Article Per Year (5 Year)
p-Index From 2021 - 2026
2.59
P-Index
This Author published in this journals
All Journal IPTEK The Journal for Technology and Science JUTI: Jurnal Ilmiah Teknologi Informasi Jurnal EECCIS Jurnal Edukasi dan Penelitian Informatika (JEPIN) JOIN (Jurnal Online Informatika) JIEET (Journal of Information Engineering and Educational Technology) Building of Informatics, Technology and Science Abdi: Jurnal Pengabdian dan Pemberdayaan Masyarakat Indonesian Journal of Electrical Engineering and Computer Science Jurnal Teknik Informatika (JUTIF) Journal of Business, Social and Technology Eduvest - Journal of Universal Studies Sewagati
Shintami Chusnul Hidayati
Institut Teknologi Sepuluh Nopember
Aerospace Engineering Arts Humanities Computer Science & IT Dentistry Economics, Econometrics & Finance Education Engineering Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Library & Information Science Medicine & Pharmacology Neuroscience Public Health Social Sciences Other

Published : 16 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 16 Documents
Search

 1   2 
IMPROVED LIP-READING LANGUAGE USING GATED RECURRENT UNITS Nafa Zulfa; Nanik Suciati; Shintami Chusnul Hidayati
JUTI: Jurnal Ilmiah Teknologi Informasi Vol. 19, No. 2, Juli 2021
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v19i2.a1080

Abstract

Lip-reading is one of the most challenging studies in computer vision. This is because lip-reading requires a large amount of training data, high computation time and power, and word length variation. Currently, the previous methods, such as Mel Frequency Cepstrum Coefficients (MFCC) with Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) with LSTM, still obtain low accuracy or long-time consumption because they use LSTM. In this study, we solve this problem using a novel approach with high accuracy and low time consumption. In particular, we propose to develop lip language reading by utilizing face detection, lip detection, filtering the amount of data to avoid overfitting due to data imbalance, image extraction based on CNN, voice extraction based on MFCC, and training model using LSTM and Gated Recurrent Units (GRU). Experiments on the Lip Reading Sentences dataset show that our proposed framework obtained higher accuracy when the input array dimension is deep and lower time consumption compared to the state-of-the-art.
Network Intrusion Detection System with Time-Based Sequential Cluster Models using LSTM and GRU Ravi Vendra Rishika; Baskoro Adi Pratomo; Shintami Chusnul Hidayati
JUTI: Jurnal Ilmiah Teknologi Informasi Vol. 23, No. 1, January 2025
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j24068535.v23i1.a1241

Abstract

Technological development and the growth of the internet today have a positive and revolutionary impact in various areas of human life, such as banking, health, science, and more. The presence of Open Data and Open API also facilitates the exchange of data and information between entities without the restrictions imposed by different regions and geographical areas. However, information openness not only has a positive impact but also makes data vulnerable to data theft, viruses, and various other types of cyber attacks. The large-scale data exchange that occurs across the network poses a challenge in detecting unusual activity and new cyber attacks. Therefore, the existence of an Intrusion Detection System (IDS) is urgently essential. The IDS helps system administrators detect cyber attacks and network anomalies, thus minimizing the risk of data leaks and intrusions. The research developed a new approach using time-based sequential clustered data sets in the Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) models. This IDS model was implemented using the CIC-IDS 2018 data set, which has more than 4 million data lines. The capabilities and uniqueness of the LSTM and GRU models are used to classify and determine various attacks in IDS based on sequential data sets ordered by time and clustered according to the destination ports and protocols, such as TCP and UDP. The model was evaluated using the accuracy, precision, recall, and F-1 scores matrix, and the results showed that the time-based sequential clustered models in LSTM and GRU have an accurities of up to 97.21%. This suggests that this new approach is good enough to be applied to the future IDS models.
Model Machine Learning Berbasis Perilaku Pembayaran Angsuran untuk Prediksi Gagal Bayar KPR Subsidi Jaya, Muhammad Triyanda Taruna; Hidayati, Shintami Chusnul
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol. 11 No. 3 (2025): Volume 11 No 3
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v11i3.100857

Abstract

Penelitian ini menyajikan rancangan dan pembuktian pemanfaatan model machine learning untuk prediksi gagal bayar sesuai definisi Otoritas Jasa Keuangan pada produk KPRS (Kredit Pemilikan Rumah Subsidi) berbasis perilaku pembayaran angsuran pada segmen MBR (Masyarakat Berpenghasilan Rendah). Berbeda dengan sebagian besar penelitian terdahulu yang berfokus pada application scoring saat pengajuan atau pencairan kredit dengan data statis nasabah seperti kemampuan finansial, riwayat peminjaman, informasi pekerjaan, agunan dan data statis lainnya, studi ini menargetkan kredit yang sudah berjalan (on-book) dengan memanfaatkan jejak historis pembayaran angsuran sebagai sumber utama sinyal risiko. Dataset berasal dari salah satu bank penyalur KPRS. Dengan teknik rekayasa fitur, data pembayaran angsuran diubah menjadi fitur tabular yang merangkum perilaku pembayaran (misalnya konsistensi nominal, kelancaran waktu bayar dan pola keterlambatan) yang kemudian dipelajari oleh beberapa metode machine learning, antara lain Multilayer Perceptron, Random Forest, XGBoost dan Logistic Regression. Data mencakup 8.116 akun dan 409.130 catatan transaksi dengan evaluasi menggunakan train set periode 2017–2022 (6.585 akun) dan test set 2023–2024 (1.217 akun). Model terbaik dicapai oleh MLP dengan performa AUC ≈ 0,997 pada test set dengan F1 Score maksimum pada threshold 0,3013 memberikan precision 0,7907, recall 0,9444 dan F1 0,8608. Hasil ini menunjukkan bahwa untuk pinjaman KPRS yang sudah berjalan, pola perilaku pembayaran angsuran semata—tanpa perlu menambahkan informasi mengenai kondisi usaha, kondisi finansial, agunan, maupun karakteristik lain nasabah—dapat dimanfaatkan untuk membangun model machine learning yang mampu memprediksi risiko gagal bayar secara akurat dan dapat memberikan early warning pada portofolio KPRS, sehingga tindakan pencegahan seperti intervensi, reminder atau kunjungan lapangan diharapkan dapat dilakukan secara lebih terarah dan efisien.
Bank Customer Churn Prediction Using a Hybrid Ensemble Soft Voting Approach Based on Tabnet and XGBOOST Mohamad Syazimmi Hersyaputra; Shintami Chusnul Hidayati
Eduvest - Journal of Universal Studies Vol. 6 No. 4 (2026): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v6i4.52494

Abstract

In an increasingly competitive banking industry, the ability to predict potential customer churn is a strategic factor in maintaining business profitability and sustainability. Churn has a direct impact on a bank’s revenue and operational efficiency; therefore, a prediction model is needed that is not only accurate but also stable and adaptive to variations in customer data. This study proposes a hybrid ensemble soft voting approach based on TabNet and XGBoost to improve the performance and robustness of churn prediction. TabNet, with its sequential attention mechanism, can selectively identify important features, while XGBoost excels at handling nonlinear relationships and controlling overfitting through gradient boosting regularization. The two models are combined using a probability-based soft voting mechanism to produce more balanced and consistent predictions. To address class imbalance, the Synthetic Minority Over-sampling Technique (SMOTE) was applied so that the data distribution is more proportional and churn patterns can be better represented. The experimental results show that the proposed approach achieves optimal performance, with an accuracy of 96.74%, precision of 90.09%, recall of 89.53%, and an F1-score of 89.81%. These values indicate that the model is able to maintain a balance between accurate churn detection and the minimization of misclassification. This hybrid ensemble soft voting approach has proven to be superior to single models in terms of predictive stability and generalization capability, making it an effective framework to support data-driven customer retention strategies in the banking sector.
Bank Customer Churn Prediction Using CTGAN-Augmented Data and Boosting-Based Ensemble Learning with SHAP Explainable AI Hersyaputra, Mohamad Syazimmi; Hidayati, Shintami Chusnul
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.3.5578

Abstract

Customer churn prediction remains a fundamental concern in the banking domain due to its direct impact on revenue stability and long-term customer value. A key challenge in churn modeling lies in severe class imbalance, which often limits model sensitivity toward minority churn cases. This study aims to develop an integrated and explainable churn prediction framework that effectively addresses class imbalance while maintaining robust predictive performance and interpretability. The proposed approach employs Conditional Tabular Generative Adversarial Networks (CTGAN), comparison of five boosting-based ensemble learning, and SHapley Additive exPlanations (SHAP) to preserve model interpretability. CTGAN is leveraged to synthesize high-fidelity instances for the churn class, yielding a class-balanced dataset that retains intricate tabular feature distributions. Five boosting-based ensemble models, XGBoost, CatBoost, Gradient Boosting Machine (GBM), Stochastic Gradient Boosting (SGB), and LightGBM, are systematically tuned using randomized hyperparameter optimization and evaluated under consistent experimental settings. Model performance is assessed using accuracy, precision, recall, and F1-score to capture classification performance under class imbalance. To ensure transparency, SHAP is applied to analyze global feature importance influencing churn predictions. Experimental results indicate CTGAN enhances model learning stability and detection capability. Among the evaluated models, CatBoost achieves the best results, with an accuracy of 0.9748 and an F1-score of 0.9178. The explainability analysis reveals that transactional features play a dominant role in churn. The novelty of this study lies in a unified and explainable churn prediction framework that integrates CTGAN-data augmentation, boosting ensembles, and interpretability for robust decision support in banking analytics.
Photo Aesthetic Assessment via Spatial and Frequency Domain Fusion Using a Vision Transformer Approach Reza Rachmadan; Shintami Chusnul Hidayati
Journal of Business, Social and Technology Vol. 7 No. 3 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i3.737

Abstract

Background: The rapid growth of digital media has increased the demand for automated image aesthetic assessment (IAA) in social media, creative industries, and e-commerce platforms. Although Vision Transformer (ViT)-based models have demonstrated promising performance, most existing approaches rely primarily on spatial representations while overlooking frequency-domain information, which captures complementary characteristics such as sharpness, texture, noise patterns, and bokeh effects. Objective: This study proposes a Dual-Branch Late Fusion FFT-ViT architecture with concatenation-based fusion as an approach for integrating dual-domain representations to improve photo aesthetic assessment (PAA). Methods: The proposed architecture consists of two parallel branches. The RGB branch employs a Vision Transformer (ViT-Small) to extract spatial and compositional features, while the FFT branch utilizes ViT-Tiny to capture frequency-domain characteristics associated with texture, sharpness, and image details. The extracted features from both branches are fused using a concatenation strategy before being passed to the regression layer. Results: The proposed Dual-Branch FFT-ViT with concatenation fusion achieved the best performance, obtaining a PLCC of 0.7336, SRCC of 0.7347, MSE of 0.0193, MAE of 0.1117, and RMSE of 0.1388. Compared with the RGB-only ViT baseline, the proposed model improved the PLCC score by 0.0124, demonstrating the effectiveness of integrating spatial and frequency-domain features for aesthetic score prediction. Conclusion: This study demonstrates that integrating spatial and frequency-domain representations through a dual-branch Vision Transformer architecture enhances photo aesthetic assessment performance.
Co-Authors Abdillah, Rifqi ABDUL MUNIF ABDUL MUNIF Adhatus Solichah Ahmadiyah Adhatus Solichah Ahmadiyah, Adhatus Solichah Ahmadiyah, Adhatus Solichah Baskoro Adi Pratomo Darlis Herumurti Dava Aulia Ekohariadi Hersyaputra, Mohamad Syazimmi Irawan Rahardja, Agustinus Aldi Jaya, Muhammad Triyanda Taruna Kelly Rosa Sungkono Kelly Rossa Sungkono Klemm, Sebastian Mohamad Syazimmi Hersyaputra Muhammad Rivai Nafa Zulfa Nanik Suciati Navinda Meutia Nurul Fajrin Ariyani Pratama, Moch Deny Rachman, Rudy Raharja, Putu Bagus Gede Prasetyo Ratih Nur Esti Anggraini Ratih Nur Esti Anggraini, Ratih Nur Esti Ravi Vendra Rishika Reza Rachmadan Riyanarto Sarno Rosyid, Alfian Nur Saikhu, Ahmad Sjahrunnisa, Anita Wahyuwidayat, Raditia Wardhiana, I Nyoman Gde Artadana Mahaputra Yeni Anistyasari