Claim Missing Document
Check
Articles

Found 20 Documents
Search

Model Penelitian Basis Data untuk Sistem Informasi Skala Besar Ega Seladevi; Desi Ramadani Putri; Agung Wibowo
Jurnal Informatika dan Kesehatan Vol. 2 No. 2 (2025): IKN : Jurnal Informatika dan Kesehatan
Publisher : Universitas Ngudi Waluyo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35473/ikn.v2i2.3804

Abstract

Database management is a crucial aspect of developing large-scale information systems that require high efficiency, scalability, and reliability. This article discusses a research model based on scientific methodology to design and optimize databases for large-scale information systems. The research approach includes exploring database schema design techniques, evaluating performance using large datasets, and implementing optimization strategies such as indexing, data partitioning, and replication. This study also highlights the comparison between relational (SQL) and non-relational (NoSQL) databases in the context of complex information system requirements. The research findings show that applying a systematic methodology can improve data processing efficiency by up to 30% and accelerate system response time. This article provides practical guidelines for developers and researchers in designing reliable database solutions to meet large-scale demands, as well as guidance for information system developers in selecting and implementing the appropriate database model. ABSTRAK Pengelolaan basis data merupakan aspek krusial dalam pengembangan sistem informasi skala besar yang memerlukan efisiensi, skalabilitas, dan keandalan tinggi. Artikel ini membahas model penelitian berbasis metodologi ilmiah untuk merancang dan mengoptimalkan basis data pada sistem informasi skala besar. Pendekatan penelitian mencakup eksplorasi teknik perancangan skema basis data, evaluasi performa menggunakan dataset besar, serta implementasi strategi optimasi seperti indexing, partisi data, dan replikasi. Studi ini juga menyoroti perbandingan antara basis data relasional (SQL) dan non-relasional (NoSQL) dalam konteks kebutuhan sistem informasi yang kompleks. Hasil penelitian menunjukkan bahwa penerapan metodologi yang sistematis mampu meningkatkan efisiensi pengolahan data hingga 30% dan mempercepat waktu respons sistem. Artikel ini memberikan panduan praktis bagi pengembang dan peneliti dalam merancang solusi basis data yang handal untuk memenuhi tuntutan skala besar, serta memberikan panduan bagi para pengembang sistem informasi dalam memilih dan mengimplementasikan model basis data yang tepat.
Rancang Bangun Buku Tamu Digital Berbasis Semantic Web dengan Metode Waterfall Retno Aoktaviani, Bunga Dea; Wibowo, Agung
Jurnal Algoritma Vol 22 No 2 (2025): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.22-2.3018

Abstract

The advancement of technology has driven progress across various professional fields, including the administrative activities of the Indonesian Midwives Association (IBI). One of the IBI branch offices in Semarang Regency still records visitor data manually, which poses several risks such as difficulties in retrieving archives, physical damage to logbooks, and reduced administrative efficiency. This study was conducted to provide a solution to these issues. The research employed the Waterfall method, consisting of analysis, design, implementation, and testing stages. The digital guestbook system was developed as a web-based application using PHP (Hypertext Preprocessor) and a MySQL database. The integration of semantic web technology enables more advanced data processing to support analysis and decision-making. Based on eleven test scenarios using black-box testing, the system achieved 100% validity. Furthermore, data search time improved significantly—by approximately 80–90% compared to traditional manual recording. The developed application has proven effective in increasing efficiency in managing visitor data.
SMARTGRAD: Prediksi Kelulusan Tepat Waktu Mahasiswa Kampus Merdeka Wibowo, Agung; Pratama, Ade; Setiawan, Dwi
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.v15i2.4605

Abstract

On-time graduation is a primary indicator of student success and serves as a key benchmark for the quality of higher education institutions. This study aims to develop SmartGrad, a prediction model for on-time graduation based on the Naive Bayes algorithm, supported by feature selection using Decision Tree. The model integrates academic variables (semester GPA, average grades) and non-academic variables (types of MBKM, employment status, age) to produce accurate and contextual predictions. The research dataset comprises 313 entries with 17 attributes, processed through feature selection and classification stages. Evaluation results demonstrate the model's excellent performance, with an average accuracy of 88.8%, precision of 90.5%, recall of 97.9%, and an F1-score of 94.0%. The implementation of SmartGrad as an interactive web application based on Streamlit supports transparent and easily comprehensible decision-making. The novelty of this research lies in the integration of MBKM factors and employment status into the prediction model, as well as the application of an interpretable AI approach to support higher education policies and the achievement of Sustainable Development Goal 4 (Quality Education). These findings are expected to serve as a strategic reference for higher education administrators in enhancing academic quality and the effectiveness of the Freedom of Learning Independent Campus program.
Implementasi Machine Learning untuk Prediksi Performa Lari Berdasarkan Data Strava Ardi Kurniawan; Didiet Hendrawan; Agung Wibowo
Jurnal Informatika dan Kesehatan Vol. 3 No. 1 (2026): IKN : Jurnal Informatika dan Kesehatan
Publisher : Universitas Ngudi Waluyo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35473/ikn.v3i1.4870

Abstract

This study aims to develop a predictive model to estimate running performance represented by pace (min/km) using activity data from Strava. The motivation stems from the fact that runners’ daily activity logs are often used only for descriptive tracking rather than as an evidence-based foundation for personalized and predictive training planning. The dataset consists of 120 running activities, with predictors including distance (km), training duration (min), elevation gain (m), and heart rate (bpm). Data preprocessing involved invalid record removal, outlier handling, and format standardization. A multiple linear regression model was then constructed and evaluated using the coefficient of determination (R²) and error metrics, namely Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) on the test set. The results indicate that training load and physiological variables jointly explain a meaningful proportion of pace variability, offering a quantitative basis for understanding factors associated with running performance. Overall, these findings suggest that Strava data can be leveraged to build practical performance prediction models to support data-driven training decisions.   ABSTRAK Penelitian ini bertujuan mengembangkan model prediktif untuk memperkirakan performa lari yang direpresentasikan oleh pace (menit/km) menggunakan data aktivitas dari platform Strava. Permasalahan yang melatarbelakangi penelitian ini adalah pemanfaatan data aktivitas harian pelari yang masih dominan bersifat deskriptif (evaluasi masa lalu) dan belum banyak digunakan untuk mendukung perencanaan latihan yang lebih terukur dan personal. Dataset penelitian terdiri dari 120 aktivitas lari, dengan variabel prediktor meliputi jarak tempuh (km), durasi latihan (menit), perubahan elevasi (m), dan denyut jantung (bpm). Data dipraproses melalui pembersihan data tidak valid, penanganan nilai ekstrem, dan standarisasi format, kemudian dianalisis menggunakan regresi linear berganda. Evaluasi model dilakukan menggunakan koefisien determinasi (R²) serta metrik galat Mean Absolute Error (MAE) dan Root Mean Square Error (RMSE) pada data uji. Hasil penelitian menunjukkan bahwa kombinasi variabel latihan dan fisiologis dapat menjelaskan variasi pace secara bermakna, serta memberikan dasar kuantitatif untuk memahami faktor-faktor yang berasosiasi dengan performa lari. Temuan ini mengindikasikan bahwa data Strava berpotensi dimanfaatkan untuk membangun model prediksi performa yang aplikatif sebagai dukungan pengambilan keputusan latihan berbasis data.
Implementasi dan Evaluasi Sistem Informasi Manajemen Keuangan UMKM Berbasis Digital di Kabupaten Semarang Menggunakan Pendekatan Design Science Research Kustiyono; Agung Wibowo; Ajeng Ramadhanti Syafitri
Jurnal Informatika dan Kesehatan Vol. 3 No. 1 (2026): IKN : Jurnal Informatika dan Kesehatan
Publisher : Universitas Ngudi Waluyo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35473/ikn.v3i1.4993

Abstract

Micro, Small, and Medium Enterprises (MSMEs) in Kabupaten Semarang play a strategic role in the regional economy; however, they still face challenges in transaction recording and financial statement preparation. Many MSMEs have not implemented a structured financial management information system, resulting in financial information that is neither accurate nor timely. This study aims to implement and evaluate a digital-based accounting management information system for MSMEs developed using the Design Science Research (DSR) approach. The DSR method was applied through the stages of problem identification, definition of solution objectives, design and development, demonstration, and evaluation. The results indicate that the implemented financial management information system improves the accuracy of financial record-keeping, enhances the efficiency of financial report preparation, and supports managerial decision-making within MSMEs. This study provides practical contributions for MSMEs in Kabupaten Semarang and academic contributions to the development of financial management information system research based on the DSR approach.   ABSTRAK Usaha Mikro, Kecil, dan Menengah (UMKM) di Kabupaten Semarang memiliki peran strategis dalam perekonomian daerah, namun masih menghadapi permasalahan dalam pencatatan transaksi dan penyusunan laporan keuangan. Banyak UMKM belum menerapkan sistem informasi manajemen keuangan yang terstruktur sehingga  informasi manajemen keuangan tidak tersedia secara akurat dan tepat waktu. Penelitian ini bertujuan untuk mengimplementasikan dan mengevaluasi sistem informasi manajemen akuntansi UMKM berbasis digital yang telah dikembangkan dengan menggunakan pendekatan Design Science Research (DSR). Metode DSR diterapkan melalui tahapan identifikasi masalah, penentuan tujuan solusi, perancangan dan pengembangan, ujicoba, serta evaluasi. Hasil penelitian menunjukkan bahwa sistem informasi manajemen keuangan yang diimplementasikan mampu meningkatkan akurasi pencatatan keuangan, efisiensi penyusunan laporan, serta mendukung pengambilan keputusan manajerial UMKM. Penelitian ini memberikan kontribusi praktis bagi UMKM di Kabupaten Semarang dan kontribusi akademik dalam pengembangan penelitian sistem informasi manajemen keuangan berbasis DSR.
Pengembangan Sistem Analisis Defect Proses Jahit Berbasis Fishbone Diagram dan FMEA Menggunakan Aplikasi Web Widia Jelita Gulo; Agung Wibowo
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3135

Abstract

The sewing process is one of the important stages in clothing production, but defects often occur that can reduce product quality and increase production costs. This study aims to develop a web-based sewing process defect analysis system that utilizes the Fishbone Diagram and Failure Mode and Effects Analysis (FMEA) methods. This system is designed to identify the most common types of defects, classify their causes, including human factors, machines, work methods, materials, and the environment using Fishbone Diagrams, and evaluate the risk level of each factor through FMEA. The analysis results show that human factors, such as operator skills and accuracy, as well as machine conditions, such as needles and components that are subject to wear and tear, are significant causes of defects. Through FMEA, the system provides a risk assessment so that repair priorities can be determined more objectively. The recommendations generated include operator training, periodic machine maintenance, and the implementation of standard operating procedures. The development of this web application contributes to providing a systematic, easily accessible defect analysis tool that can be applied in the garment industry to improve the quality of the sewing process.
Sistem Pendukung Keputusan Untuk Memilih Pemasok Terbaik Menggunakan Metode Simple Additive Weighting (SAW) Farid Achmad; Agung Wibowo
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3139

Abstract

Choosing the right supplier is an important part of maintaining an effective and efficient supply chain. In reality, this decision can be very difficult because it involves many different factors, such as price, quality, delivery time, and supplier reliability. This study presents a Decision Support System (DSS) that uses the Simple Additive Weighting (SAW) method to help select the best supplier based on these criteria. The SAW method is known for its straightforward approach to multi-criteria decision making, making it an ideal choice for this type of task. A prototype of the system was developed and tested using sample supplier data to assess its performance. Based on the results, the system was able to provide accurate and consistent recommendations, helping users identify the most suitable suppliers for their needs. This research offers a practical tool that can support businesses in making better supplier decisions and demonstrates how the SAW method can be effectively applied in everyday business scenarios.
Analisis Sentimen Ulasan Produk Marketplace Indonesia Menggunakan Naive Bayes dan SVM dengan Label Berdasarkan Rating Levi Ardin Gulo; Agung Wibowo
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3206

Abstract

Sentiment analysis aims to identify user opinions about products on marketplaces such as Shopee and Tokopedia. This study classifies product review sentiment using Naive Bayes (NB) and Support Vector Machine (SVM). The dataset underwent text preprocessing, including case folding, tokenization, stopword removal, and stemming, then was represented using TF-IDF. The results show that Support Vector Machine (SVM) achieved the highest accuracy of 94.54%, but had a very low negative class recall (5.71%), indicating a strong bias towards the majority class. In contrast, Naïve Bayes (NB) recorded a lower accuracy of 67.88%, but showed more balanced performance with a negative class recall of 48.57%. Conversely, NB provided more balanced performance between positive and negative classes despite its slightly lower accuracy. These findings emphasize the importance of considering class imbalance in sentiment analysis, especially for applications that require consumer complaint detection. This research is expected to serve as a reference for the development of automatic sentiment analysis systems on marketplace platforms with a focus on performance balance between classes.
Perbandingan K-Medoids(PAM) Dan K-Means Untuk Semgentasi Produk Smartphone Di Shoope Indonesia Berdasarkan Harga Rating Dan Jumlah Ulasan: Studi Periode Maret 2026 Amanda Nur Haliza; Agung Wibowo
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3324

Abstract

This study aims to segment smartphone products based on the variables of Price, Rating, and Number of Reviews using the K-Means and K-Medoids methods. The dataset used consists of 400 smartphone products that have undergone data normalization as part of the preprocessing stage. The number of clusters was determined using an internal evaluation method, and the optimal number of clusters was found to be four (K=4). The clustering results show that both methods are capable of forming significantly different product group characteristics based on a combination of price level, user rating quality, and review intensity. The K-Means method produces a more structured cluster separation based on centroid values and is effective in representing the average data distribution. Meanwhile, K-Medoids demonstrate better resilience against outliers because cluster centers are represented by actual objects (medoids), making them more stable on heterogeneous data. Based on a comparative analysis of the methods’ characteristics and cluster evaluation results, K-Medoids demonstrates more robust performance for datasets with significant price variation. The findings of this study can serve as a basis for decision-making in marketing strategies and product clustering on e-commerce platforms.
Kombinasi Decision Tree dan Naïve Bayes dengan Explainable AI untuk Prediksi Dropout Agung Wibowo; Kustiyono; Eko Nur Hermansyah
Jurnal Algoritma Vol 23 No 1 (2026): Jurnal Algoritma
Publisher : Institut Teknologi Garut

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33364/algoritma/v.23-1.3367

Abstract

Predicting student dropout risk is crucial for supporting early intervention and accountable academic decision-making. This study proposes a multi-class classification (Dropout, Enrolled, Graduate) using voting (Naïve Bayes and Decision Tree) and Explainable AI to enhance transparency. The dataset consists of 4,424 records with 36 features. Evaluation was conducted using k-fold stratified cross-validation (k=10) and the F1-macro metric. The results show that model performance is relatively close and stable at k=10, so model selection must consider the trade-off between performance and interpretability. The main contribution of this research is a web-based early warning DSS prototype that integrates Voting (NB+DT) with an XAI module (SHAP–LIME) so that predictions can be explained, audited, and followed up with academic intervention recommendations.