Garuda - Garba Rujukan Digital

Credit risk prediction using neural network backpropagation algorithm Maradu Sihombing; Erwin D . Sitanggang; Maranata Pasaribu; Misdem Sembiring
INFOKUM Vol. 10 No. 1 (2021): Desember, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (765.166 KB)

Credit is a business activity that contains high risk and greatly affects the health and survival of banking businesses and financing institutions. Predicting credit risk is very beneficial for banks or financing institutions in taking decisions to establish credit. Decision makers of banks and financing institutions must have the precautionary principle to minimize credit risk when credit will be provided. The study designed credit risk prediction software with artificial neural network methods backpropagationalgorithms. Artificial neural network backpropagation with 1 hidden layer and the amount of data for training and testing as many as 20 pieces consisting of 5 models and using the logsig activation function is able to predict credit risk with a truth percentage of 70%-80%. Training and testing is used using matlab 6.1 software. Based on these results, the study recommends the development of artificial neural network algorithms as an effective method on credit risk prediction systems.

Analysis of Elearning Quality Measurement With Webqual Method at Politeknik MBP Medan Erwin Daniel Sitanggang; Maradu Sihombing; Maranata Pasaribu; Beny Irawan
INFOKUM Vol. 10 No. 1 (2021): Desember, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (344.355 KB)

The development of information technology today has also changed the lifestyle and way of life of many people. By using information technology, many people can explore the world without being limited by space and time through the internet. Information technology has become a tool that has the power as a driving force that changes business, economics, socio-politics and other fields without limits. One of the things that has experienced major changes in lifestyle and way of life in the field of education is teaching and learning activities. The Politeknik MBP Medan college, which was also affected by Pandami, had to change the teaching-learning method using the Learning Management System service which is the right teaching-learning method to provide learning materials to students, in this case called students. In order to obtain the quality of this service, first, the satisfaction level of service users is measured based on the standard of comparison (gap) between reality and the expectations of users of the service. Based on the results of quality measurements from e-learning at the Politeknik MBP Medan for the academic year 2020/2021 in the even semester using the Webqual method, it was concluded that the Webqual method along with its attributes can provide analytical results to be used in improving the performance quality of e-learning. The results of measuring the quality of the data processing of respondents' answers are obtained that the User Satisfaction Level Score is -0.18, this indicates that the quality of e-learning as a whole is not in line with the expectations of users. The results of the analysis of 22 statement attributes from the Webqual method show that all attributes get the results of the "Tingkatkan" pattern analysis and none of the statement attributes get the "Pertahankan" pattern.

Analysis of Elearning Quality Measurement with Webqual method using Artificial Neural Networks Erwin Daniel Sitanggang; Misdem Sembiring; Anjar Pinem; Maranata Pasaribu
INFOKUM Vol. 10 No. 02 (2022): Juni, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (469.138 KB)

Currently, artificial intelligence is a concern for the world because of its increasingly rapid and sophisticated application in helping humans to complete their work in everyday life. One of the widely used methods is artificial neural networks that are part of deep learning and a subsection of machine learning. In its network training, the data used as input is the gap score of each webqual dimension and the data used as the output is the gap score of the average webqual attributes of each respondent. The training process is expected to produce an actual output close to the predetermined target output, resulting in the best model of artificial neural networks with feedforward backpropagation algorithms. From the results of the training experiment, the best model of artificial neural network architecture was obtained with a feedforward backpropagation algorithm at the time of training from 174 data to be able to replace the Webqual method in this study using the 3-20-1 model and the algorithm used was Levenberg-Marquardt (trainln). Where there is 1 Input layer with 3 neuron units, 1 hidden layer with 20 neuron units and 1 Output layer with 1 neuron unit with a mean square error (mse) of 0.00000000000721 and regression of 1 or 100%. And after testing using 58 data using the network configuration obtained during training, the results of the comparison between the network output and the target were 100% accurate.

IMPLEMENTATION OF FUZZY LOGIC TO DETERMINE THE BEST EMPLOYEES Maranata Pasaribu; Sartana Sartana; Sariadin Siallagan; Ratnawati Simbolon
INFOKUM Vol. 10 No. 5 (2022): December, Computer and Communication
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar

Employees are people who are able to work and produce goods and services for their own needs and society. Every company really yearns for employees who are able to work professionally so that the company's targets can be met. How does the company motivate employees by rewarding the best employees so that employees are motivated to work. Selection of the best employees by setting 5 (five) criteria, namely: Discipline, Loyalty, Communication, Attendance and Problem Solving. The assessment is carried out by taking attendance data and observation visually. The Fuzzy Tsukamoto method is used to obtain accurate, relevant and quickly presented results. Developed an information system to be able to produce the right decision by processing 5 (five) criteria data whose processing combines all criteria values and high rated values as the BEST value.

Perancangan Simulator Interlock Protocol saat Serangan Man-in-the-Middle-Attack pada Kriptografi Kunci Publik RSA Maranata Pasaribu; Marice Hotnauli Simbolon
LOFIAN: Jurnal Teknologi Informasi dan Komunikasi Vol 1 No 1 (2021): September
Publisher : Universitas Mandiri Bina Prestasi (MBP)

Dalam proses transmisi data, walaupun data telah dienkripsi, namun terdapat kemungkinan bahwa data tersebut dapat dimiliki oleh orang lain. Salah satu kemungkinan tersebut adalah dengan terjadinya penyadapan media komunikasi yang digunakan oleh kedua orang yang sedang berkomunikasi tersebut. Problema man-in-the-middle-attack ini dapat dicegah dengan menggunakan interlock protocol. Algoritma inti dari protokol ini yaitu mengirimkan 2 bagian pesan terenkripsi. Bagian pertama dapat berupa hasil dari fungsi hash satu arah (one way hash function) dari pesan tersebut dan bagian kedua berupa pesan terenkripsi itu sendiri. Penelitian ini akan merancang perangkat lunak simulasi yang dapat menjelaskan proses kerja dari man-in-the-middle-attack dalam menyadap dan mengubah pesan, menjelaskan proses kerja interlock protocol untuk mengatasi problema Man-In-The-Middle-Attack. Setelah menyelesaikan perangkat lunak simulasi, peneliti menarik kesimpulan: Dengan menggunakan interlock protocol, walaupun kunci publik pihak penerima dan pengirim didapatkan dan diganti oleh penyadap, tetapi penyadap tidak dapat menjalankan prosedur man-in-the-middle-attack untuk melihat dan mengubah pesan. Hal ini dikarenakan pesan terenkripsi terbagi menjadi dua bagian pada variasi pertama dan terdapat fungsi hash untuk memverifikasi keaslian pesan pada variasi kedua.

Perancangan Simulator Interlock Protocol saat Serangan Man-in-the-Middle-Attack pada Kriptografi Kunci Publik RSA Maranata Pasaribu; Marice Hotnauli Simbolon
LOFIAN: Jurnal Teknologi Informasi dan Komunikasi Vol 1 No 1 (2021): September
Publisher : Universitas Mandiri Bina Prestasi (MBP)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58918/lofian.v1i1.157

Dalam proses transmisi data, walaupun data telah dienkripsi, namun terdapat kemungkinan bahwa data tersebut dapat dimiliki oleh orang lain. Salah satu kemungkinan tersebut adalah dengan terjadinya penyadapan media komunikasi yang digunakan oleh kedua orang yang sedang berkomunikasi tersebut. Problema man-in-the-middle-attack ini dapat dicegah dengan menggunakan interlock protocol. Algoritma inti dari protokol ini yaitu mengirimkan 2 bagian pesan terenkripsi. Bagian pertama dapat berupa hasil dari fungsi hash satu arah (one way hash function) dari pesan tersebut dan bagian kedua berupa pesan terenkripsi itu sendiri. Penelitian ini akan merancang perangkat lunak simulasi yang dapat menjelaskan proses kerja dari man-in-the-middle-attack dalam menyadap dan mengubah pesan, menjelaskan proses kerja interlock protocol untuk mengatasi problema Man-In-The-Middle-Attack. Setelah menyelesaikan perangkat lunak simulasi, peneliti menarik kesimpulan: Dengan menggunakan interlock protocol, walaupun kunci publik pihak penerima dan pengirim didapatkan dan diganti oleh penyadap, tetapi penyadap tidak dapat menjalankan prosedur man-in-the-middle-attack untuk melihat dan mengubah pesan. Hal ini dikarenakan pesan terenkripsi terbagi menjadi dua bagian pada variasi pertama dan terdapat fungsi hash untuk memverifikasi keaslian pesan pada variasi kedua.

Research And Community Service Information System At LPPM Universitas MBP Medan With Unified Modeling Language (UML) Fauzi Haris Sibolon; Sartana, Sartana; Pasaribu, Maranata; Bangkit Iyoel Siregar
Jurnal Info Sains : Informatika dan Sains Vol. 14 No. 03 (2024): Informatika dan Sains , Edition July - September 2024
Publisher : SEAN Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar

Universitas Mandiri Bina Prestasis (UMBP) which was established in 2022 as a merger of two institutions, namely AMIK MBP with the Vocational Education program D-III Informatics Engineering and D-III Informatics Management and STIKOM with the S1 Informatics Engineering and S1 Information Systems Study Programs and the addition of 3 new study programs, namely S1 Software Engineering, S1 Accounting and S1 Entrepreneurship. Along with that, UMBP was born and developed with a commitment that was stated in the Vision of Becoming a Superior and Independent University in the field of Information Technology and Business with an Entrepreneurial Spirit at the National level in 2036 "by developing various superior programs in the fields of research, innovation, and community service, as well as the Regulation of the Minister of Research, Technology, and Higher Education (Permenristekdikti) number 44 of 2015 concerning National Standards for Higher Education, so every university must make adjustments towards meeting the standards of education, research and community service. UMBP has one institution that is tasked with research and development called the Institute for Research and Community Service (LPPM). This institution is a forum for academics to carry out research and community service. The establishment of LPPM is UMBP's strategy in an effort to realize the improvement of quality and development of technology, social and business in higher education and its implementation in the community.

Sistem Pendukung Keputusan Pemilihan Karyawan Terbaik Metode Simple Additive Weighting (SAW) (Studi Kasus di PT MNC Sky Vision Tbk) Simbolon, Marice Hotnauli; Sartana; Maranata Pasaribu
Jurnal Mahajana Informasi Vol 8 No 1 (2023): JURNAL MAHAJANA INFORMASI
Publisher : Universitas Sari Mutiara Indonesia Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51544/jurnalmi.v8i1.4311

MNC Sky Vision (formerly known as PT Matahari Lintas Cakrawala) is a company involved in operating the first Pay TV in Indonesia. The problem of evaluating employee performance is something that cannot be avoided in today's world of work. Assessment by voting with the most votes is still considered ineffective because the measurement of values is still guided by interpersonal relationships and the principle of conscience. To be able to improve the quality of good employee performance and to be able to support the company's progress, especially at PT MNC Sky Vision Tbk, the agency needs a stage of improvement and system development in a good and directed management process, based on this the researcher wants to provide a solution to solving the problem through the title research “Decision Support System for Selection of the Best Employees Simple Additive Weighting (SAW) Method (Case Study at PT MNC Sky Vision Tbk).

Aplikasi Perbaikan Citra Digital Berbasis Android Dengan Metode Histogram Equalization Matondang, Zekson Aizona; Pasaribu, Maranata
KAKIFIKOM : Kumpulan Artikel Karya Ilmiah Fakultas Ilmu Komputer Volume 6, Nomor 2, Edisi Oktober 2024
Publisher : UNIKA Santo Thomas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54367/kakifikom.v6i2.4568

Digital images (photos) have become an integral part of everyday life. This is supported by the increasingly sophisticated technology today where communication devices such as mobile phones can also use their role to replace analog cameras to take pictures or even record videos. Capturing happy moments or just wanting to record an event has become very easy to do, but sometimes the resulting photos are less than satisfactory due to the specifications of the mobile phone itself or other factors such as poor lighting (dark). Improvement efforts are also very necessary, but because the application to do this is only available on computers and not too many on mobile phones, this becomes difficult to do. One method in image improvement is the Histogram Equalization method. This method can be used to improve image quality related to lighting, namely by maintaining color constancy. The use of this histogram equalization method is considered easy because of its efficiency and relatively better performance on almost all types of images. The operation of HE (Histogram Equalization) is carried out by remapping the gray image level based on the probability distribution of the input gray level. It horizontally and dynamically stretches the various histograms of the image and produces an overall increase in contrast.

Implementasi Algoritma Principal Component Analisys dan Jaringan Syaraf Tiruan Dalam Mengoptimasi Fitur dan Performa Intrusion Detection System Fauzi Haris Simbolon; Maranata Pasaribu; Marice Hotnauli Simbolon; Maradu Sihombing; Sartana
LOFIAN: Jurnal Teknologi Informasi dan Komunikasi Vol 5 No 1 (2025): Agustus
Publisher : Universitas Mandiri Bina Prestasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58918/yyzrza47

Mengamankan data dan informasi merupakan aktivitas yang sangat dibutuhkan dalam dunia idustri, bisnis maupun perkantoran terutama terkait dengan data dan informasi yang dikirim melalui jaringan. Intrusion Detection System atau Sistem deteksi intrusi (IDS) merupakan suatu produk perangkat keras atau perangkat lunak yang mampu mendeteksi aktivitas yang janggal, aneh dan mengandung unsur bahaya di jaringan komputer atau di host yang terpisah. IDS hanya memantau lalu lintas yang disalin, dan memberi peringatan, bahwa paket yang sebenarnya bermasalah telah terkirim ke target yang dituju. Bahkan jika telah dilakukan pengaturan IDS untuk memperbarui firewall dengan aturan pemblokiran, paket serangan awal sudah terlanjur masuk Pelaksanaan proses intrusi berkecepatan tinggi tentunya akan menimbulkan beberapa kendala yang cukup signifikan terutama masalah dimensionalitas yang sangat besar, untuk itu dibutuhkan algoritma Principal Component Analisys (PCA) untuk menangani masalah tersebut, dengan algoritma ini memungkinkan peningkatan kinerja pengklasifikasian Jaringan Syaraf Tiruan (JST) dalam deteksi intrusi. Melalui bantuan algoritma PCA dapat diidentifikasi 15 fitur teratas dari 41 fitur yang terdapat pada kumpulan fitur KDD Cup 1999, dan perolehan peningkatan lebih dari 62% pada saat pelatihan JST. melalui pengujian menggunakan JST dapat disimpulkan bawa Jaringan Saraf Tiruan Multi Layer Perceptron dapat meningkatkan akurasi bahkan setelah mereduksi fitur-fitur yang ada.

Title

Found 14 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 14 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 14 Documents
Search