cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota surabaya,
Jawa timur
INDONESIA
Jurnal Infra
Published by Universitas Kristen Petra Surabaya
ISSN : -     EISSN : -     DOI : -
Core Subject : Science,
Computer Science & IT
Arjuna Subject : -
Articles 1,338 Documents
 130   131   132   133   134 
Analisis Penjualan dan Pelanggan Toko Swalayan di Kediri Menggunakan Market Basket Analysis dan Machine Learning
Jurnal Infra Vol. 14 No. 1 (2026): Jurnal Infra
Publisher : Universitas Kristen Petra

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

Abstract

Inventory management and sales analysis in convenience stores are often handled manually, making it difficult for store owners to understand customer purchasing patterns and make effective operational decisions. This study analyzes transaction and inventory data from a convenience store in Kediri by combining Market Basket Analysis and machine learning to produce more measurable, actionable insights. The methods include FP-Growth to discover product associations, Decision Tree to predict inventory status (restock/overstock), K-Means to segment products, and Random Forest Regression to forecast monthly profit. The results show that consistent purchasing patterns can support bundling and product arrangement recommendations, while the classification, clustering, and regression models help improve stock monitoring, wholesale strategy, and financial planning. All outputs are implemented in an interactive dashboard to support practical use by the store owner.
Web Manajemen Rekam Medis dan Asesmen Psikologis Berbasis Web untuk Psikiater dengan Fitur Deteksi Interaksi Obat
Jurnal Infra Vol. 14 No. 1 (2026): Jurnal Infra
Publisher : Universitas Kristen Petra

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

Abstract

Praktik psikiatri di Indonesia menghadapi tantangan kritis dalam pengelolaan rekam medis manual, efisiensi asesmen psikologis, dan keamanan resep polifarmasi. Penelitian ini mengembangkan sistem terintegrasi berbasis web yang menggabungkan Electronic Medical Record (EMR), asesmen psikologis digital terstandar (HAM-A dan HAM-D), dan deteksi interaksi obat menggunakan database lokal dan OpenFDA API. Sistem dibangun menggunakan Flutter dengan arsitektur Model-View-Controller (MVC) dan database MySQL. Evaluasi melalui User Acceptance Testing (UAT) menunjukkan peningkatan efisiensi signifikan: waktu registrasi pasien 96,7% lebih cepat (15 menit → 30 detik), pencarian rekam medis 98,4% lebih efisien (5-10 menit → 4,7 detik), dan waktu asesmen 75% lebih cepat (8-10 menit → 2m5 menit). Sistem mencapai akurasi perhitungan asesmen 100% (57/57 kasus) dan deteksi interaksi obat 90,4% (141/156 interaksi). Skor System Usability Scale (SUS) mencapai 95 (Grade A+), memvalidasi kelayakan sistem sebagai alat bantu klinis yang efektif untuk meningkatkan kualitas layanan kesehatan mental di Indonesia. 
Evaluasi Akurasi Analisis Forensik Velociraptor dan Tools Tradisional pada Serangan LockBit dengan Pendekatan DFRWS
Jurnal Infra Vol. 14 No. 1 (2026): Jurnal Infra
Publisher : Universitas Kristen Petra

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

Abstract

Peningkatan kasus ransomware seperti LockBit 3.0 mendorong kebutuhan akan analisis forensik yang cepat dan akurat. Selama ini banyak investigasi mengandalkan tools tradisional yang bekerja secara terpisah, sehingga proses korelasi artefak sering memerlukan waktu lebih lama. Velociraptor sebagai tools modular menawarkan pendekatan yang otomatis dan terpusat. Penelitian ini dilakukan untuk menilai apakah Velociraptor dapat memberikan tingkat akurasi yang setara atau lebih baik dibandingkan tools tradisional ketika digunakan untuk menganalisis serangan ransomware pada lingkungan yang disimulasikan. Hasil penelitian menunjukkan bahwa meskipun Velociraptor lebih cepat secara signifikan dalam akuisisi data, tetapi tools tradisional menghasilkan cakupan artefak yang lebih lengkap. Pada pengujian tiga alur serangan LockBit 3.0, Velociraptor tidak berhasil mendeteksi beberapa taktik MITRE ATT&CK yang sebenarnya dapat diidentifikasi oleh tools tradisional, yaitu pada teknik yang berhubungan dengan taktik Persistence, Privilege Escalation, Defense Evasion, Lateral Movement, Command and Control, serta Exfiltration. Temuan ini menunjukkan bahwa adanya trade-off antara penggunaan tools tradisional dengan Velociraptor. 
Implementation of the Gamification Method for Employee Training Systems at PT XYZ Using the Moodle Learning Management System
Jurnal Infra Vol. 14 No. 1 (2026): Jurnal Infra
Publisher : Universitas Kristen Petra

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

Abstract

This study aims to develop a Moodle-based Learning Management System (LMS) to address employee training challenges at PT XYZ. The main obstacle faced by the company is the onboarding process, which was previously conducted manually via WhatsApp, resulting in unstructured materials and difficult monitoring. Therefore, this system is designed to provide modular learning paths, automated evaluation mechanisms, and data-based progress tracking features to improve training management. As a primary solution to enhance user engagement, this study applies gamification methods that include points (XP), levels, activity badges, and leaderboards. Its technical implementation is supported by the development of an additional plugin named "My Command Center," which functions to manage automatic badge assignment based on learning activity completion. This approach aims to transform the monotonous training process into a more interactive and motivating learning experience. Testing results indicate that the system operates stably without major errors and is able to significantly accelerate the onboarding process duration. Evaluation using User Acceptance Testing (UAT) proves that gamification integration effectively increases employee motivation, comprehension, and engagement, as evidenced by improved module completion rates, XP accumulation, and assessment results. Thus, the application of gamification within the LMS is proven to be an effective solution for enhancing training quality and efficiency at PT XYZ. 
SISTEM PENERJEMAH MULTI BAHASA TERINTEGRASI DENGAN GEMINI UNTUK MENINGKATKAN AKSESIBILITAS KONTEN TEKS DI GMS CHURCH
Jurnal Infra Vol. 14 No. 1 (2026): Jurnal Infra
Publisher : Universitas Kristen Petra

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

Abstract

Dalam lingkungan gereja multibahasa seperti GMS Church, perbedaan linguistik sering menjadi hambatan dalam penyampaian pesan rohani dan informasi pelayanan. Tanpa sistem penerjemahan yang memadai, sebagian jemaat berisiko mengalami keterbatasan pemahaman sehingga mengurangi keterlibatan dalam kegiatan gereja. Penelitian ini mengembangkan sistem penerjemah berbasis web dengan integrasi kecerdasan buatan Gemini. Sistem dilengkapi dengan fitur penerjemahan otomatis, validasi berjenjang dan manajemen proyek untuk memastikan hasil terjemahan yang akurat, konsisten, dan sesuai konteks keagamaan. Hasil pengujian melalui User Acceptance Test (UAT) menunjukkan bahwa sistem mampu meningkatkan efisiensi dan kualitas penerjemahan, serta membantu jemaat dari berbagai latar belakang bahasa untuk mengakses materi gereja dengan lebih mudah
Aspect-Controlled Summarization in Indonesian Language Scientific Papers Using Longformer Encoder-Decoder
Jurnal Infra Vol. 14 No. 1 (2026): Jurnal Infra
Publisher : Universitas Kristen Petra

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

Abstract

In the current information era, the number of scientific papers published in Indonesian continues to increase, creating a need for automated document summarization systems that enable efficient and rapid access to essential information. This study investigates the application of aspect-controlled summarization to Indonesian scientific articles using the Longformer Encoder-Decoder (LED) model. The proposed system aims to generate summaries that explicitly consider predefined aspects, namely Purpose, Method, Findings, and Value. This study employs the Indonesian-translated version of the FacetSum dataset, which has undergone preprocessing and structural reorganization to support aspect-based summarization. The LED model is fine-tuned using this dataset and evaluated at both the whole-document level and the facet level. Model performance is assessed using ROUGE metrics as the primary quantitative evaluation method, complemented by qualitative analysis. Experimental results indicate that while the LED model is capable of generating aspect-based summaries, its performance remains limited when compared to baseline models trained on English datasets. The obtained facet-level ROUGE-L scores are 34.28 for Purpose, 19.45 for Method, 19.37 for Findings, and 21.37 for Value, whereas the BART-Facet model on the original English FacetSum dataset achieves scores of 42.55, 28.07, 28.98, and 28.70, respectively. Further analysis suggests that this performance gap is primarily attributable to architectural limitations of the LED model for aspect-based summarization tasks, as the ability to process long input sequences does not inherently translate into improved facet-level summary quality.
Prediksi Harga Sewa Tenant dengan Pendekatan Hybrid K-prototype Clustering dan Categorical Boosting pada Mall XYZ
Jurnal Infra Vol. 14 No. 1 (2026): Jurnal Infra
Publisher : Universitas Kristen Petra

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

Abstract

Mall XYZ menghadapi tantangan dalam menetapkan harga sewa yang kompetitif dan berbasis data bagi tenant, terutama akibat ketimpangan performa tenant. Ketimpangan ini dipengaruhi oleh variabel seperti jenis usaha, lokasi, dan kapasitas finansial tenant. Untuk mengatasi tantangan tersebut, penelitian ini bertujuan membangun sistem pendukung keputusan yang mengintegrasikan segmentasi tenant dan prediksi harga sewa. Penelitian mengusulkan pendekatan hybrid yang menggabungkan K-Prototype dan K-Medoid Clustering untuk segmentasi tenant berdasarkan karakteristik multidimensional, serta algoritma Categorical Boosting (CatBoost) untuk memprediksi harga sewa. Dataset yang digunakan meliputi data historis kontrak sewa tenant periode 2015 hingga 2025, dilengkapi variabel eksternal berupa inflasi dan pertumbuhan PDRB Kota Surabaya untuk meningkatkan kontekstualitas prediksi. Pendekatan hybrid yang menggabungkan segmentasi tenant dan prediksi berbasis CatBoost menghasilkan peningkatan akurasi prediksi harga sewa. Segmentasi yang diperoleh memberikan wawasan berbasis data yang dapat digunakan oleh manajemen Mall XYZ dalam evaluasi kebijakan harga. Selain itu, sebuah dashboard juga dikembangkan untuk memvisualisasikan hasil prediksi dan analisis klaster guna mendukung proses pengambilan keputusan operasional.
Sales Time Series Data Analysis Using a Combination of Supervised andUnsupervised Learning for Business Strategy Optimization at PT X
Jurnal Infra Vol. 14 No. 1 (2026): Jurnal Infra
Publisher : Universitas Kristen Petra

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

Abstract

PT X is an industrial gas company with an extensive operational network, yet it faces challenges in analyzing sales performance and price inconsistencies across regions. The lack of a data-driven analytical system makes it difficult for the company to identify sales trends, product performance, and branch contributions objectively. This study aims to develop a data-driven analytical system to support business decision-making. Sales trend analysis was conducted using SARIMAX, compared with SARIMA and XGBoost, with SARIMAX showing the highest accuracy. Evaluation using MAPE and RMSE indicated error rates of 18% for SARIMA, 14% for XGBoost, and 5% for SARIMAX. Branch clustering was tested using K-Means and GMM, with GMM selected due to faster execution and better clustering quality (Silhouette Score 0.623 vs 0.622). Additionally, Linear Regression and Random Forest were applied for price standardization across branches, with Linear Regression providing more consistent predictions, high R², and relatively low errors. The results demonstrate an effective analytical system that supports more accurate and consistent business decision-making.

Page 134 of 134 | Total Record : 1338

 130   131   132   133   134 

Filter by Year

2013 2026


Reset
Filter By Issues
All Issue Vol. 14 No. 1 (2026): Jurnal Infra Vol 10, No 2 (2022) Vol 10, No 1 (2022) Vol 9, No 2 (2021) Vol 9, No 1 (2021) Vol 8, No 2 (2020) Vol 8, No 1 (2020) Vol 7, No 2 (2019) Vol 7, No 1 (2019) Vol 6, No 2 (2018) Vol 6, No 2 (2018) Vol 6, No 1 (2018) Vol 5, No 2 (2017) Vol 5, No 1 (2017) Vol 4, No 2 (2016) Vol 4, No 1 (2016) Vol 4, No 1 (2016) Vol 3, No 2 (2015) Vol 3, No 2 (2015) Vol 3, No 1 (2015) Vol 3, No 1 (2015) Vol 2, No 2 (2014) Vol 2, No 2 (2014) Vol 2, No 1 (2014) Vol 2, No 1 (2014) Vol 1, No 2 (2013) Vol 1, No 2 (2013) Vol 1, No 1 (2013) Vol 1, No 1 (2013) More Issue