Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : INTEGER: Journal of Information Technology

Modifikasi Kombinasi Particle Swarm Optimization dan Genetic Algorithm untuk Permasalahan Fungsi Non-Linier Kurniawan, Muchamad; Suciati, Nanik
INTEGER: Journal of Information Technology Vol 2, No 2 (2017): September 2017
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (539.078 KB) | DOI: 10.31284/j.integer.2017.v2i2.177

Abstract

Particle Swarm Optimization (PSO) is the population-based optimization algorithm and the generation of random values. The deficiency of the PSO algorithm is prematurely convergent, meaning it quickly finds solutions to local solutions. PSO tidak mampu untuk mencari ruang solusi lebih luas. PSO can not afford to search for wider solution space. In this study modification of the combination of PSO with Genetic Algortihm (GA) or we call M-PSOGA. The advantage of GA taken is to find a wider solution space. M-PSOGA is evaluated on non-linear function problem. The results obtained by M-PSOGA produce the best solution from its predecessor method, PSO and PSOGA. Better on the results of the solutions obtained and the convergent velocity on global solutions.Keywords: Particel Swarm Optimization, Genetic Algorithm, Non-Linier Function.
Algoritma Steganografi untuk Pengamanan Data Teks ke dalam Citra Digital Menggunakan XOR Sederhana Kurniawan, Muchamad; Agustini, Siti
INTEGER: Journal of Information Technology Vol 3, No 2 (2018)
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (358.845 KB) | DOI: 10.31284/j.integer.2018.v3i2.416

Abstract

Kerahasiaan data atau informasi merupakan hal yang sangat penting untuk dijaga dari seseorang yang tidak berhak atas data tersebut. Salah satu solusi untuk pengamann data adalah dengan steganografi. Steganografi merupakan ilmu untuk penyisipan informasi rahasia ke dalam pesan yang lain. Pada penelitian ini, konsep steganografi menggunakan pesan teks yang disembunyikan ke dalam suatu citra digital. Citra yang digunakan adalah citra dalam bentuk grayscale. Penelitian dilakukan sebanyak 5 kali dengan ukuran pesan teks yang berbeda-beda. Hasilnya, system steganografi berjalan dengan baik dimana semua pesan teks dapat dienkripsi dan didekripsi kembali. Running time akan semakin tinggi ketika ukuran pesan teks semakin besar dan begitu juga dengan nilai entropy sehingga tingkat keamanan dari proses steganografi ini semakin tinggi. Kata Kunci: Steganografi, XOR, running time, entropy.
Implementasi Multilayer Perceptron Pada Jaringan Saraf Tiruan Untuk Memprediksi Nilai Valuta Asing Hadimarta, Tommy Ferdian; Muhima, Rani Rotul; kurniawan, muchamad
INTEGER: Journal of Information Technology Vol 5, No 1: April 2020
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (332.448 KB) | DOI: 10.31284/j.integer.2020.v5i1.909

Abstract

Abstract. In the context of FOREX investment, the fluctuation of currency becomes a common thing in which movement is greatly influenced by supply and demand. If the demand is higher, the price will increase and conversely, if the supply is higher, the price will go downward. There is a principle that the behavior of price patterns will repeat randomly and make unpredictable movement of FOREX. These patterns of currency fluctuation have deceived many investors and brought losses and even capital failure. Basically, the value of foreign exchange belongs to the data of time series and Multilayer Perceptron is very suitable to process data of time series as it is often used to make prediction. Therefore, this research aimed at implementing Multilayer Perceptron in the artificial nerve network for predicting the value of foreign exchange on the available resources using the attributes of open, high, low, and close. To process the data from the existing attributes, there must be initialization first in X1 (open), X2 (high), and X3 (low) as the inputs and Y (close) as the data target, and then they were normalized so as to calculate sigmoid. The increasing number of epoch does not guarantee that the errors will be smaller. On the contrary, perhaps, the error value will increase. The best result of training occurred by epoch 200 and learning rate 3 within the smallest values of MSE 281.02518, MAD 13.168, and deviation standard 10.294.
Review Pemanfataan Data Electroencephalogram (EEG) dengan metode Convolution Neural Network Kurniawan, Muchamad; Rachman, Andy; Pakarbudi, Adib
INTEGER: Journal of Information Technology Vol 6, No 2: September 2021
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.integer.0.v6i2.2419

Abstract

Electroencephalogram (EEG) is a brain data signal that is captured by sensors. Many studies have used EEG to be used as a decision maker or classifying. What classification has been used most frequently in existing studies over the last 5 years? These are the questions that will be answered in this research. In addition to these questions, another question that will be answered is what is the most popular method used in processing EEG data? The final question in research is the recent development of EEG and CNN research. The results of these answers are the most popular research using the CNN method as a classification method, the application of the field of Human-computer InterfacesKeywords: Electroencephalogram, Convolution Neural Network.  
Analisis Fast Moving Consumer Goods untuk Memprakirakan Penjualan Barang Menggunakan Metode Triple Exponential Smoothing Ar, Nanda Hafiz; Kurniawan, Muchamad
INTEGER: Journal of Information Technology Vol 6, No 2: September 2021
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.integer.0.v6i2.2311

Abstract

Fast Moving Consumer Goods (FMCG) refers to a business sector generating economy particularly in Indonesia. The movement of goods runs quickly as they belong to staple food and have relatively short shelf life. They are sometimes unpredictable and even out of stock specifically to goods in fast moving category. Consequently, business doers can lose opportunities. Therefore, sale prediction is necessary to reduce opportunity loss and stock piling upon the goods that should not be ordered excessively. This research conducted prediction through Triple Exponential Smoothing method in the period of January 2018 to June 2020 by taking 5 item samples that were then tried out using alpha 0.1 – 0.9. As a result, alpha 0.1 became the best alpha in this research compared to alpha 0.2 – 0.9. Out of 5 trials, alpha 0.1 (MAPE 22%, 19%, and 34%) occurred three times and alpha 0.2 (MAPE 34% and 11%) happened twice. However, this research has not obtained the best result yet as it has not satisfied the indicator of more than 10% whole MAPEs. Thus, Triple Exponential Smoothing Brown was less appropriate to the data being used. The calculation of estimation did not consider the data fluctuation such as Ramadhan event greatly affecting the data training and forecasting result