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
Kab. sleman,
Daerah istimewa yogyakarta
INDONESIA
Telematika : Jurnal Informatika dan Teknologi Informasi
Published by Universitas Pembangunan Nasional Veteran Yogyakarta
ISSN : 1829667X     EISSN : 24609021     DOI : 10.31315
Core Subject : Engineering,
Electrical & Electronics Engineering
Arjuna Subject : -
Articles 371 Documents
 34   35   36   37   38 
Enhancing The Accuracy of Small Object Detection In Traffic Safety Attributes Using Yolov11 And Esrgan: Peningkatan Akurasi Deteksi Objek Kecil pada Atribut Keselamatan Berkendara Menggunakan Yolov11 dan ESRGAN Pinem, Tuahta Hasiholan; Haris, Muhammad
Telematika Vol 22 No 3 (2025): Edisi Oktober 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v22i3.14800

Abstract

This study aims to detect motorcycle rider attributes, specifically helmets and side mirrors, using a deep learning approach combining YOLOv11 and ESRGAN models. The proposed model addresses challenges in attribute detection under real-world conditions, such as low-resolution images, varying angles, and uneven lighting. The dataset comprises images of motorcycle riders captured by surveillance cameras (CCTV), which underwent preprocessing, augmentation, and resolution enhancement using ESRGAN to improve input quality. The results demonstrate that ESRGAN significantly enhances the performance of YOLOv11, particularly for high-resolution images. The YOLOv11 + ESRGAN model with 300 epochs achieved the best performance, with precision of 75.8%, recall of 69.1%, and an F1-score of 0.7 during testing. During validation, the model reached a precision of 0.826 and recall of 0.797, indicating good generalization capabilities. Compared to the YOLOv11 model without ESRGAN, this combination significantly improved accuracy, especially in detecting small attributes such as side mirrors. This study suggests further exploration with larger and more diverse datasets and fine-tuning to enhance detection accuracy. Additionally, integrating the model into real-world systems based on edge computing can accelerate real-time inference and reduce reliance on cloud-based servers. With broader implementation, this model has the potential to improve the efficiency and safety of AI-powered traffic monitoring systems.
Optimization Redesign UI/UX Using the User Centered Design (UCD) Method and Usability Testing System Usability Scale (SUS) (Case Study: Website RSUD Dr. Tjitrowardojo B Class Purworejo 2024) Fadilah - Akbar
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14429

Abstract

Purpose: This research aims to increase the level of usability and user experience website RSUD Dr. Tjitrowardojo Purworejo through improvements to the interface design and features website by prioritizing user needs and preferences using a User Centered Design (UCD) and testing approach usability System Usability Scale (SUS).Design/methodology/approach: The research was carried out using a quantitative approach through a questionnaire survey distributed to users website RSUD Dr. Tjitrowardojo Purworejo. The data from the survey results are then analyzed and the recommendation design is implemented in the form wireframe, mockup, and design guideline.Findings/result: Recommendation design results from redesign UI/UX significantly improves the acceptance aspect (Acceptability) and user satisfaction website Net Promoter Score (NPS). Thus the design recommendations result from the process redesign in this research can be implemented in website RSUD Dr. Tjitrowardojo Purworejo in the future because it can accurately answer user problems and their needs.Originality/value/state of the art: This research adapts the model User Centered Design (UCD) according to ISO 9241-210:2010, which has previously been used in various evaluations website hospital and website-website other. The process of identifying feature and appearance requirements website In this research, it was identified through the process of distributing user needs questionnaires and user feature display preference questionnaires.
Detection of Potato Leaf Diseases Using the YOLOv8 Method Fadel Raditya Latief
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14440

Abstract

The cultivation of potatoes faces significant challenges due to leaf diseases such as late blight and early blight, which adversely affect productivity. This study aims to evaluate the YOLOv8 model in detecting potato leaf diseases, particularly under varying object distances and different light intensity conditions. The research dataset consists of primary images collected from potato farms in Dieng and secondary data sourced from Kaggle. The model was tested at various distances (10 cm, 25 cm, 50 cm, and 75 cm) as well as under bright and dim lighting conditions. The test results showed that the model's performance tends to decline as the distance between the object and the camera increases, with the best results observed at a distance of 10 cm. For variations in light intensity, the model performed better under bright conditions compared to dim lighting, although the difference was not significant. The YOLOv8 model achieved an mAP50 score of 0.994, precision of 0.994, and recall of 0.997 during training with 50 epochs. These findings demonstrate the potential of YOLOv8 for automatic detection of potato leaf diseases with strong performance at close distances and across varying lighting conditions.  
APPLICATION OF K-MEANS AND Z-SCORE METHODS FOR UNEMPLOYMENT CLUSTERING IN REGENCIES AND CITIES OF WEST JAWA PROVINCE Vanka Angelica Putri
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14464

Abstract

Unemployment is one of the pressing issues faced by by Indonesia as a developing country. According to data from Badan Pusat Statistik (BPS), unemployment is a significant problem in West Java Province, which consistently reports an unemployment rate above the nasional average compared to other provinces in the country. Therefore, addressing this issue in West Jawa Province is critical. To tackle this challenge, an analysis of districts and cities within West Java Province is critical. To tackle this chalengge, an analysis of districts and cities within West Java is necessary to identify areas with high unemployment rates by applying clustering techniques. Clustring encompasses a variety  of methods, particularly within the realms of supervised and unsupervised approaches. One prominent unsupervised clustering technique is K-Means. This method is widely used in addressing social issues due to its simplicity, quick convergence, computational efficiency, and ease of implementation. This study aims to employ Z-Score standardization prior to applying the K-Means algorithm for clustering and to evaluate the impact of Z-Score standardization on the clustering process itself. In this research, experiments were conducted by testing the hyperparameter k ranging from 2 to 10 using Silhouette Score for evaluation. The optimal result was achieved with k = 3, yielding a score of 4.305. The application of Z-Score standardization played a significant role in preventing data dominance and ensuring unbiased clustering outcomes, as it normalized the varying scales of the variables.
Detection of Attacks on Healthcare Devices through WiFi and MQTT Protocols using Machine Learning Models. Roymond Chandra Pradana; Alva Hendi Muhammad
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14528

Abstract

Purpose: This research aims to identify and analyze cyber attacks on health devices connected via WiFi and MQTT protocols, as well as to develop an effective detection model using machine learning techniques. Design/methodology/approach: The methodology includes collecting data from open datasets, preprocessing the data, and applying several machine learning algorithms, including Random Forest, Support Vector Machine (SVM), KNN, LightGBM, SGD Classifier, Catboost, and XGBoost. This process involves testing and evaluating the models to determine their accuracy and effectiveness in detecting attacks. Findings/result: The findings indicate that the developed model is capable of detecting attacks with high accuracy, achieving 99.5% for detecting 2 categories of attacks, 91.5% for detecting 6 categories, and 86.9% for detecting 19 categories in several testing scenarios. This demonstrates that the application of machine learning techniques can enhance the detection capabilities of cyber attacks on health devices. Originality/value/state of the art: This research makes a significant contribution to the development of security solutions for the Internet of Medical Things (IoMT). By employing advanced machine learning techniques, the study highlights the importance of innovation in cyber attack detection and provides recommendations for further research in developing more efficient algorithms.
Sentiment Analysis of Indonesian National Team Player Composition Using the Convolutional Neural Network fishilia saqila istanti; Ahmad Riyadi Riyadi
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14568

Abstract

Football is one of the most popular sports in Indonesia, especially when it comes to supporting the Indonesian National Team. The composition of the national team players is a frequently discussed topic among the public, particularly on social media platforms like YouTube. YouTube is one of the most popular social media platforms for expressing public opinions. Sentiment analysis can help identify and address issues based on public opinions shared on social media platforms such as YouTube.The classification method used in this study is Convolutional Neural Network. The dataset was obtained through data scraping, resulting in 3,200 data points. The labeling process was conducted manually by involving three annotators. The labeling results indicate 1,036 instances of "proportional," 1,416 of "not proportional," and 747 of "doubtful."Next, preprocessing was performed on the labeled data, followed by word weighting using TF-IDF. After that, modeling was conducted using Convolutional Neural Network, and the final step involved developing an interactive web application using Streamlit to analyze text sentiment based on the trained model. The accuracy result, comparing 80% training data and 20% testing data, achieved an accuracy of 89%. Meanwhile, the sentiment analysis results show that the "not proportional" sentiment appeared more frequently than the "proportional" and "doubtful" sentiments.
Decision Support System f`or Boarding House Recommendations for Students in Kendari City Using the Weighted Product Method Andi Anugrah Ma'Arif
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14619

Abstract

Purpose: This research aims to develop a Decision Support System that is able to provide boarding house recommendations for students in Kendari City. This system is designed to make it easier for students to choose a boarding house that suits their criteria and preferences. Design/methodology/approach: This study uses the Weighted Product (WP) method. Boarding house data was obtained through field surveys and information collection from boarding house providers in Kendari City. The criteria considered include the type of boarding house, monthly rental price, distance to campus, facilities, availability of toilets, availability of kitchens, and security. Each criterion is weighted according to its level of importance. Findings/result: The research results show that the DSS developed is able to provide boarding recommendations that suit student preferences. This system makes it easier for students to find boarding houses that best suit their needs. Originality/value/state of the art: Previously, boarding house recommendation systems were rarely implemented with a WP-based approach that considered various criteria simultaneously. This research is expected to contribute to the development of a recommendation system that can be implemented in various other cities by adjusting relevant variables and criteria weights.
Sentiment Analysis of Traveloka App User Reviews Using Word2vec and LSTM Danica Kirana
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14640

Abstract

Objective: As the travel trend in Indonesia increases, online travel agent (OTA) services such as Traveloka are becoming increasingly popular. However, with high competition in this industry, companies need to understand customer sentiment to improve service quality. This study aims to develop an automated sentiment analysis model on Traveloka app user reviews using a deep learning approach with Long 0Short-Term Memory (LSTM) and Word2Vec word representation. Design/method/approach: This study uses a quantitative method with stages including data collection, preprocessing, labeling, and modeling. The data used comes from Kaggle, which contains 12,689 Traveloka user reviews on the Google Play Store between January and October 2023. Preprocessing is carried out using case folding, tokenization, stopword removal, and stemming. Next, the data is represented in vector form using Word2Vec before being trained with an LSTM model. Experiments are conducted with various vector sizes (100, 200, 300, and 400) to evaluate their effect on model accuracy. Results: The test results show that the LSTM model with a vector size of 400 and a training dataset of 4073 achieved the highest accuracy of 89%, while vector sizes of 100, 200, and 300 produced accuracies of 85%, 86%, and 82%, respectively. This indicates that the dimensionality of word representation and the amount of data can affect the model's performance in understanding user sentiment. Originality/state of the art: This study contributes to the development of deep learning-based sentiment analysis models in Indonesian, especially in the travel services sector. Different from previous studies that mostly use shallow learning methods such as Naïve Bayes and SVM, this study adopts the Word2Vec and LSTM approaches that are more effective in capturing semantic relationships between words. This study also provides insights into the effect of Word2Vec vector size and training dataset size on LSTM in improving the accuracy of sentiment analysis models.
ETL Implementation for Centralizing Academic Data in an Educational Bootcamp Nathania Santa Nigel Simbolon; Didik Kurniawan; Rahman Taufik
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14668

Abstract

Inefficiencies in decentralized data management have become a critical issue for bootcamp companies. This study explores the implementation of an Extract, Transform, Load (ETL) process to centralize academic data at PT. Hacktivate Teknologi Indonesia (Hacktiv8) in order to enhance learning process efficiency. With the rapid growth of disorganized academic data, an integrated automation system is required to monitor and evaluate bootcamp participants' progress. The ETL process employed in this study collects data from various Google Spreadsheets, transforms it into a normalized structure, and stores it in a centralized data warehouse using Google Cloud Platform. The research follows the 4-Steps-Kimball methodology to design the data warehouse schema and evaluates data quality based on the ISO/IEC 25012 standard. Data quality assessment is conducted through two approaches: (1) technical validation using Great Expectations shows key attribute accuracy of 98.44%, consistency of 97%, and completeness of 100%, despite 5–7% data loss due to the removal of null values in instructor columns to maintain referential integrity; (2) stakeholder feedback (N=10) collected via a Likert scale (1–5) yields an average score of 4/5, with the highest ratings in data consistency and centralized structure. The evaluation results indicate that the implemented ETL system is highly efficient and positively received by users, although suggestions were made for improvements in system documentation and adaptability. This study is expected to contribute significantly to data-driven decision-making in non-formal education environments.
Clustering of Emergency Events in Surabaya Using K-Means Algorithm Ninda Istiqoma
Telematika Vol 23 No 1 (2026): Edisi Februari 2025
Publisher : Jurusan Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v23i1.14701

Abstract

Purpose: To optimize knowledge and simplify the analysis process, the clustering method is used to group emergencyevent data that occurred in the Surabaya City area. Design/methodology/approach: The clustering method usedin this research is the K-Means Clustering. Findings/result: The results of cluster 0 contain sub-districts with a highlevel of vulnerability to emergencies such as Dukuh Pakis, Genteng, Gubeng, Rungkut, Sawahan, Sukomanunggal and Tambaksari sub-districts. Cluster 1 contains sub-districts with a low level of vulnerability to emergencies such as Asem Rowo, Benowo, Bulak, Bubutan, Gunung Anyar, Gayungan, Jambangan, Karang Pilang, Krembangan, Kenjeran, Lakarsantri, Mulyorejo, Pakal, Pabean Cantian, Sambikerep, Semampir, Sukolilo, Simokerto, Tegalsari, Tandes, Tenggilis Mejoyo, Wiyung, and Wonocolo. Cluster 2 contains sub districts with a moderate level of vulnerability to emergencies such as Wonokromo Sub- district. Validation of the cluster results obtained using the Silhouette coefficient is 0.610. Originality/value/state of the art: This research uses emergency incident data directly obtained from BPBD Surabaya and processed using the K-Means Clustering method.

Page 37 of 38 | Total Record : 371

 34   35   36   37   38 

Filter by Year

2010 2026


Reset
Filter By Issues
All Issue Vol 23 No 1 (2026): Edisi Februari 2025 Vol 22 No 3 (2025): Edisi Oktober 2025 Vol 22 No 2 (2025): Edisi Juni 2025 Vol 22 No 1 (2025): Edisi Februari 2025 Vol 21 No 3 (2024): Edisi Oktober 2024 Vol 21 No 2 (2024): Edisi Juni 2024 Vol 21 No 1 (2024): Edisi Pertama 2024 Vol 21, No 1 (2024): Edisi Februari 2024 Vol 20, No 3 (2023): Edisi Oktober 2023 Vol 20 No 3 (2023): Edisi Oktober 2023 Vol 20, No 2 (2023): Edisi Juni 2023 Vol 20 No 2 (2023): Edisi Juni 2023 Vol 20 No 1 (2023): Edisi Februari 2023 Vol 20, No 1 (2023): Edisi Februari 2023 Vol 19, No 3 (2022): Edisi Oktober 2022 Vol 19, No 2 (2022): Edisi Juni 2022 Vol 19, No 1 (2022): Edisi Februari 2022 Vol 18, No 3 (2021): Edisi Oktober 2021 Vol 18, No 2 (2021): Edisi Juni 2021 Vol 18, No 1 (2021): Edisi Februari 2021 Vol 17, No 2 (2020): Edisi Oktober 2020 Vol 17, No 1 (2020): Edisi April 2020 Vol 16, No 2 (2019): Edisi Oktober 2019 Vol 16, No 1 (2019): Edisi April 2019 Vol 15, No 2 (2018): Edisi Oktober 2018 Vol 15, No 1 (2018): Edisi April 2018 Vol 14, No 2 (2017): Edisi Oktober 2017 Vol 14, No 1 (2017): Edisi April 2017 Vol 13, No 2 (2016): Edisi Juli 2016 Vol 13, No 1 (2016): Edisi Januari 2016 Vol 12, No 2 (2015): Edisi Juli 2015 Vol 12, No 1 (2015): Edisi Januari 2015 Vol 11, No 1 (2014): Edisi Juli 2014 Vol 10, No 2 (2014): Edisi Januari 2014 Vol 10, No 1 (2013): Juli 2013 Vol 9, No 2 (2013): Edisi Januari 2013 Vol 9, No 1 (2012): Edisi Juli 2012 Vol 8, No 2 (2012): Edisi Januari 2012 Vol 8, No 1 (2011): Edisi Juli 2011 Vol 7, No 2 (2011): Edisi Januari 2011 Vol 7, No 1 (2010): Edisi Juli 2010 Vol 6, No 2 (2010): Edisi Januari 2010 More Issue