Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal IJCCS (Indonesian Journal of Computing and Cybernetics Systems) Seminar Nasional Aplikasi Teknologi Informasi (SNATI) Seminar Nasional Informatika (SEMNASIF) JRST (Jurnal Riset Sains dan Teknologi) Contemporary Mathematics and Applications (ConMathA)
Edi Winarko
Unknown Affiliation
Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Engineering Materials Science & Nanotechnology Mathematics

Published : 18 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Contemporary Mathematics and Applications (ConMathA)

 1 
Classification of Review Text using Hybrid Convolutional Neural Network and Gated Recurrent Unit Methods Fiqih Fathor Rachim; Auli Damayanti; Edi Winarko
Contemporary Mathematics and Applications (ConMathA) Vol. 4 No. 2 (2022)
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/conmatha.v4i2.38262

Abstract

Consumer reviews are opinions from buyers to sellers based on service satisfaction or product quality. The more consumer reviews cause the process of analyzing manually will be difficult. Therefore, an automated sentiment analysis system is needed. Each review will be grouped into a sentiment class which is divided into positive and negative classes. This study aims to classify review texts using the Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) methods. The research stages in this study include collecting data on Tokopedia review texts, extracting hidden information from review texts using CNN, conducting learning on review texts using GRU. A total of 1000 review texts were divided into 80% training data and 20% test data. The review text is converted into matrix using One Hot Encoding algorithm and then extracted using CNN. The CNN process includes the convolution calculation, the calculation of the Rectified Linear Unit (ReLU) activation function, and the pooling stage. The extraction results in the CNN process are continued in the GRU process. The GRU process includes initializing parameters, GRU feed forward, Cross-Entropy Error calculation, GRU feedback, and updating weights and biases. The optimal weight is obtained when the error value in the training is less than the expected minimum error or the training iteration has reached the specified maximum iteration. Optimal weight is used for validation test on test data. The implementation of review text classification using the hybrid Convolutional Neural Network (CNN) and Gated Recurrent Unit (GRU) method was made using the python programming language. The accuracy of the validation test is 88.5%
Cryptocurrency Price Prediction Using Long Short Term Memory Algorithm and Moving Average Convergence Divergence Abiyyu Dicky Pratama; Auli Damayanti; Edi Winarko
Contemporary Mathematics and Applications (ConMathA) Vol. 8 No. 1 (2026)
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/conmatha.v8i1.76496

Abstract

Cryptocurrency is one of the digital assets that is increasingly popular for investment in Indonesia. However, the price movements of cryptocurrencies tend to be volatile, as prices can change at any time and are not easy to predict. This study aims to predict cryptocurrency price movements using the Long Short-Term Memory Algorithm (LSTM) and Moving Average Convergence Divergence (MACD). LSTM is an algorithm used to generate optimal weights and biases in modeling cryptocurrency data, while MACD is used to analyze trends and momentum in cryptocurrency prices. The data used consists of daily closing prices of Bitcoin (BTC), totaling 809 data points. The data is divided into 70% (566 data) for the training process and 30% (243 data) for the testing process. From this data, patterns are formed with five inputs and one output, resulting in 561 patterns for the training process and 238 patterns for the testing process. The LSTM and MACD processes for predicting cryptocurrency include procedures for data input, data division, parameter initialization, LSTM calculation, average error evaluation, and MACD calculation. Based on the program implementation, with several parameter values, the average error difference obtained during the training stage is 0.0695 and 0.0303 during the testing stage. Because the average error difference obtained is relatively small, this indicates that LSTM-MACD is capable of recognizing data patterns and predicting data effectively.
Co-Authors Abdiansah, Abdiansah Abiyyu Dicky Pratama Agus Sasmito Ariwibowo Agustinus Jacobus Ahmad Irfan Abdullah Aina Musdholifah Auli Damayanti Badrus Zaman Edhy Sutanta (Jurusan Teknik Informatika IST AKPRIND Yogyakarta) Edy Irwansyah Fiqih Fathor Rachim Khabib Mustofa Lutfi Budi Ilmawan Mardi Siswo Utomo Natalis Ransi Retantyo Wardoyo Robynson Amseke Sandi Fajar Rodiyansyah Sulistyowati Sulistyowati Sumarni Adi Wayan Gede Suka Parwita