Article Per Year (5 Year)
p-Index From 2021 - 2026
1.931
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer Journal of Information Technology and Computer Science JIEET (Journal of Information Engineering and Educational Technology) Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Indonesian Journal of Electrical Engineering and Computer Science Indonesian Journal of Engineering and Technology (INAJET) Journal of Informatics and Computer Science (JINACS) Jurnal Ilmiah Edutic : Pendidikan dan Informatika J-Icon : Jurnal Komputer dan Informatika Repeater: Publikasi Teknik Informatika dan Jaringan Indonesian Journal of Electronics, Electromedical Engineering, and Medical Informatics JURNAL LINTAS KARSA
Ervin Yohannes
Universitas Negeri Surabaya
Arts Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Materials Science & Nanotechnology Mechanical Engineering Social Sciences

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 17 Documents
Search

 1   2 
A Performance Comparison of LSTM and GRU Architectures for Forecasting Daily Bitcoin Price Volatility Nafisah, Nurun; Yamasari, Yuni; Yohannes, Ervin
JIEET (Journal of Information Engineering and Educational Technology) Vol. 9 No. 2 (2025)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/jieet.v9n2.p156-167

Abstract

The highly volatile movement of Bitcoin prices necessitates the use of prediction methods capable of accurately capturing complex and rapidly changing patterns. This study aims to compare the performance of two recurrent neural network architectures, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in forecasting Bitcoin prices based on historical time series data. The analysis was conducted using daily closing price data, with several parameter configurations applied, including dropout value, learning rate, and number of epochs at a window size of 30. The training process was carried out using a univariate approach to assess the fundamental ability of each model to learn temporal patterns without the influence of external variables. The results indicate that the GRU model consistently outperforms LSTM across most experimental settings. The best performance was achieved with 30 epochs, dropout 0.1, and a learning rate of 0.001, producing RMSE 1478.333, MAE 1000.900, R² 0.996081, and MAPE 1.973072. These metrics demonstrate a lower error level and a stronger fit to actual Bitcoin price movements. Moreover, a paired t-test confirmed that the performance gap between the two models is statistically significant. Overall, the findings suggest that the Gated Recurrent Unit architecture is more efficient in capturing nonlinear patterns and responding to the volatile dynamics of cryptocurrency price fluctuations, making it a promising approach for future predictive modeling in financial time series.
Optimizing UKT Prediction Based on Socio-Economic Features: A Multimodel Evaluation with Feature Selection Srategies Putri, Windy Chikita Cornia; Yustanti, Wiyli; Yohannes, Ervin
EDUTIC Vol 12, No 2: 2025
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/edutic.v12i2.31828

Abstract

Determining the tuition fee group (UKT) for new students in Indonesian public universities represents a complex challenge requiring an equitable, data-driven approach. This study introduces an integrative feature selection strategy that combines five popular techniques Chi-Square, Recursive Feature Elimination (RFE), LASSO Regression, Random Forest Importance, and Exploratory Factor Analysis (EFA) to extract the most relevant attributes from 53 socioeconomic variables of prospective students at Universitas Negeri Surabaya. As a novelty, the study identifies intersecting features consistently selected by all five methods and evaluates their impact on the performance of five classification algorithms: Support Vector Machine (SVM), Decision Tree, Random Forest, K-Nearest Neighbor (KNN), and Naïve Bayes. Experimental results demonstrate a significant improvement in accuracy, with SVM increasing from 0.7550 to 0.7810. These findings confirm that integrative feature selection can optimize model performance while reducing data complexity. This study provides a replicable methodological contribution for developing transparent and adaptive classification systems based on socioeconomic data in higher education contexts.
Comparative Analysis of Traditional Machine Learning Models (SVM, KNN, and Linear Regression) for KSE 100 Stock Price Forecasting Febriansyah, Aldin; Ervin Yohannes
Journal of Informatics and Computer Science (JINACS) Vol. 7 No. 02 (2025)
Publisher : Universitas Negeri Surabaya

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

Abstract

Abstract—The erratic volatility of stock prices presents a significant challenge for analysts and investors when making informed investment decisions. Although the Efficient Market Hypothesis suggests that price prediction is theoretically impossible, numerous studies indicate that predictive models can yield high-quality results. This research compares the effectiveness of three traditional machine learning algorithms—Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Linear Regression (LR)—in forecasting the daily stock prices of the KSE 100 Index from the Pakistan Stock Exchange (PSX). The study utilized 3,221 daily closing prices recorded between February 22, 2008, and February 23, 2021. The models were implemented in Python and optimized through hyperparameter tuning using GridSearchCV. To ensure robust evaluation, five distinct data-splitting techniques were employed: a chronological split of 2020 and proportional splits of 80:20, 75:25, and 70:30. Performance was measured using MSE, RMSE, MAE, MAPE, and Accuracy metrics. The findings reveal that Linear Regression (LR) consistently delivered the best and most stable performance across all testing schemes. LR achieved its highest accuracy of 97.9% and lowest error (MSE 0.000404) in the 70:30 split, while maintaining a 97.3% accuracy in the 2020 test data. In contrast, KNN was the most sensitive model, with accuracy dropping to 92.2% in the 30% test scheme. These results underscore that LR is the most accurate and dependable option for stock price time-series prediction among these traditional models, proving that simpler models can remain highly competitive. Keywords— Stock Price Forecasting, Machine Learning, Linear Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbors (KNN).
Penerapan Deep Learning untuk Pengenalan Aktivitas Manusia Secara Non-Intrusif Menggunakan Wi-Fi Channel State Information Reza Pahlevi; Ervin Yohannes
Repeater : Publikasi Teknik Informatika dan Jaringan Vol. 4 No. 1 (2026): Januari: Repeater : Publikasi Teknik Informatika dan Jaringan
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/repeater.v4i1.818

Abstract

This study is motivated by the increasing need for accurate modeling and classification of one-dimensional signal data in intelligent systems. The rapid development of deep learning has led to the adoption of more adaptive and complex neural network architectures capable of capturing both temporal dependencies and local patterns in sequential data. This research aims to analyze and compare the performance of several deep learning models, namely Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid Convolutional Neural Network–GRU (CNN–GRU) model for signal data classification. The research method employs a quantitative experimental approach involving data preprocessing, windowing, model training, and performance evaluation. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. The results indicate that the hybrid CNN–GRU model outperforms the other models, particularly in capturing local features and long-term temporal dependencies within signal data. These findings suggest that the integration of convolutional layers and recurrent mechanisms enhances feature representation and learning stability. This study is expected to contribute both theoretically and practically to the development of deep learning models for signal processing and time-series-based intelligent applications.
Pemanfaatan Canva AI Guna Meningkatkankan Kreatifitas Guru dalam Mengembangkan Media Pembelajaran di SMP Negeri 1 Pagerwojo Ronggo Alit; Paramitha Nerisafitra; Ervin Yohannes
Jurnal Lintas Karsa Vol. 1 No. 1 (2024): Jurnal Lintas Karsa (November 2024)
Publisher : S1 Teknik Mesin Fakultas Teknik. Universitas Negeri Surabaya Gedung A6 Kampus UNESA Ketintang Surabaya 60231

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

Abstract

Canva adalah salah satu dari sekian aplikasi yang dapat dimanfaatkan untuk membuat promosi dalam bentuk video, animasi dan gambar yang dapat disajikan dalam bentuk poster, flyer serta teks berjalan yang bisa mempermudah orang lain untuk memahami maksud dari sebuah desain. Begitu juga dengan para siswa, dengan adanya media pembelajaran yang menarik dapat membantu mereka dalam memahami materi Pelajaran. Dengan adanya Pelatihan Canva para Bapak dan Ibu guru dapat membuat presentasi pembelajaran di kelas dengan semenarik mungkin. Guru dapat membuat materi pembelajan yang bisa dipilih desainnya sesuai selera. Selain itu agar tampilan presentasi bisa dikreasikan, berbagai fitur yang terdapat dalam desain juga bisa dimanfaatkan. Tampilan presentasi juga dapat disisipi dengan gambar atau video sesuai materi yang diajarkan. Kegiatan pengabdian ini bertujuan memberikan wawasan dan penerapan praktis dalam memanfaatkan canva sehingga para guru diharapkan memiliki kreatifitas didalam menyusun media pembelajaran yang interaktif yang dapat mempermudah para siswa dalam memahami materi pelajaran  
A Data-Driven Framework Integrating Clustering and Classification for Fair Tuition Grouping (UKT) Prediction Windy Chikita Cornia Putri; Wiyli Yustanti; Ervin Yohannes; Yoyok Prastyo
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 11, No. 3, August 2026 (Article in Progress)
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v11i3.2578

Abstract

This study aims to identify the most effective combination of feature selection techniques and classification algorithms for predicting student tuition groups (Uang Kuliah Tunggal, UKT) based on pre-admission data. Three feature selection methods Exploratory Factor Analysis (EFA), Recursive Feature Elimination (RFE), and Random Forest Feature Importance (RFFI) were employed and combined with five supervised learning models: Decision Tree, Random Forest, Support Vector Machine (SVM) with RBF kernel, Naïve Bayes, and K-Nearest Neighbor (KNN). The results demonstrate that the EFA–SVM (RBF) combination achieved the best performance, with an average accuracy exceeding 98%, outperforming other models across most faculties. EFA also yielded the highest Silhouette Score (0.2933), indicating a more stable and distinct cluster structure compared to RFE (0.2564) and RFFI (0.2575). These findings highlight the critical role of appropriate feature selection in improving classification accuracy and model generalization, particularly when emphasizing socioeconomic variables such as parental income, land area, housing conditions, and basic family facilities. The integration of factor-based dimensionality reduction with non-linear classification algorithms proved effective in developing a more transparent and equitable UKT prediction model. This research contributes to the advancement of data-driven decision support systems in higher education and provides a foundation for future automation in tuition group determination processes.
A COMPARATIVE STUDY OF SUPERVISED FEATURE SELECTION METHODS FOR PREDICTING UANG KULIAH TUNGGAL (UKT) GROUPS Windy Chikita Cornia Putri; Wiyli Yustanti; Ervin Yohannes
J-Icon : Jurnal Komputer dan Informatika Vol 13 No 2 (2025): October 2025
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v13i2.23893

Abstract

The manual classification of Uang Kuliah Tunggal (UKT) groups at Indonesian public universities is laborious, subjective, and error-prone, especially given the explosion of socio-economic data captured via online admission portals. In this study, we evaluate five feature selection techniques Chi-Square filter, Random Forest importance, Recursive Feature Elimination, LASSO embedded selection, and Exploratory Factor Analysis on a dataset of 9,369 applicants described by 53 socio-economic variables. Six classifiers (Decision Tree, Random Forest, SVM-RBF, K-Nearest Neighbor, and Naïve Bayes) were tuned via stratified 5-fold cross-validation within an 80:20 train-test split. Performance was measured by accuracy, macro-F1, and training time, and differences in weighted-average accuracy across feature-selection scenarios were assessed using the Friedman test (χ² = 15.06, p = 0.010). Results show that reducing to 13 features via LASSO (weighted-average accuracy 0.730) or Chi-Square (0.678) significantly outperforms both the full feature baseline (0.624) and the EFA baseline (0.303), while cutting computational costs by over 40%. We conclude that supervised feature selection particularly LASSO and Chi-Square enables simpler, faster, and more transparent UKT prediction without sacrificing accuracy. The novelty of this study lies in comparing five feature-selection methods within a standardized preprocessing pipeline on real UKT data from UNESA, resulting in a 13-feature subset aligned with the current UKT policy. This finding is ready to be integrated into an automated UKT verification system to enhance decision accuracy and efficiency.
Co-Authors Ahmad Fikri Hanafi Asyrofa Rahmi, Asyrofa Esti, Esti Yogiyanti Febriansyah, Aldin Mulyono, Alfito Nafisah, Nurun Paramitha Nerisafitra Putri, Windy Chikita Cornia Ramadhany, Sinta Dhea Reza Pahlevi Ronggo Alit Shih, Timothy K. Utaminingrum, Fitri Wayan Firdaus Mahmudy Windy Chikita Cornia Putri Wiyli Yustanti Wiyli Yustanti Yogiyanti, Esti Yoyok Prastyo YUNI YAMASARI