Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal Sistemasi: Jurnal Sistem Informasi Jiko (Jurnal Informatika dan komputer) JURNAL TEKNOLOGI DAN OPEN SOURCE Paradigma
Nur Latifah Dwi Mutiara Sari
Universitas PGRI Semarang
Computer Science & IT Electrical & Electronics Engineering

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Performance Comparison of K-Means Algorithm and BIRCH Algorithm in Clustering Earthquake Data in Indonesia with Web-Based Map Visualization Baromim Triwijaya; Setyoningsih Wibowo; Nur Latifah Dwi Mutiara Sari
JURNAL TEKNOLOGI DAN OPEN SOURCE Vol. 8 No. 1 (2025): Jurnal Teknologi dan Open Source, June 2025
Publisher : Universitas Islam Kuantan Singingi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36378/jtos.v8i1.4400

Abstract

This study applies the K-Means and BIRCH algorithms to cluster earthquake data in Indonesia based on geographic coordinates (latitude and longitude), depth, and magnitude from 2008 to 2023. Due to its position at the intersection of three major tectonic plates, Indonesia is highly prone to earthquakes, making the mapping of vulnerable regions essential for disaster risk reduction. K-Means is selected for its simplicity and clustering effectiveness, while BIRCH is known for its scalability and efficiency in processing large datasets. The clustering process involves data preprocessing and normalization, followed by determining the optimal number of clusters using the Elbow method. Initial findings indicate that K-Means produces more distinct and well-separated clusters than BIRCH, with Silhouette Scores of 0.3501 and 0.2247, respectively. However, after expanding the dataset to 121,123 records and incorporating additional attributes such as mag_type, phasecount, and azimuth_gap, BIRCH demonstrated a significant improvement in performance, achieving a Silhouette Score of 0.3489—surpassing K-Means, which dropped to 0.1293. These results suggest that BIRCH is more effective for clustering large and complex datasets. The final clustering results are visualized on a web-based map to support spatial analysis and the identification of earthquake-prone zones.
Facial Skin Disease Classification Using Swin Transformer V2 and ResNet-50 in a Flask-Based System Shinta Arum Imaniyah; Febrian Murti Dewanto; Nur Latifah Dwi Mutiara Sari
Paradigma - Jurnal Komputer dan Informatika Vol. 28 No. 1 (2026): March 2026 Period
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/p.v28i1.12381

Abstract

Facial skin diseases are common health conditions that can significantly affect both physical and psychological well-being. Early identification is essential to minimize the risk of disease progression. However, in many areas, there is still a lack of access to dermatological care. Although deep learning algorithms have been widely used in medical image categorization, few studies offer a direct comparison between convolutional neural networks (CNN) and transformer-based architectures within a cohesive experimental framework, especially concerning the classification of facial skin diseases. This study compares the effectiveness of ResNet-50 with Swin Transformer V2 and develops a deep learning system to classify six different types of skin problems on the face. The models were evaluated using accuracy, precision, recall, and F1-score after the dataset was divided into subsets for testing, validation, and training. According to the trial results, Swin Transformer V2 achieves an astounding accuracy of 97.54%, outperforming ResNet-50, which achieves 94.44%. The training curves indicate stable learning behavior with minimal overfitting. Grad-CAM visualization is applied to improve interpretability by highlighting relevant regions in the images. The best-performing model is implemented in a Flask-based web application as a prototype system for early detection. These results demonstrate how transformer-based architectures can improve classification performance and highlight their potential applications in practical diagnostic support systems
IMPLEMENTATION OF GEOSPATIAL INTELLIGENCE FOR SENTIMENT ANALYSIS ON STUNTING POLICY IN BATANG REGENCY USING INDOBERT Dian Fitria Maharani; Bambang Agus Herlambang; Nur Latifah Dwi Mutiara Sari
JIKO (Jurnal Informatika dan Komputer) Vol 9 No 2 (2026)
Publisher : Program Studi Teknik Informatika Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v9i2.12620

Abstract

This study develops a Geospatial Artificial Intelligence (GeoAI)-based WebGIS that integrates IndoBERT sentiment classification to evaluate public percetion of stunting-management policy in Batang Regency, Central Java, Indoneia. The Cross-Industri Standart Process for Data Mining (CRISP-DM) framework was applied to the sentiment-analysis pipeline, while Rapid Application Development (RAD) governed the system construction. A total of 478 public-opinion responses were collected through questionnaires from residents of fifteen sub-districts, preprocessed through data cleaning, case folding, tokenizing, stopword removal, and stemming, then labeled and classified into positive, neutral, and negative sentiment using a fine-tuned IndoBERT model. The system was built with Python, Flask, Leaflet.js, and QGIS to visualize sentiment spatially. On a held-out test set of 96 samples, the model achieved 82.29% accuracy, 83.49% weighted precision, 82.29% weighted recall, and an 82.58% weighted F1-score (macro F1-score of 0.77), with class-weighted loss applied during fine-tuning to counter a severe class imbalance in the labeled dataset (Imbalance Ratio = 5.82). Spatial analysis showed that Bandar Sub-district recorded both the highest number of positive (37) and negative (8) responses, indicating the highest level of public engagement, Batang Sub-district recorded the highest number of neutral responses (46). System functionality was further validated through User Acceptance Testing and Black Box Testing, each covering nine functional scenarios spanning authentication, dashoard acces, sentiment-analysis display, spatial map interaction, and page navigation; all eighteen test scenarios were completed successfully (100% valid), confirming that the system operates correctly and satisfies the intended user requirements. The resulting GeoAI-based WebGIS enable policymakers to identify sub-districts requiring closer attention and design more targeted, evidence-based interventions. These findings demonstrate that integrating sentiment classification with spatial visualization provides greater insight into public perception than statistical data.
Comparison of Sequential and Logarithmic Data Access Methods based on Archiving Scenarios Validity Evan Averill Andika; Bambang Agus Herlambang; Nur Latifah Dwi Mutiara Sari
SISTEMASI Vol 15, No 8 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i8.6768

Abstract

The growing volume of customer documents in financing companies presents challenges in archive retrieval when the search method is not well suited to increasing data volumes. This study aims to compare Linear Search and Binary Search methods within a web-based customer document archiving information system at PT Multindo Auto Finance. An experimental comparative analysis was conducted by empirically evaluating both algorithms under identical conditions and using the same dataset. The dataset consisted of 4,996 customer documents and was evaluated under two testing scenarios: searching for data that exists in the system and searching for data that does not exist. The primary performance metric was execution time, measured in milliseconds (ms). The results show that Binary Search outperformed Linear Search in both scenarios, achieving an execution time of 0.01 ms, while Linear Search required 0.09 ms when the target data was found and 0.23 ms when the target data was not found. However, Binary Search requires the data to be sorted, which may limit its suitability for systems containing frequently updated or dynamically changing data. The study concludes that Binary Search is recommended for large-volume systems with relatively static datasets, whereas Linear Search is more suitable for systems with dynamic datasets that are continuously updated.
Co-Authors Bambang Agus Herlambang, Bambang Baromim Triwijaya Dian Fitria Maharani Evan Averill Andika Febrian Murti Dewanto Setyoningsih Wibowo Shinta Arum Imaniyah