Article Per Year (5 Year)
p-Index From 2021 - 2026
2.245
P-Index
This Author published in this journals
All Journal EXPERT: Jurnal Manajemen Sistem Informasi dan Teknologi Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) RABIT: Jurnal Teknologi dan Sistem Informasi Univrab JOURNAL OF APPLIED INFORMATICS AND COMPUTING SELAPARANG: Jurnal Pengabdian Masyarakat Berkemajuan JPPM (Jurnal Pengabdian dan Pemberdayaan Masyarakat) EDUMATIC: Jurnal Pendidikan Informatika Abdimasku : Jurnal Pengabdian Masyarakat International Journal of Marine Engineering Innovation and Research Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat
Soni Adiyono
Universitas Muria Kudus
Religion Agriculture, Biological Sciences & Forestry Humanities Automotive Engineering 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 Environmental Science Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Materials Science & Nanotechnology Mechanical Engineering Medicine & Pharmacology Nursing Physics Public Health Social Sciences Transportation Other

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

Found 16 Documents
Search

 1   2 
Explainable XGBoost Early-Warning Framework for Academic Stress-Based Student Mental Health Risk Mapping Supriyono; Heru Noviyanto Firmansyah; Soni Adiyono
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 10 No 4 (2026): August 2026 (in progress)
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v10i4.7812

Abstract

Existing university mental health monitoring often depends on voluntary help-seeking or manual questionnaire interpretation, which may delay early support for students experiencing academic stress. This study proposes an explainable XGBoost-based early-warning framework for non-clinical mapping of student mental health risk from academic stress indicators. The single-site dataset comprised 1,002 anonymized student records from Universitas Muria Kudus. K-Means clustering was used to transform DASS-21 depression, anxiety, and stress scores into low, moderate-, and high-risk categories, while XGBoost predicted the cluster-derived labels using seven single-item academic stress indicators and engineered aggregate and interaction features. On a stratified hold-out testing set of 201 records, the model achieved weighted precision, recall, and F1-score values of 0.8907, 0.8905, and 0.8906, respectively, with class-level F1-scores of 0.9109 for low risk, 0.8900 for moderate risk, and 0.8713 for high risk. Additional ablation, clustering sensitivity, subgroup, threshold, and SHAP stability analyses were conducted to strengthen robustness and interpretability. The findings show that cumulative academic stress and interaction features involving parental expectations, exam anxiety, and learning-method adaptation were consistently influential predictors. The framework is intended to support early institutional prioritization and counseling referral, not clinical diagnosis. Generalization remains limited by the single-institution sample and the use of single-item academic stress indicators; therefore, local retraining and recalibration are required before institutional deployment, including implementation of the Streamlit prototype.
Digitalisasi Pelaporan Nota Operasional melalui Implementasi Sistem Informasi Berbasis Web pada PT Telkom Akses Kudus Anita Rahmawati; Soni Adiyono
Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat Vol. 6 No. 3 (2026): Mei 2026 - Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/altifani.v6i3.1186

Abstract

Pengabdian kepada masyarakat ini dilatarbelakangi oleh proses pelaporan nota operasional di Service Area PT Telkom Akses Kudus yang masih dilakukan secara manual menggunakan Microsoft Excel dan Telegram, sehingga kurang efisien, memerlukan waktu lama, dan berpotensi menimbulkan kesalahan pencatatan. Kegiatan ini bertujuan untuk mengimplementasikan sistem informasi berbasis web guna mengintegrasikan proses pencatatan, verifikasi, rekapitulasi, dan pembayaran nota operasional. Metode pelaksanaan meliputi analisis kebutuhan, perancangan sistem, implementasi, pengujian, dan pemeliharaan. Hasil kegiatan menunjukkan bahwa sistem dapat digunakan dengan baik oleh admin dan teknisi serta memperoleh tanggapan positif dari pengguna. Sistem membantu mempermudah pengelolaan data, pencarian eviden, verifikasi, dan pemantauan pembayaran. Dengan demikian, penerapan sistem berbasis web penting untuk meningkatkan efisiensi, ketepatan, dan transparansi pelaporan nota operasional.  
An Integrated Safety Stock and Net Promoter Score System for Inventory and Customer Loyalty Arya Putra Badruzzaman; Yudie Irawan; Soni Adiyono
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 1 (2026): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i1.33557

Abstract

Manual and separate inventory management and customer loyalty monitoring often lead to information delays, record-keeping errors, low operational efficiency, and an unmonitored relationship between stock availability and customer perception. The aim of our research was to develop a web-based sales and loyalty information system that integrates Safety Stock and Net Promoter Score (NPS) methods into a single decision support framework. Our research is a study of system development using the Waterfall model, which includes the stages of requirements analysis, system design, implementation, testing, and maintenance, supported by use cases and activity diagrams. The findings of this study are an integrated system that is able to calculate minimum stock levels, safety stocks, risk of stock-outs, and display real-time NPS visualizations. The test results obtained through black box testing on system access, inventory processing, and NPS reporting show that all key functions are running well and to specification. The implications of this study suggest that the proposed system can improve inventory accuracy, reduce the risk of stock shortages, improve operational efficiency, and support objective, responsive, and sustainable managerial decision-making for small and medium-sized distributors through an integrated and reliable information system.
Analisis Churn Menggunakan Metode K-Means Clustering Berdasarkan Model LRFM Untuk Meningkatkan Retensi Pada Mahes Printing Bagus Joko Winarso; Diana Laily Fithri; Soni Adiyono
EXPERT: Jurnal Manajemen Sistem Informasi dan Teknologi Vol 15, No 2 (2025): December
Publisher : Universitas Bandar Lampung (UBL)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36448/expert.v15i2.4584

Abstract

In the competitive digital era, customer retention has become a critical factor for business sustainability, particularly in the digital printing industry which faces intense competition. Mahes Printing, despite recording a high transaction volume, continues to experience low repurchase rates due to fragmented and manual management of customer data and transaction history. This study aims to implement churn analysis within a Sales Management Information System using a Customer Relationship Management (CRM) approach supported by the LRFM (Length, Recency, Frequency, Monetary) model and the K-Means clustering algorithm. The results indicate that customers can be effectively grouped into three main clusters representing low, medium, and high churn risk levels. This segmentation facilitates the identification of customers with high churn potential, characterized by low Recency and Frequency values, thereby providing strategic insights to support data-driven decision-making and the development of more targeted and effective customer retention strategies.
Implementasi Sistem Informasi Usulan Jabatan Fungsional ASN untuk Mendukung Layanan Kepegawaian di BKPSDM Kudus: Implementation of ASN Functional Position Proposal Information System to Support BKPSDM Kudus Personnel Services Sholichatunnita Nita; Soni Adiyono
JPPM (Jurnal Pengabdian dan Pemberdayaan Masyarakat) VOL. 10 NOMOR 2 JULI 2026 JPPM (Jurnal Pengabdian dan Pemberdayaan Masyarakat)
Publisher : Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/jppm.v10i2.31008

Abstract

Proses pengusulan jabatan fungsional Aparatur Sipil Negara (ASN) di Badan Kepegawaian dan Pengembangan Sumber Daya Manusia (BKPSDM) Kabupaten Kudus sebelumnya masih dilakukan secara manual sehingga menyebabkan proses administrasi kurang efisien, penyimpanan dokumen belum terintegrasi, serta pemantauan status usulan oleh pemohon menjadi terbatas. Mitra dalam kegiatan pengabdian kepada masyarakat ini adalah BKPSDM Kabupaten Kudus sebagai instansi yang mengelola pelayanan administrasi kepegawaian ASN. Kegiatan ini bertujuan mengembangkan dan mengimplementasikan Sistem Informasi Usulan Jabatan Fungsional ASN berbasis web untuk meningkatkan efektivitas, efisiensi, dan transparansi pelayanan kepegawaian. Metode yang digunakan adalah model Waterfall yang meliputi analisis kebutuhan, perancangan sistem, implementasi, pengujian menggunakan Black-Box Testing, serta pelatihan dan pendampingan kepada pengguna. Sistem dikembangkan menggunakan framework PHP Laravel dengan basis data MySQL. Hasil implementasi menunjukkan bahwa sistem mampu mendukung proses pengajuan usulan, verifikasi berkas, penyimpanan dokumen digital, pelacakan status usulan secara real-time, serta penyusunan laporan secara terintegrasi. Berdasarkan hasil observasi selama implementasi, waktu pemrosesan usulan berkurang dari sekitar 5–9 hari menjadi 2,5–4 hari. Hasil pengujian Black-Box menunjukkan bahwa seluruh fungsi utama sistem berjalan sesuai dengan kebutuhan pengguna. Hasil pengabdian ini menunjukkan bahwa penerapan sistem informasi berbasis web mampu meningkatkan efisiensi proses administrasi, akurasi pengelolaan data, dan transparansi pelayanan kepegawaian serta berpotensi menjadi model pengembangan layanan digital pada instansi pemerintah lainnya.
Comparative Analysis of Machine Learning Algorithms with SMOTE for Imbalanced Sentiment Classification of IndiHome on Platform X Rizky Adisaputra; Muhammad Arifin; Soni Adiyono
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13271

Abstract

Sentiment analysis of IndiHome users on social media X faces a severe class imbalance, with negative tweets dominating 88.26% of the dataset. This study compares four machine learning algorithms, Support Vector Machine (SVM), Naive Bayes, Decision Tree, and Random Forest, for sentiment classification using SMOTE to address the imbalance. Initially, 20,001 Indonesian tweets were scraped using Tweet Harvest with the keyword "indihome". After duplicate removal and preprocessing, 7,199 tweets were retained. Each tweet was manually annotated into positive, negative, and neutral categories. TF-IDF was applied for feature extraction, and Stratified 5-Fold Cross Validation was used for evaluation. Algorithms were tested under two conditions: without and with SMOTE. Before SMOTE, SVM achieved the highest accuracy (94.55%) and F1-score (94.05%). After SMOTE, Random Forest outperformed others with 94.14% accuracy and 93.83% F1-score, as the only algorithm showing consistent improvement across all metrics, including balanced accuracy and MCC. Although Wilcoxon tests showed no statistically significant differences between algorithms, Random Forest demonstrated the most stable and consistent performance. These findings confirm that Random Forest with SMOTE is the most effective strategy for imbalanced sentiment classification in this context.
Co-Authors - Supriyono Abdul Azis Al Baehaqi Amanda Diyas Setiyoadi Anita Rahmawati Arya Putra Badruzzaman Bagus Joko Winarso Damar Aji Gurowo Diana Laily Fithri Diyas Aditya Adi Saputra Eko Darmanto Heru Noviyanto Firmansyah Ira Iriyanty Lu'lu'il Laili Muhammad Arifin Noor Latifah Pratiwi Cahyaningtiyas R Rhoedy Setiawan Rizky Adisaputra Salum Ainayya Alfatikhah Sholichatunnita Nita Supriyono Syafrie Muhammad Hawari Triana Rahajeng Hadiprawoto Yeshika Alversia Yudie Irawan Zainur Romadhon