Article Per Year (5 Year)
p-Index From 2021 - 2026
1.197
P-Index
This Author published in this journals
All Journal Jurnal EECCIS Jurnal Edukasi dan Penelitian Informatika (JEPIN) JOIN (Jurnal Online Informatika) Building of Informatics, Technology and Science Indonesian Journal of Electrical Engineering and Computer Science Sewagati
Hidayati, Shintami Chusnul
Unknown Affiliation
Arts Humanities Computer Science & IT Education Engineering Languange, Linguistic, Communication & Media Public Health Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
Pelatihan Desain Antarmuka Mobile Application dengan Figma untuk Meningkatkan Kompetensi Guru MGMP TIK Surabaya Ahmadiyah, Adhatus Solichah; Sarno, Riyanarto; Hidayati, Shintami Chusnul; Anggraini, Ratih Nur Esti; Sungkono, Kelly Rossa; Munif, Abdul
Sewagati Vol 8 No 4 (2024)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j26139960.v8i4.1216

Abstract

Studi ini mengevaluasi dampak pelatihan desain antarmuka mobile application (aplikasi perangkat bergerak) menggunakan Figma terhadap peningkatan wawasan dan keterampilan guru MGMP TIK di Surabaya. Kegiatan pelatihan yang diikuti 43 peserta terlaksana dalam dua tahap, yakni penyampaian materi dan pendampingan berupa asistensi pengerjaan desain antarmuka pada studi kasus. Metode evaluasi melibatkan pengumpulan data melalui kuesioner yang diberikan sebelum dan setelah pelatihan, serta analisis hasil penugasan desain antarmuka pada studi kasus. Sebagaimana terlihat dari hasil kuesioner. Hasil karya desain antarmuka peserta juga mencerminkan penguasaan konsep desain antarmuka aplikasi perangkat bergerak. Implikasi dari peningkatan ini berupa kontribusi positif terhadap pendekatan pembelajaran berbasis teknologi di lingkungan sekolah. Kesimpulannya, pelatihan desain antarmuka aplikasi perangkat bergerak menggunakan Figma mampu secara efektif meningkatkan pengetahuan dan keterampilan guru MGMP TIK Surabaya, yang selanjutnya dapat diterapkan dan dioptimalkan dalam konteks pembelajaran teknologi di sekolah. Studi ini memberikan landasan bagi pengembangan lebih lanjut dalam memperkaya metode pelatihan guru untuk menghadapi tantangan pembelajaran berbasis teknologi di era digital.
Algorithmic Advancements in Heuristic Search for Enhanced Sudoku Puzzle Solving Across Difficulty Levels Pratama, Moch Deny; Abdillah, Rifqi; Herumurti, Darlis; Hidayati, Shintami Chusnul
Building of Informatics, Technology and Science (BITS) Vol 5 No 4 (2024): March 2024
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v5i4.4622

Abstract

Computer technology, particularly artificial intelligence, has found diverse applications in the rapidly evolving era of the industrial revolution, notably in gaming, delving into artificial intelligence and explicitly applying game-solving techniques to Sudoku puzzles. Sudoku, a popular game requiring logical precision, serves as an ideal platform for exploring algorithms such as depth-first search, breadth-first search, and heuristic search. This research identifies memory-intensive demands in breadth-first search and the potential issue of infinite traversal in depth-first search. To address these challenges, the study proposes implementing the heuristic search algorithm, which prioritizes promising paths based on estimations of proximity to the goal state made by a heuristic function. The primary objective is to enhance Sudoku puzzle-solving by comparing the performance of the heuristic search algorithm with traditional breadth-first and depth-first search methods, with a particular focus on improving efficiency and reducing memory usage, including time and steps. The results indicate that the heuristic search algorithm outperforms traditional methods, demonstrating faster completion times and reduced memory requirements, thereby contributing to the advancement of Sudoku-solving algorithms. The study evaluates their performance across different difficulty levels, utilizing data from sudoku.com and extremesudoku.info. Notably, the heuristic search algorithm emerges as a superior method, outperforming other algorithms in terms of completion steps and time efficiency. The implementation and analysis involved three types of Sudoku puzzle-solving methods, revealing that the heuristic search algorithm significantly outperforms other algorithms, optimizing its performance in solving Sudoku puzzles. The average time required to complete Sudoku puzzles from data sourced from Sudoku.com was 0.02, 0.05, and 0.61 seconds for each level, respectively. In contrast, according to extremesudoku.info, it took 0.31 seconds for the highest difficulty level. Furthermore, the average total steps needed on sudoku.com ranged from 43 to 1201 steps for each level, spanning from easy to hard. On extremesudoku.info, 509 steps were required for the highest difficulty level. These results affirm the reliability of heuristic search, consistently demonstrating encouraging outcomes and outperforming other algorithms across diverse conditions. This strategic selection facilitates a comprehensive analysis of Sudoku problem-solving algorithms, allowing for the exploration of algorithmic performance and providing a comprehensive range of Sudoku puzzles, thereby ensuring the study's robustness and validity
Stacking-based ensemble learning for identifying artist signatures on paintings Hidayati, Shintami Chusnul; Irawan Rahardja, Agustinus Aldi; Suciati, Nanik
Indonesian Journal of Electrical Engineering and Computer Science Vol 36, No 3: December 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v36.i3.pp1683-1693

Abstract

Identifying artist signatures on paintings is essential for authenticating artworks and advancing digital humanities. An artist’s signature is a consistent element included in each painting that the artist creates, providing a unique identifier for their work. Traditional methods that rely on expert analysis and manual comparison are time-consuming and are prone to human error. Although convolutional neural networks (CNNs) have shown promise in automating this process, existing single-model approaches struggle with the diversity and complexity of artistic styles, leading to limitations in their performance and generalizability. Therefore, this study proposes an ensemble learning approach that integrates the predictive power of multiple CNN-based models. The proposed framework leverages the strengths of three state-of-the-art CNNs: EfficientNetB4, ResNet-50, and Xception. These models were independently trained, and the predictions were combined using a meta-learning strategy. To address class imbalance, data augmentation techniques and weighted loss functions were employed. The experimental results obtained on a dataset of more than 8,000 paintings from 50 artists demonstrate significant improvements over individual CNN architectures and other ensemble methods, thereby effectively capturing complex features and improving generalizability.
Combination of Historical Stock Data and External Factors In Improving Stock Price Prediction Performance Sjahrunnisa, Anita; Suciati, Nanik; Hidayati, Shintami Chusnul
Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems) Vol. 18 No. 2 (2024)
Publisher : Faculty of Engineering, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21776/jeeccis.v18i2.1707

Abstract

Stock price prediction continues to be a major focus for investors today, some previous studies often focus on technical analysis using historical stock price data and ignore external factors that can affect stock prices. The purpose of this research is to overcome the shortcomings of previous research by creating a stock price prediction model that combines historical stock data consisting of date, high, low, open, close, adj close, volume and external factors such as days, interest rates, inflation, and dividends. The data used came from 33 companies from 11 industrial sectors in Indonesia for 2267 trading days and evaluated the prediction performance using MSE, MAPE and R-squared. The results show a significant improvement in the evaluation metrics when external factors are added. This shows the importance of such factors in improving the prediction analysis and increasing the reliability of the prediction model. This approach is expected to not only overcome the limitations of traditional methods but also utilize a combination of deep learning and machine learning to improve prediction accuracy. Thus, this research not only provides new insights in the field of financial analysis but also provides new insights and solutions for investors to make more informed and less risky decisions.
Road Damage Detection Using YOLOv7 with Cluster Weighted Distance-IoU NMS Rachman, Rudy; Suciati, Nanik; Hidayati, Shintami Chusnul
JOIN (Jurnal Online Informatika) Vol 10 No 1 (2025)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v10i1.1481

Abstract

Road damage can occur everywhere. Potholes are one of the most common types of road damage. Previous research that used images as input for pothole detection used the Faster Regional Convolutional Neural Network (R-CNN) method. It has a large inference time because it is a two-stage detection method. The object detection method requires post-processing for its detection results to save only the best prediction from the method, namely, non-maximum suppression (NMS). However, the original NMS could not properly detect small, far, and two objects close to each other. Therefore, this research uses the YoloV7 method as the object detection method because it has better mean Average Precision (mAP) results and a lower inference time than other object detection methods; with an improved NMS method, namely Cluster Weighted Distance Intersection over Union (DIoU) NMS (CWD-NMS), to solve small or close potholes. When training YoloV7, we combined a new, independently collected pothole dataset, with previous public research datasets, where the detection results of the YoloV7 method were better than those of Faster R-CNN. The YoloV7 method was trained using various scenarios. The best scenario during training is using the best checkpoint without using a scheduler. The mAP.5 and mAP.5-.95 value of CWD-NMS was 89.20% and 63.30% with 10.30 millisecond per image for inference time.
Optimalisasi Manajemen Keuangan Kelompok Belajar dan Taman Kanak-Kanak melalui Modul Front-Office KinderFin di Wilayah Kota Surabaya Ahmadiyah, Adhatus Solichah; Sarno, Riyanarto; Hidayati, Shintami Chusnul; Sungkono, Kelly Rossa; Anggraini, Ratih Nur Esti
Sewagati Vol 9 No 6 (2025)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j26139960.v9i6.4679

Abstract

Pengelolaan keuangan yang efisien dan transparan sangat penting untuk mendukung operasional lembaga pendidikan anak usia dini, termasuk kelompok bermain (KB) dan taman kanak-kanak (TK). Namun, banyak institusi tersebut masih mengandalkan pencatatan manual yang rawan kesalahan dan tidak transparan. Kegiatan pengabdian masyarakat ini bertujuan untuk mengembangkan dan mengimplementasikan modul Front-Office aplikasi KinderFin guna membantu digitalisasi manajemen keuangan di tujuh sekolah KB/TK di beberapa kecamatan di Kota Surabaya. Metode pelaksanaan mencakup analisis kebutuhan mitra, pengembangan aplikasi dengan pendekatan iteratif, pelatihan langsung, serta evaluasi berbasis survei umpan balik. Hasil menunjukkan bahwa fitur-fitur utama aplikasi seperti PPDB, pembayaran SPP, dan pencatatan pengeluaran sangat membantu administrasi sekolah. Mitra memberikan penilaian positif dengan skor rata-rata 4,0 hingga 4,8 dari skala 5,0. Hal ini menunjukkan peningkatan transparansi dan efisiensi dalam pengelolaan keuangan sekolah. Program ini memberikan kontribusi nyata dalam transformasi digital tata kelola keuangan sekolah PAUD dan membuka peluang pengembangan lanjutan untuk adopsi skala lebih luas.
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.
Co-Authors Abdillah, Rifqi ABDUL MUNIF Adhatus Solichah Ahmadiyah, Adhatus Solichah Darlis Herumurti Irawan Rahardja, Agustinus Aldi Jaya, Muhammad Triyanda Taruna Kelly Rossa Sungkono Nanik Suciati Pratama, Moch Deny Rachman, Rudy Ratih Nur Esti Anggraini, Ratih Nur Esti Riyanarto Sarno Sjahrunnisa, Anita