Bulletin of Information System Research

e-Growth Posyandu: Transformasi Digital Monitoring Tumbuh Kembang Anak dengan Metode Human-Centered Design (HCD)

2026-06-28T08:49:07+00:00

Posyandu merupakan ujung tombak layanan Kesehatan bagi seluruh siklus kehidupan khususnya ibu dan anak di tingkat desa atau kelurahan, namun pencatatan tumbuh kembang anak masih dilakukan secara manual menggunakan buku KIA, sehingga rentan terhadap kesalahan data, keterlambatan deteksi, dan keterbatasan aksesibilitas informasi bagi orang tua. Penelitian ini bertujuan mengembangkan sistem digital berbasis web dan mobile bernama e-Growth Posyandu yang dirancang untuk memantau tumbuh kembang anak secara real-time dengan pendekatan Human-Centered Design (HCD). Metode HCD diterapkan melalui empat tahapan utama: (1) empathize, yaitu menggali kebutuhan pengguna melalui wawancara dengan kader posyandu dan orang tua; (2) define, mengidentifikasi permasalahan inti; (3) ideate, merancang solusi melalui brainstorming; (4) prototype yaitu merepresentasikan ide/konsep berupa sketsa, mockup digital; (5) test yaitu fase di mana prototype yang telah dibuat diuji langsung oleh pengguna. Fase ini bertujuan untuk menilai efektivitas, kegunaan, dan kesesuaian solusi dengan kebutuhan pengguna. Sistem e-Growth dilengkapi fitur pencatatan berat badan, tinggi badan, dan lingkar kepala anak secara digital, notifikasi jadwal posyandu, grafik pertumbuhan otomatis berbasis standar WHO, serta laporan yang dapat diunduh oleh orang tua. Pengujian dilakukan terhadap 30 kader posyandu dan 50 orang tua di tiga kelurahan di Kota Bandung. Hasil evaluasi menggunakan System Usability Scale (SUS) memperoleh skor rata-rata 82,4 yang termasuk dalam kategori "Excellent", dan 93% responden menyatakan sistem mudah digunakan. Penelitian ini menunjukkan bahwa pendekatan HCD efektif dalam menghasilkan solusi digital yang sesuai kebutuhan pengguna lapangan posyandu.

Rancang Bangun Sistem Informasi Pendaftaran Siswa Baru Berbasis Web

2026-06-27T08:42:23+00:00

The New Student Admission Process (PPDB) is an essential activity in school administration aimed at recruiting prospective students. MTs Wali Songo Asy-Syirbany still conducts its new student registration process manually, starting from filling out registration forms, recording data, and storing documents. This process creates various challenges, including the risk of data loss, recording errors, delays in information processing, and inefficiencies for prospective students who must visit the school in person to register. This study aims to design and develop a web-based New Student Registration Information System for MTs Wali Songo Asy-Syirbany to improve the effectiveness and efficiency of the registration process. The system development method used is the Prototype method because it enables direct interaction and feedback from users throughout the system development process. The system was designed using the Unified Modeling Language (UML), Entity-Relationship Diagram (ERD), and Logical Record Structure (LRS). The website-based implementation includes features such as account registration, login, registration form completion, document upload, registration verification, payment verification, applicant data management, and report generation. The results of the study indicate that the developed system can automate the PPDB process, making it easier for prospective students to register online without visiting the school. In addition, the system assists the school in managing applicant data more structured, accurate, and secure, while accelerating verification and report generation. Therefore, the web-based New Student Registration Information System at MTs Wali Songo Asy-Syirbany can serve as an effective solution for improving the quality of administrative services in the new student admission process

Evaluasi Keamanan Komunikasi Data Pada Sistem Informasi Cloud Menggunakan Enkripsi End-to-End

2026-07-11T08:40:47+00:00

The use of cloud computing technology is increasingly widespread due to its ability to facilitate the storage, management, and exchange of information over the internet. However, cloud-based systems also face security risks such as eavesdropping, theft, data manipulation, and unauthorized access. To address these risks, a security mechanism is needed that ensures the confidentiality, integrity, and availability of information. This study aims to analyze data communication security in cloud-based information systems by implementing the End-to-End Encryption (E2EE) method with the Advanced Encryption Standard (AES) 256-bit algorithm. The research method used an experimental approach with a quantitative descriptive approach. The test environment was built using Docker and the Nginx web server on the Windows Subsystem for Linux (WSL). Security evaluations were conducted based on the Confidentiality, Integrity, and Availability (CIA Triad) concept. The data encryption and decryption processes utilized OpenSSL with AES-256, while service testing was conducted using Nmap and vulnerability analysis using Nessus Essentials. The results showed that AES-256 can convert plaintext into ciphertext that is unintelligible without the decryption key. Integrity testing proved that the decrypted data was identical to the original data, thus maintaining its integrity. Availability was demonstrated by the web server remaining active on port 8080. Furthermore, the Nessus scan found no vulnerabilities with a significant risk level, only those in the informational category. In conclusion, the implementation of E2EE using AES-256 effectively improves the security of cloud-based data communications by meeting the key indicators of the CIA Triad

Optimasi Prediksi Penyakit Asma Menggunakan Improved LightGBM Berbasis Bayesian Optimization dengan Hybird SMOTE-ENN dan SHAP Feature Selection

2026-07-15T06:06:32+00:00

Asthma is one of the most prevalent chronic respiratory diseases worldwide, affecting more than 300 million people, and its early prediction is essential for timely clinical intervention. A major obstacle in data-driven asthma prediction is the severe class imbalance of large-scale clinical datasets, which biases conventional classifiers toward the majority (non-asthma) class. This study proposes an Improved LightGBM that integrates three components: Hybrid SMOTE-ENN to correct class imbalance and remove noisy boundary samples, SHAP-based feature selection to retain the most informative attributes, and Bayesian Optimization for hyperparameter tuning. A Kaggle-derived asthma dataset (409,216 SMOTE-balanced training records and 59,672 test records over 23 encoded clinical features) was used. Hybrid SMOTE-ENN reduced a 40,000-sample working set to 8,322 cleaned, balanced instances; SHAP selected 13 of 23 features; and Bayesian Optimization produced the optimal configuration (best cross-validation accuracy 92.20%). On the balanced hold-out test set the proposed Improved LightGBM achieved an accuracy of 93.87%, precision of 0.9447, recall of 0.9359, F1-score of 0.9403, and ROC-AUC of 0.9839, clearly surpassing the LightGBM Bayesian-Optimization baseline reported in the main reference (78% accuracy, ROC-AUC 0.975). Evaluation on the original imbalanced test distribution (accuracy 72.83%, ROC-AUC 0.6392) transparently reflects the difficulty of severely imbalanced real-world clinical data. The results show that combining Hybrid SMOTE-ENN, SHAP feature selection, and Bayesian Optimization yields a more accurate, interpretable, and discriminative asthma-prediction model

Analisis Komparatif Model Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, dan K-Nearest Neighbor untuk Klasifikasi Penyakit Batu Empedu Menggunakan Machine Learning

2026-07-16T05:07:29+00:00

Gallstone disease is a common medical condition that often presents without symptoms until complications occur. Early prediction of this disease can improve patient outcomes through timely intervention. This study aims to compare the performance of five classification algorithms in predicting gallstone disease using clinical data: Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbors (K-NN). The dataset used was obtained from the UCI Machine Learning Repository and contains clinical data from 319 patients, comprising 38 numerical features. Outlier handling was conducted using Winsorized Transformation and RobustScaler. Each model was optimized using GridSearchCV and evaluated using accuracy, precision, recall, F1-score, and ROC AUC metrics. The results show that SVM and Logistic Regression achieved the best performance, each with 85.9% accuracy and an AUC above 0.90. Based on these findings, Logistic Regression and SVM are recommended as the most effective classification models for gallstone disease prediction using clinical data

Analisis Penerimaan Pengguna terhadap Claude AI sebagai Virtual Coworker Menggunakan Model TAM (Technology Acceptance Model)

2026-07-23T13:26:41+00:00

The acceptance of artificial intelligence technology in the workplace has become a primary concern in Indonesia's digital transformation era. Claude AI, a generative AI assistant developed by Anthropic, demonstrates significant potential as a virtual coworker supporting work productivity. This study analyzes Indonesian professional users' acceptance of Claude AI using the Technology Acceptance Model (TAM) framework (Davis, 1989), covering Perceived Usefulness (PU), Perceived Ease of Use (PEOU), Attitude Toward Using (ATU), and Behavioral Intention (BI). A quantitative survey method was applied to 120 professional respondents in Indonesia. Regression analysis results show all hypotheses were accepted (p < 0.05): PEOU positively affects PU (β = 0.412), PU affects ATU (β = 0.387), PEOU directly affects ATU (β = 0.298), and ATU is the strongest predictor of BI (β = 0.521). These findings indicate that ease of use and perceived usefulness of Claude AI jointly contribute to positive behavioral intention among Indonesian professionals