Article Per Year (5 Year)
p-Index From 2020 - 2025
0.444
P-Index
This Author published in this journals
All Journal HUMAN FALAH: Jurnal Ekonomi dan Bisnis Islam Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer) Jurnal Ilmiah Sistem Informasi dan Ilmu Komputer
Dedi Suhendro
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
ANALISIS PROFITABILITAS DAN LIKUIDITAS UNTUK MENILAI KINERJA KEUANGAN PADA PT SIANTAR TOP Tbk Dedi Suhendro
HUMAN FALAH: Jurnal Studi Ekonomi dan Bisnis Islam HUMAN FALAH: Jurnal Ekonomi dan Bisnis Islam | Vol. 4 | No. 2 | 2017
Publisher : Fakultas Ekonomi dan Bisnis Islam Universitas Islam Negeri Sumatera Utara

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

Abstract

The purpose of this study is to assess the company's financial performance at PT Siantar Top Tbk with the use of financial ratio analysis during the period of 2011-2015. The financial ratios used are profitability and liquidity. Profitability ratios at PT Siantar Top Tbk show an efficient company performance in terms of average Net Profit Margin ratio as it is above the industry average (time series). The Return On Asset (ROA) ratio is also efficient because the company's net profit tends to increase and is above the industry average (time series). The average value of the Return On Equity (ROE) ratio below the industry average (time series) for financial performance is said to be inefficient. Analysis of Liquidity Ratio (Likuidity Ratio) when viewed from the Current Ratio indicates the condition of corporate liquidity is not good, the calculation of the average Current Ratio is below the industry average (time series) for financial performance is said ILLikuid (not good). The calculation of the average Quick Ratio is below the industry average (time series) for financial performance is said IL Liquid (not good).
PENERAPAN ALGORITMA K-MEDOIDS UNTUK MENGELOMPOKKAN PENDUDUK 15 TAHUN KEATAS MENURUT LAPANGAN PEKERJAAN UTAMA Nurliana Pulungan; Suhada Suhada; Dedi Suhendro
KOMIK (Konferensi Nasional Teknologi Informasi dan Komputer) Vol 3, No 1 (2019): Smart Device, Mobile Computing, and Big Data Analysis
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/komik.v3i1.1609

Abstract

The main occupations in 15 years and above are on average not suitable for their age, which is done by adults but is done by people 15 years and older. Therefore, I do grouping data on population 15 years and above so that we know what their main jobs are. Here I use data mining with the K-Medoids method to classify the population of 15 years according to the main occupation, this research was conducted in Indonesia. The K-Medoids method is a method of collecting data with the classic clustering partitioning technique that groups datasets from n objects into K groups known a priori. A useful tool for determining k is a silhouette. It is stronger to be agreed upon and bigger than K-Means because it must add to the difference in the difference in the square of the euclidean distance. Attractions that can be determined as cluster objects are average differences for all objects in the cluster are minimal. That is the easiest point in the cluster. K-Medoids uses objects in a collection of objects to represent a cluster. The object chosen to represent a cluster is called medoid. Clusters are built by calculating the proximity they have between a medoid and non-medoid objects.Keywords: Data mining, K-Medoid, Main Job Fields 15 years and above
ANALISIS TINGKAT KEPUASAN PENGGUNA GOOGLE CLASSROOM DALAM PEMBELAJARAN ONLINE MENGGUNAKAN ALGORITMA NAÏVE BAYES Fildzah Nadya Arieni; Eka Irawan; Dedi Suhendro
Jurnal ilmiah Sistem Informasi dan Ilmu Komputer Vol. 2 No. 3 (2022): November : Jurnal ilmiah Sistem Informasi dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/juisik.v2i3.327

Abstract

SMK Negeri 3 Pematangsiantar is one of the schools affected by the COVID-19 pandemic, which at that time the whole world was facing an outbreak of this infectious disease. The Covid-19 pandemic that was hitting the whole world at that time, required all students and students to carry out the online learning process in order to prevent the spread of the Covid-19 virus. This study aims to classify the level of satisfaction of Google classroom users using nave Bayes data mining techniques. Sources of data obtained from questionnaires given to students randomly as many as 100 students. The criteria used as Google Classroom user satisfaction include: system quality, service, information, usage, user satisfaction. The model generated by researchers and Rapid Miner Software with training data as much as 75 data. There are 25 test data that are processed in Rapid Miner 5.3. get test results with an accuracy of 96.00%, namely 15 satisfied users and 10 dissatisfied users.
Comparative Analysis of Gradient Descent Learning Algorithms in Artificial Neural Networks for Forecasting Indonesian Rice Prices Rica Ramadana; Agus Perdana Windarto; Dedi Suhendro
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 8 No 4 (2024): August 2024
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v8i4.5822

Abstract

Artificial Neural Networks (ANN) are a field of computer science that mimics the way the human brain processes data. ANNs can be used to classify, estimate, predict, or simulate new data from similar sources. The commonly used algorithm for prediction in ANN is Backpropagation, which yields high accuracy but tends to be slow during the training process and is prone to local minima. To address these issues, appropriate parameters are needed in the Backpropagation training process, such as an optimal learning function. The aim of this study is to evaluate and compare various learning functions within the Backpropagation algorithm to determine the best one for prediction cases. The learning functions evaluated include Gradient Descent Backpropagation (traingd), Gradient Descent with Adaptive Learning Rate (traingda), and Gradient Descent with Momentum and Adaptive Learning Rate (traingdx). The dataset used is the average wholesale rice price in Indonesia, obtained from the Central Statistics Agency (BPS) website. The evaluation results show that the traingdx learning function with a 5-5-1 architecture model achieves the highest accuracy of 83.33%, representing an 8.3% improvement over the traingd and traingda learning functions, which both achieved a maximum accuracy of 75%. Based on this study, it can be concluded that using various learning functions in Backpropagation yields better accuracy compared to standard Backpropagation.
Co-Authors Agus Perdana Windarto Eka Irawan Fildzah Nadya Arieni Nurliana Pulungan Rica Ramadana Suhada Suhada