Article Per Year (5 Year)
p-Index From 2019 - 2024
0.61
P-Index
This Author published in this journals
All Journal SisInfo : Jurnal Sistem Informasi dan Informatika
Firdaniza Firdaniza
Departemen Matematika, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Padjadjaran
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Peramalan Data Univariat Menggunakan Metode Long Short Term Memory Helma Syifa Izzadiana; Herlina Napitupulu; Firdaniza Firdaniza
SisInfo Vol 5 No 2 (2023): SisInfo
Publisher : Universitas Informatika dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37278/sisinfo.v5i2.669

Abstract

Peramalan data univariat mengacu pada kegiatan meramalkan nilai pada data dengan satu variabel independen yang mungkin muncul di masa depan berdasarkan nilai-nilai yang ada di masa lalu. Penelitian ini bertujuan untuk memperoleh model yang dibangun menggunakan pendekatan deep learning jenis supervised learning yaitu metode Long Short Term Memory (LSTM) yang diterapkan pada data univariat. Metode LSTM merupakan pengembangan dari metode Recurrent Neural Network (RNN) dengan menambahkan 3 gate yang mampu memilih informasi yang dibutuhkan untuk pelatihan sel sehingga mampu mengurangi kemungkinan exploding gradients dan vanishing gradients. Model dibangun dengan input layer LSTM dengan unit sel dan output dense layer dengan tambahan hyperparameter tuning yang diset menggunakan optimizer, fungsi aktivasi dan , dan nilai epoch. Performa model peramalan diuji menggunakan mean absolute percentage error (MAPE).
Model Gerak Brown Fraksional Geometrik dalam Peramalan Harga Saham PT Indofood Sukses Makmur Tbk Menggunakan Pemrograman Python Nurhadini Putri; Firdaniza Firdaniza; Nurul Gusriani
SisInfo Vol 6 No 1 (2024): SisInfo
Publisher : Universitas Informatika dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37278/sisinfo.v6i1.798

Abstract

Accurate stock price forecasting is needed by investors. Several methods can be used to forecast stock prices, such as trend models, Autoregressive Integrated Moving Average, Double Moving Average, and Exponential Smoothing. Apart from that, there are also more complex models, such as the Geometric Brownian Motion (GBM) model and the Geometric Fractional Brownian Motion (GFBM) model. The GBM and GFBM models have several advantages, including being able to predict stock prices over short time periods, the suitability of the model to stock price movements which are always positive and do not require a lot of data testing. Moreover, GFBM model can also overcome the problem of actual stock data, most of which are not independent of each other. This research aims to forecast the stock price of PT Indofood Sukses Makmur Tbk (INDF) using the Geometric Fractional Brownian Motion (GFBM) model. The Hurst index in the GFBM model is estimated using Rescaled Range (R/S) with the help of Python programming. The results of forecasting the share price movement of PT Indofood Sukses Makmur Tbk (INDF) using the GFBM model provide very accurate values based on the MAPE value.
Ekstraksi Fitur Berdasarkan Fuzzy Restricted Boltzmann Machine Pada Klasifikasi Fashion-MNIST Dengan Dan Tanpa Noise Muhammad Ribhan Hadiyan; Firdaniza Firdaniza; Herlina Napitupulu
SisInfo Vol 6 No 2 (2024): SisInfo
Publisher : Universitas Informatika dan Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37278/sisinfo.v6i2.876

Abstract

Mixed Accelerated Learning Method based on a Fuzzy Restricted Boltzmann Machine (MAFRBM) was a relatively new feature extraction method on images that had not been widely implemented. MAFRBM had advantages in extracting features from noisy images. Generally, the presence of noise in images could significantly affect the outcome of feature extraction. In this study, feature extraction was performed using MAFRBM on the Fashion-MNIST dataset with and without added noise. The types of noise added to the images were Gaussian, salt & pepper, and Poisson. The features extracted by MAFRBM were then classified using a Support Vector Machine (SVM). The classification results showed the highest accuracy at 88%. Moreover, the comparison of accuracy results from the classification of Fashion-MNIST with noise did not differ significantly from the images without noise.
Co-Authors Helma Syifa Izzadiana Herlina Napitupulu Muhammad Ribhan Hadiyan Nurhadini Putri Nurul Gusriani