue over using back propagation neural network until the maximum iteration and the results of the initial approach the target value. Furthermore, from the output obtained to search the value of the average error.
Analisis Perbandingan Toolkit Puran File Recovery, Glary Undelete Dan Recuva Data Recovery Untuk Digital Forensik Handrizal Handrizal
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1317.265 KB) | DOI: 10.30645/j-sakti.v1i1.31

Abstract

This paper presents a comparative analysis of three digital forensics toolkit for data recovery scenario that has been deleted. Toolkit used is Puran File Recovery, Glary Undelete and Recuva Data Recovery. Their ability to restore deleted data has been tested and analyzed in a USB flash drive. The results of the comparison show that this third toolkit can work well in terms of finding the data that has been deleted or in recovering the deleted data.
Implementasi Web Commerce Sebagai Media Pelatihan Kewirausahaan Mahasiswa M. Safii
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (853.803 KB) | DOI: 10.30645/j-sakti.v1i1.32

Abstract

This study proposes a dynamic web-based information system using a content management system (CMS) osCommerce with PHP programming language and MySQL database. Utilization of a dynamic web Content Management System has advantages of easy and friendly in content management. Realtime information dissemination network using the Internet will bring up a quick response from the customer as the target market so that the main goal of entrepreneurial activity is achieved. With the implementation of web commerce information system is expected to be a solution for students as a means of self-employment training that has relevance to the subject so that students will have confidence in the start up of entrepreneurial activity as an effort to create their own jobs for students.
Fuzzy Query Database Untuk Sistem Pendukung Keputusan Yang Cerdas Poningsih Poningsih; Jalalludin Jalalludin
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 1, No 1 (2017): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (622.144 KB) | DOI: 10.30645/j-sakti.v1i1.33

Abstract

The process of education and teaching is one of the acts of Tri Dharma College. The success of the learning process can not be separated from the role of a lecturer. Quality of faculty plays an important role in a college that wants to achieve the goal of teaching and learning processes that produce graduates (output) quality. Lecturer rated quality if it has the value of a good performance, which is reviewed from several aspects. This paper proposes an analysis based on the evaluation of faculty performance feedback using fuzzy query the database for intelligent decision support system. The value of diverse faculty performance, so as to the criteria of each lecturer is still ambiguous and still need to be clarified. Here will be determined three criteria of assessment of faculty performance is lacking, just and good. Of the three criteria are later obtained a recommendation to make a decision. Model rules obtained is the value of students and professors taken the maximum value, then rules obtained from students and professors taken minimum value, in order to obtain the value of the performance of lecturers as well as the criteria. Then the value of this performance, it can be used by institutions as advice on making a decision relating to a lecturer.

Page 1 of 32 | Total Record : 314