Article Per Year (5 Year)
p-Index From 2021 - 2026
2.049
P-Index
This Author published in this journals
All Journal Journal of Information Systems Engineering and Business Intelligence Science and Technology Indonesia Jurnal Pengabdian Masyarakat Tapis Berseri Abdi Akommedia : Jurnal Pengabdian Masyarakat Integra: Journal of Integrated Mathematics and Computer Science Nemui Nyimah
Wamiliana
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Computer Science & IT Education Engineering Environmental Science Materials Science & Nanotechnology Mathematics Physics Other

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : Science and Technology Indonesia

 1 
LSTM-CNN Hybrid Model Performance Improvement with BioWordVec for Biomedical Report Big Data Classification Kurniasari, Dian; Warsono; Usman, Mustofa; Lumbanraja, Favorisen Rosyking; Wamiliana
Science and Technology Indonesia Vol. 9 No. 2 (2024): April
Publisher : Research Center of Inorganic Materials and Coordination Complexes, FMIPA Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/sti.2024.9.2.273-283

Abstract

The rise in mortality rates due to leukemia has fueled the swift expansion of publications concerning the disease. The increase in publications has dramatically affected the enhancement of biomedical literature, further complicating the manual extraction of pertinent material on leukemia. Text classification is an approach used to retrieve pertinent and top-notch information from the biomedical literature. This research suggests employing an LSTM-CNN hybrid model to tackle imbalanced data classification in a dataset of PubMed abstracts centred on leukemia. Random Undersampling and Random Oversampling techniques are merged to tackle the data imbalance problem. The classification model’s performance is improved by utilizing a pre trained word embedding created explicitly for the biomedical domain, BioWordVec. Model evaluation indicates that hybrid resampling techniques with domain-specific pre-trained word embeddings can enhance model performance in classification tasks, achieving accuracy, precision, recall, and f1-score of 99.55%, 99%, 100%, and 99%, respectively. The results suggest that this research could be an alternative technique to help obtain information about leukemia.
The Use of Probability and Edge Analysis to Solve the Multi-Period Degree Constrained Minimum Spanning Tree Problem Wamiliana; Junaidi, Akmal; Gamal, Mohammad Danil Hendry; Thamrin, Taqwan
Science and Technology Indonesia Vol. 9 No. 4 (2024): October
Publisher : Research Center of Inorganic Materials and Coordination Complexes, FMIPA Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/sti.2024.9.4.999-1008

Abstract

The goal of the Multiperiod Degree Constrained Minimum Spanning Tree (MPDCMST) problem is to determine the smallest weight-spanning tree that satisfies the vertex installation criterion for each period and maintains the degree requirement in each vertex. This issue emerges as a network connection problem. The degree requirement indicates the reliability of each vertex, and the vertex connection/installation requirement denotes the priority vertices that must be inserted in the network within a specific time frame. The installation is split up into multiple phases/stages. This is because of various considerations such as severe weather, budgetary limitations, etc. In this research, two algorithms for solving the MPDCMST using probability hybridized with Prim’s modification, and edge analysis are proposed. The algorithms are implemented on the undirected complete graph of orders 10 to 100. The solutions are compared with some heuristics which are already in the literature. The results show that the proposed algorithms perform better.
Modeling Vector Error Correction with Exogeneous (VECMX) Variable for Analyzing Nonstationary Variable Energy Used and Gross Domestic Product (GDP) Usman, Mustofa; Wamiliana; Russel, Edwin; Kurniasari, Dian; Widiarti; Elfaki, Faiz A.M
Science and Technology Indonesia Vol. 10 No. 1 (2025): January
Publisher : Research Center of Inorganic Materials and Coordination Complexes, FMIPA Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/sti.2025.10.1.283-293

Abstract

Analysis of energy used, GDP and population has been carried out in many countries and has become a topic of interest for many researchers and governments. This is because energy used is an important factor for society and industry in a country. In this study, the modeling of the relationship between energy used, GDP and population as an exogenous variable for the cases of Indonesia from 1967-2023 will be discussed. The energy used and GDP data are nonstationary with order one, I(1), and there is cointegration between energy used and GDP. Therefore, the model which will be used is the Vector Error Correction Model with Exogenous variable (VECMX) with population as the exogenous variable. From the results of analysis, the best model is VECMX(3,1) with cointegration rank R=1. Based on this model, the pattern of the relationship among the three variables, Granger-causality between energy used and GDP, exogenous impact on energy used and GDP, and forecasting for the next 10 years will be discussed.
Dynamic Modeling of Energy Data: World Crude Oil and Coal Prices 2017-2023 (A State-Space Model Analysis of Multivariate Time Series) Russel, Edwin; Wamiliana; Usman, Mustofa; Elfaki, Faiz AM; Adnan, Arisman; Lindrianasari
Science and Technology Indonesia Vol. 10 No. 4 (2025): October
Publisher : Research Center of Inorganic Materials and Coordination Complexes, FMIPA Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/sti.2025.10.4.1301-1311

Abstract

The analysis of global crude oil and coal prices has attracted considerable research interest, as these prices significantly affect both society and industry, making the topic highly relevant for governments and policy makers. This study examines the correlation between global coal and crude oil prices from 2017 to 2023. It analyzes the behavior of these price series using a unit root test and develops an optimal model for conducting a Granger-causality analysis. To forecast crude oil and coal prices for the next 30 periods, a state-space modeling approach is applied. The unit root test results reveal that these prices are non-stationary, suggesting that any shocks to prices will have persistent effects. The best-fitting model for the association between coal and crude oil prices is a vector autoregressive model of order two (VAR(2)). The Granger-causality results reveal that current crude oil prices are influenced by both their own past values and previous coal prices, and vice versa. Forecasts using the state-space model suggest a modest upward trend for crude oil prices over the next 30 periods, while coal prices are projected to rise more strongly.
Modeling Cointegrated Nonstationary Air Pollution Data: A Forecasting Study of NO₂ and SO₂ in Indonesia (1950–2022) Adnan, Arisman; Erda, Gustriza; Wamiliana; Russel, Edwin
Science and Technology Indonesia Vol. 11 No. 1 (2026): January
Publisher : Research Center of Inorganic Materials and Coordination Complexes, FMIPA Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26554/sti.2026.11.1.161-173

Abstract

 Air pollution from nitrogen dioxide (NO2) and sulfur dioxide (SO2) poses serious threats to human respiratory health and contributes to environmental degradation through acid rain formation. In Indonesia, despite rapid industrialization and increasing emissions, studies examining the interrelated dynamics between NO2 and SO2 at the national level remain limited, with most research focusing only on provincial areas and short time periods. This study fills this gap by analyzing the dynamic relationship between NO2 and SO2 using comprehensive national-level time series data from 1950 to 2022. The analysis examines short-term adjustments, long-term equilibrium patterns, directional causality, and shock responses between the two pollutants. The analysis focuses on identifying the best statistical model to capture the interaction between the two variables. Granger causality tests, impulse response functions (IRFs), and forecast error variance decomposition are applied to examine causal links and response dynamics. The data exhibits nonstationary but cointegrated with rank r=1, indicating a long-run equilibrium correlation between two pollutants. Consequently, the Vector Error Correction Model, VECM(4), is selected as the most appropriate model. The study also provides 10-year forecasts for both pollutants insights into potential future air pollution trends in Indonesia, with NO2 rising from 5.29 to 8.09 million tons and SO2 from3.38 to 5.10 million tons, underscoring the urgent need for integrated emission control policies that address both pollutants simultaneously rather than in isolation.
Co-Authors Abdurrahman, Ahmad Faruq Akmal Junaidi Amansyah, Wahyu Dwi Arisman Adnan Asmiati Dian Kurniasari Elfaki, Faiz A.M Elfaki, Faiz AM Gamal, Mohammad Danil Hendry Gustriza Erda Hadi, Nur Wafiqoh Jani Master, Jani Lindrianasari Lumbanraja, Favorisen R Mega Sapitri, Nonik Mustika, Mira Mustofa Usman Notiragayu Nuning Nurcahyani Nur Hamzah Nurdin, Muhaymi Nurfabella, Rehsya Russel, Edwin Sawitri, Riza Taqwan Thamrin Warsono Widiarti Zaenal Abidin