BIOS : Jurnal Teknologi Informasi dan Rekayasa Komputer

Perbandingan Algoritma Decision Tree dan K-Nearest Neighbor untuk Klasifikasi Penyakit ISPA

Marchell William Putra Pakpahan — 2026-06-12

Acute Respiratory Infection (ARI) is one of the most common respiratory diseases with diverse and overlapping clinical symptoms, making initial identification challenging and necessitating a systematic, data-driven classification approach. This study aims to compare the performance of the Decision Tree and K-Nearest Neighbor (KNN) algorithms in classifying ARI-related disease categories. The novelty of this research lies in the specific construction of ARI labels into five distinct categories from the Pediatric Respiratory Infections dataset, coupled with a rigorous feature selection process to handle mixed data types and address class imbalance using weighted evaluation metrics. The dataset consisted of 801 patient records with 91 initial attributes. The classification label was constructed from the Main diagnostic column and grouped into five categories: Asthma/Bronchospasm/Wheezing, Pneumonia/Pneumopathy, Bronchiolitis, Laryngeal/Upper Respiratory, and Other. After feature selection to remove noise and redundancy, 54 features were used, consisting of 24 numerical and 30 categorical features. The research stages included preprocessing, label construction, missing value handling, categorical encoding, KNN normalization, 80:20 train-test splitting, and model evaluation. The results show that Decision Tree achieved higher performance with 67.08% accuracy and 69.12% weighted F1-score, while KNN achieved 65.84% accuracy and 64.18% weighted F1-score. Thus, Decision Tree demonstrates superior performance and interpretability for this specific dataset.

Analisis Kesiapan Penerapan Rekam Medis Elektronik dengan Metode DOQ-IT di Puskesmas Kendit Situbondo

Sabran Sabran — 2026-07-09

Kendit Public Health Center currently uses paper-based medical records and has only recently begun implementing electronic medical records (EMR) in several service areas. However, this implementation faces numerous challenges, including data duplication, file damage, and the accumulation of 9,424 physical records. This situation highlights the importance of accelerating the comprehensive implementation of Electronic Medical Records (EMR) to enhance the efficiency of patient data management. This study aims to analyze the readiness for EMR implementation using the DOQ-IT method. This descriptive research involved 53 respondents, with data collected through questionnaires. The results showed that organizational alignment readiness was in the “very ready” category with a score of 31.72 out of a maximum score range of 45. The subvariables included culture (mean: 3.56), leadership (mean: 3.53), and strategy (mean: 3.47) on a 1 – 4 scale. Meanwhile, organizational capacity readiness was in the “moderately ready” category with a score of 59.77 out of a maximum score range of 100. The subvariables included information management (mean: 3.11), clinical and administrative staff (mean: 3.07), training (mean: 3.42), workflow process (mean: 2.92), accountability (mean: 2.75), budgeting (mean: 3.12), patient involvement (mean: 2.58), IT management (mean: 3.06), and IT infrastructure (mean: 2.80) on a 1 – 4 scale. Improvements are needed in organizational capacity, particularly in patient involvement, accountability, and IT infrastructure.

Analisis Prediksi Permintaan Produk FMCG menggunakan Model LSTM dan DES Untuk Optimalisasi Operasional Gudang Distribusi

Tanti Cahya Herdiyani — 2026-07-27

The Fast-Moving Consumer Goods (FMCG) sector is characterized by rapid product turnover and short shelf lives, requiring effective inventory management. Companies such as PT Macrosentra Niagaboga face challenges in maintaining stock availability. Although the inventory system has been integrated, stock verification is still conducted manually, requiring adaptive management to minimize the risk of overstock and stockout. Therefore, this study aims to develop a demand forecasting model using the Long Short-Term Memory (LSTM) algorithm integrated with Discrete-Event Simulation (DES) to optimize inventory management. The study utilized historical shipment data from May 2025 to January 2026. Preprocessing included data cleansing, date validation, and aggregation into daily and weekly data. Forecasting results were subsequently used as inputs for the DES simulations to determine optimal inventory policies. The results demonstrated that weekly LSTM aggregation was more accurate and stable than daily aggregation, as evidenced by a reduction in WAPE from 49.9% to 16.94% for high-demand products. Furthermore, integration with DES reduced stock levels by more than 30% using a safety stock ratio of 0.7 without compromising service levels. Finally, the proposed model was implemented in a web-based dashboard serving as a decision support system for monitoring forecasting and inventory policy recommendations.

Sistem Sistem Informasi Akreditasi Online Multi-LAM untuk Manajemen Dokumen Program Studi

Eko Wahyu Wibowo — 2026-07-28

Study-program accreditation requires supporting evidence to be organised in a valid, current, and traceable manner. This need becomes more complex when study programs within one faculty are evaluated by different independent accreditation agencies, such as LAMSAMA and LAM INFOKOM. This study develops a web-based multi-accreditation-agency information system for managing accreditation documents at a Faculty of Science and Technology. The system was developed using the System Development Life Cycle, which consists of requirements analysis, design, coding, testing, and maintenance. The results show that the system supports three user roles, document mapping by study program, accreditation agency, and criteria, as well as upload, download, validation, revision, and monitoring functions. Black-box testing indicates that the main functional scenarios run as expected. The proposed system contributes an adaptive document management model that can be updated when accreditation criteria or agency schemes change.

Analisis Klasifikasi Stadium Kanker Payudara Menggunakan Algoritma Naïve Bayes Berdasarkan Data Rekam Medis

Mudafiq Riyan Pratama — 2026-07-29

Breast cancer is one of the leading causes of cancer-related mortality among women, highlighting the need for faster and more accurate approaches to support disease staging. The utilisation of electronic medical records through data mining techniques provides an alternative approach for breast cancer stage classification. This study aimed to analyse breast cancer stage classification using the Naïve Bayes algorithm based on electronic medical record data from patients at Baladhika Husada Level III Hospital, Jember. A quantitative approach was employed using secondary data consisting of 476 breast cancer medical records selected from a total of 1,082 records. The research stages included data selection, data cleaning, categorical encoding, model development using the Naïve Bayes algorithm, and model evaluation using a Confusion Matrix based on accuracy, precision, and recall. Model performance was evaluated using nine training-testing split scenarios ranging from 10:90 to 90:10. The experimental results showed that the 90:10 split scenario achieved the best performance, with an accuracy of 87.50%, precision of 86.36%, and recall of 86.36%. These findings indicate that the Naïve Bayes algorithm is capable of classifying breast cancer stages effectively based on patients' clinical characteristics recorded in electronic medical records. The proposed approach demonstrates the potential of integrating electronic medical records and the Naïve Bayes algorithm to support the development of clinical decision support systems for breast cancer stage classification.

Model HOT-FIT dalam Menilai Keberhasilan Implementasi Aplikasi Gemini serta Dampaknya pada Kepuasan Pengguna

Dewi Lusiana — 2026-07-29

The rapid development of Artificial Intelligence (AI) has increased the use of the Gemini application to support information retrieval, task completion, and work productivity. This study aims to analyze the factors influencing the successful use of the Gemini application using the Human-Organization-Technology Fit (HOT-FIT) model. The variables examined include Service Quality, User Satisfaction, Organizational Structure, and Net Benefit. A quantitative approach with purposive sampling was employed. Data were collected from 100 respondents, consisting of students, lecturers, and employees, and analyzed using Partial Least Squares-Structural Equation Modeling (PLS-SEM) with SmartPLS 4. The results indicate that all constructs meet the validity and reliability requirements. The R-Square values of 0,588 for User Satisfaction and 0,676 for Net Benefit demonstrate satisfactory explanatory power. Hypothesis testing shows that Service Quality has a positive and significant effect on User Satisfaction (β=0.767; p<0.001), User Satisfaction has a positive and significant effect on Net Benefit (β=0.274; p=0.023), and Organizational Structure has a positive and significant effect on Net Benefit (β=0.599; p<0.001). These findings indicate that the HOT-FIT model effectively explains the success of the Gemini application, highlighting the importance of service quality and organizational support in maximizing its benefits.

The Hybrid Cloud API Gateway Architecture with Zero Trust for Digital Banking

B. Junedi Hutagaol — 2026-08-11

The rapid adoption of digital banking services has increased the reliance on Application Programming Interfaces (APIs) to support integration, service delivery, and collaboration with external partners. However, the growing exposure of APIs has also introduced significant security risks, while financial institutions must simultaneously address scalability demands and regulatory compliance requirements. This study aims to design a Hybrid Cloud API Gateway Architecture integrated with Zero Trust Security principles for digital banking systems. The research employs a qualitative approach using the Design Science Research (DSR) methodology, consisting of literature review, requirements analysis, architecture design, expert validation, and architecture evaluation. The proposed architecture integrates API Gateway capabilities, Hybrid Cloud Architecture, and Zero Trust mechanisms to provide secure, scalable, and resilient banking services. Critical workloads and sensitive data are maintained within private cloud environments, while scalable services are deployed in the public cloud to improve flexibility and resource utilization. Evaluation results indicate that the proposed architecture aligns with NIST SP 800-207 Zero Trust Architecture principles, addresses major risks identified in the OWASP API Security Top 10, and supports compliance with PCI DSS and ISO/IEC 27001 standards. The proposed framework provides a practical reference for developing secure, scalable, and compliant digital banking infrastructures.