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
Kota tangerang selatan,
Banten
INDONESIA
TEKNIK INFORMATIKA
Published by Universitas Islam Negeri Syarif Hidayatullah Jakarta
ISSN : 19799160     EISSN : 25497901     DOI : -
Core Subject : Science,
Computer Science & IT
Jurnal Teknik Informatika merupakan wadah bagi insan peneliti, dosen, praktisi, mahasiswa dan masyarakat ilmiah lainnya untuk mempublikasikan artikel hasil penelitian, rekayasa dan kajian di bidang Teknologi Informasi. Jurnal Teknik Informatika diterbitkan 2 (dua) kali dalam setahun.
Arjuna Subject : -
Articles 282 Documents
 25   26   27   28   29 
Small Object Detection and Object Counting for Primary Roe Dataset Based on Yolo Saputra, Wahyu Andi; Nugroho, Nicolaus Euclides Wahyu; Febrianto, Dany Candra; Yunus, Andi Prademon; Gustalika, Muhammad Azrino; Choo, Yit Hong
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.46063

Abstract

This research offers an initial exploration into the effectiveness of three variations of the YOLOv8 model original, trimmed, and YOLOv8n.pt in combination with two distinct datasets characterized by tight and loose distributions of roe, aimed at enhancing small object detection and counting accuracy. Utilizing a primary roe dataset across 776 images, the research systematically compares these model-dataset configurations to identify the most effective combination for precise object detection. The experimental results reveal that the YOLOv8n.pt model combined with the loosely distributed dataset achieves the highest detection performance, with a mean Average Precision (mAP) of 53.86%. This outcome underscores the critical impact of both model selection and data distribution on the detection accuracy in machine learning applications. The findings highlight the importance of tailored model and dataset synergies in optimizing detection tasks, particularly in complex scenarios involving small, densely clustered objects. This research contributes valuable insights into the strategic deployment of neural network architectures for refined object detection challenges.
Detection of Vulgarity in Anime Character: Implementation of Detection Transformer Suciati, Amalia; Sari, Dian Kartika; Yunus, Andi Prademon; Amaliah, Nuuraan Rizqy
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i1.46064

Abstract

Vulgar and pornographic content has become a widespread issue on the internet, appearing in various fields include anime. Vulgar pornographic content in anime is not limited to the sexuality genre; anime from general genres such as action, adventure, and others also contain vulgar visual. The main focus of this research is the implementation of the Detection Transformer (DETR) object detection method to identify vulgar parts of anime characters, particularly female characters. DETR is a deep learning model designed for object detection tasks, adapting the attention mechanism of Transformers. The dataset used consists of 800 images taken from popular anime, based on viewership rankings, which were augmented to a total of 1,689 images. The research involved training models with different backbones, specifically ResNet-50 and ResNet-101, each with dilation convolution applied at different stages. The results show that the DETR model with a ResNet-50 backbone and dilation convolution at stage 5 outperformed other backbones and dilation configurations, achieving a mean Average Precision of 0.479 and  of 0.875. The other result is dilated convolution improves small object detection by enlarging the receptive field, applying it in early stages tends to reduce spatial detail and harm performance on medium and large objects. However, the primary focus of this research is not solely on achieving the highest performance but on exploring the potential of transformer-based models, such as DETR, for detecting vulgar content in anime. DETR benefits from its ability to understand spatial context through self-attention mechanisms, offering potential for further development with larger datasets, more complex architectures, or training at larger data scales.
Efficiency vs. Accuracy: A Comparative Analysis of Lightweight MobileNetV2 and VGG16 for Brain Tumor MRI Classification Using Deep Feature Extraction Nasution, Raja Anan; Mhd. Furqan; Rika Rosnelly
JURNAL TEKNIK INFORMATIKA Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v19i1.45002

Abstract

Brain tumor detection using magnetic resonance imaging (MRI) is a crucial task for early diagnosis and treatment planning, requiring models that are not only accurate but also computationally efficient. This study presents a comparative analysis of two Convolutional Neural Network (CNN) architectures, MobileNetV2 and VGG16, combined with Principal Component Analysis (PCA) for deep feature dimensionality reduction. The dataset consists of 253 brain MRI images (155 tumor and 98 non-tumor), which have been preprocessed and divided into training and testing sets using an 80:20 stratification split. Experimental results show that MobileNetV2 with PCA achieves an accuracy of 86.27%, with a precision of 87.50% and a recall of 90.32% for the tumor class, demonstrating balanced performance in classifying tumor and non-tumor images. VGG16 with the same PCA configuration achieves an accuracy of 64.71%, with a recall of 100% for the tumor class but a low recall of 10% for the non-tumor class. These findings suggest that extreme dimensionality reduction affects deep feature representation differently depending on the original feature structure. The results show that MobileNetV2 provides a better balance between accuracy and feature compactness at high dimensionality reduction settings, making it more suitable for resource-constrained medical image classification scenarios.
Handling Class Imbalance in Fan Sentiment Analysis: Naïve Bayes with TF-IDF on Instagram and Twitter Nimah, Khomsatun; Rakha Arian Archaniga
JURNAL TEKNIK INFORMATIKA Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v19i1.46733

Abstract

Social media platforms such as Instagram and Twitter serve as major channels for football fans to share opinions and respond to club-related dynamics, including Manchester United. Beyond fan interaction, these platforms play an important role in business, marketing, and information exchange, making efficient text classification essential. This study applies the Naïve Bayes to analyze sentiment toward Manchester United’s performance based on 2,500 Instagram comments and 2,500 Twitter comments. The research process included data cleaning, sentiment labeling, and preprocessing steps. An imbalance in positive, negative, and neutral comments was managed using data balancing techniques to enhance model reliability. Results show that balancing significantly improved performance, with accuracy reaching 83.87% for Instagram and 82.48% for Twitter. Improvements in precision, recall, and F1-score further confirmed Naïve Bayes’ capability to handle complex, noisy, and diverse social media language. The study highlights how dataset size, effective preprocessing, and accurate labeling contributed to performance gains. Overall, Naïve Bayes proved effective for sentiment classification, offering insights into public perception of Manchester United. These findings emphasize its potential for large-scale social media analysis, supporting both academic research and practical applications in digital marketing and fan engagement strategies.
A Socio-Technical Windows 11 Hardening Framework Integrating Ferret-Windows and CIS Benchmarks Prasetyo Adi Wibowo Putro; Ray Novita Yasa Yasa; Mochammad Latief Reswandana Musonip; Dimas Nugroho Putro; Agry Zharfa
JURNAL TEKNIK INFORMATIKA Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v19i1.46816

Abstract

The high level of vulnerability in the Windows operating system requires implementing a hardening strategy that focuses not only on technical security but also on end-user convenience. This study, using a Design Science Research (DSR) methodology, aims to design and evaluate a Windows-based host security configuration by applying 35 parameters developed by integrating the Ferret-Windows open-source tool and the Microsoft Windows 11 Benchmark CIS standard. The research method includes a descriptive study to analyze the effectiveness of the tool and its parameter formulation, and a prescriptive study to formulate a combined configuration. The evaluation was carried out through functional testing and usability measurements using the System Usability Scale (SUS) instrument for 31 end-users (e.g., staff and students) in a public institution context, using the System Usability Scale (SUS) instrument on a standardized test laptop. The results showed that the configured system obtained an average SUS score of 73.63, which falls within the "good" category according to the standard interpretation scale, indicating that the resulting system is usable by most users. These findings indicate that the proposed hardening framework results in a system configuration that achieves acceptable usability without significant user sacrifice. While the study’s limitations include a focus on usability rather than quantitative pre-/post-security validation, it provides a practical contribution, a socio-technical hardening framework adaptable for public institutions.
Integration of YOLOv8 and ResNet-50 to Improve Road Damage Detection Performance Rendi Andrea Pramana; M. Arief Soeleman
JURNAL TEKNIK INFORMATIKA Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v19i1.46941

Abstract

Automatic road damage detection is an important solution for more effective and efficient transportation infrastructure maintenance. This study proposes the implementation of the You Only Look Once version 8 (YOLOv8) method with ResNet50 as a backbone to improve feature extraction capabilities in detecting various types of road damage. The model was trained using a road damage image dataset that has gone through preprocessing and data augmentation stages to enrich image variations. Test results show that the proposed model is able to achieve excellent performance, with an accuracy value of 95.2%, a precision of 0.979, a recall of 0.968, and an F1-score of 0.974. This achievement proves that the integration of YOLOv8 with ResNet50 as a backbone can improve the reliability of the road damage detection system compared to the original model. With this performance, this method has the potential to be applied in a real-time road monitoring system to support more optimal transportation infrastructure maintenance planning.
Automatic Detection of Foot Arch Using Clarke's Angle Calculation Through A Web-Integrated System for Children Shobiha Awwaliyah; Rivantona, Qalbi; Pahlevi, Alfaturachman Maulana; Nurcipto, Dedi; Kurniatie, Menik Dwi
JURNAL TEKNIK INFORMATIKA Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v19i1.47091

Abstract

Foot deformities, particularly flatfeet (pes planus), are frequently observed in children. Although many children exhibit some form of flatfeet, this condition can persist and cause biomechanical issues, pain, and postural misalignments. Early detection and monitoring of foot arch development are critical to preventing long-term complications. However, common diagnostic methods such as wet foot print tests, X-rays, and MRIs are costly, time-consuming, and involve radiation exposure. This study proposes an innovative web-based system that detects foot arch types in children using Clarke’s Angle. The system employs digital image processing to calculate the arch angle, offering a non-invasive, efficient, and cost-effective alternative to existing methods. The system was tested on 180 children aged 2-7 years at two locations in Semarang: Kindergarten & Daycare Habibie Ainun Tlogosari and Integrated Service Post Kemuning. The results from the Clarke’s Angle measurements from the web-based system were compared with the wet foot print test, showing minimal differences and achieving an accuracy rate of 98.89%. This system offers a reliable solution for early detection and is suitable for use in both clinical and community health settings. It provides a faster, more accessible approach to pediatric foot assessment, delivering real-time results and eliminating any waiting time.
A Real-Time IOT Monitoring and Safety Cutoff System for Electric Vehicle Batteries Using the BLYNK Platform jefri Lianda; Agustiawan; Adam; Custer, Johny; Rindilla Antika; Marzuarman
JURNAL TEKNIK INFORMATIKA Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v19i1.47098

Abstract

This paper presents the design and implementation of a 58-volt LiFePO₄ battery voltage management system for electric vehicles, featuring remote monitoring and control via the Blynk application. The system continuously monitors battery voltage levels and enables control through a Solid-State Relay (SSR) connected to a NodeMCU ESP8266 microcontroller. Through the Blynk interface, users can view real-time voltage readings along with the corresponding battery capacity percentage. The NodeMCU ESP8266 demonstrated reliable performance throughout all test phases, maintaining a stable internet connection. The average voltage measurement deviation displayed on the Blynk application was approximately 0.74%. The SSR is configured to disconnect the vehicle’s power supply when the battery voltage reaches around 46.3 volts or when the battery percentage decreases to 0.16%. This disconnection can be triggered manually through the Blynk application or automatically by the SSR. The disconnection process can be carried out through the Blynk application or automatically via the Solid State Relay (SSR). Remote disconnection via the Blynk application serves as an additional safety measure activated when suspicious conditions or activities are detected. This mechanism safeguards the battery from excessive discharge, promoting better performance and extending its service life by cutting off the load at critical limits.
A Computer Vision Approach for Bali Cattle Morphometric Measurement Using Multi-Threshold Segmentation and FIS–CF-Based Classification Arnaldy, Defiana; Kudang Boro Seminar; Muladno; Heru Sukoco; Shelvie Nidya Neyman
JURNAL TEKNIK INFORMATIKA Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v19i1.47324

Abstract

Manual morphometric measurement of livestock is time-consuming, stressful to animals, and poses safety risks to handlers. This study presents a computer vision-based system for automatically measuring three key morphometric parameters of Bali cattle—withers height (WH), body length (BL), and chest girth (CG)—in accordance with the Indonesian National Standard (SNI). Images were captured from side and rear perspectives and processed using threshold-based image segmentation in the HSV color space to isolate the cattle contour. Pixel-to-centimeter calibration was performed using a fixed reference marker placed at a known distance of 1.5–2.0 m from the camera. The extracted morphometric values were subsequently fed into a Fuzzy Inference System with Certainty Factor (FIS-CF) for cattle grading and classification. Threshold values ranging from 0.5 to 0.9 were evaluated against manual ground-truth measurements using MAE, RMSE, MAPE, and R². The optimal threshold of 0.9 achieved MAPE values of 9.85% (WH), 6.04% (BL), and 11.49% (CG), representing up to 52% improvement over the lowest threshold. Although R² values remain negative due to limited sample size and non-linear pixel-to-metric variance, a consistent upward trend toward zero confirms measurement improvement with higher thresholds. The proposed method offers a practical, non-invasive alternative to manual measurement, with potential application in precision livestock farming and automated cattle grading systems.
Ensemble Hybrid Recommender System (CBF, CF, KNN, NBC) With Multi-View TF-IDF for Robust Preliminary Medical Diagnosis Karaman, Jamilah; Triyanna Widiyaningtyas
JURNAL TEKNIK INFORMATIKA Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v19i1.48705

Abstract

Advances in health information technology require intelligent systems capable of supporting rapid and accurate diagnosis. This study proposes a Hybrid Recommender System (HRS) for preliminary medical diagnosis based on electronic medical records. The developed system combines K-Nearest Neighbor and Naïve Bayes Classifier with Multi-View TF-IDF feature representation. A total of 948 doctor-annotated medical records were used in the evaluation using a 10-Fold Cross-Validation scheme to improve the reliability of performance assessment. The results show that the hybrid model provides the best performance with an accuracy of 87.37% and an F1-score of 84.20%, consistently surpassing all comparison methods. These findings confirm that the integration of similarity-based and probabilistic learning can improve the quality of initial diagnosis recommendations in medical decision support systems. Further research will focus on expanding the dataset and clinical validation to ensure the reliability of the system in real-world practice.

Page 27 of 29 | Total Record : 282

 25   26   27   28   29 

Filter by Year

2016 2026


Reset
Filter By Issues
All Issue Vol. 19 No. 1: JURNAL TEKNIK INFORMATIKA Vol. 18 No. 2: JURNAL TEKNIK INFORMATIKA Vol 18, No 1: JURNAL TEKNIK INFORMATIKA Vol. 18 No. 1: JURNAL TEKNIK INFORMATIKA Vol 17, No 2: JURNAL TEKNIK INFORMATIKA Vol. 17 No. 2: JURNAL TEKNIK INFORMATIKA Vol 17, No 1: JURNAL TEKNIK INFORMATIKA Vol. 17 No. 1: JURNAL TEKNIK INFORMATIKA Vol. 16 No. 2 (2023): JURNAL TEKNIK INFORMATIKA Vol 16, No 2 (2023): JURNAL TEKNIK INFORMATIKA Vol 16, No 1 (2023): JURNAL TEKNIK INFORMATIKA Vol. 15 No. 2 (2022): JURNAL TEKNIK INFORMATIKA Vol 15, No 2 (2022): JURNAL TEKNIK INFORMATIKA Vol 15, No 1 (2022): JURNAL TEKNIK INFORMATIKA Vol 14, No 2 (2021): JURNAL TEKNIK INFORMATIKA Vol 14, No 1 (2021): JURNAL TEKNIK INFORMATIKA Vol 13, No 2 (2020): JURNAL TEKNIK INFORMATIKA Vol 13, No 1 (2020): JURNAL TEKNIK INFORMATIKA Vol 12, No 2 (2019): JURNAL TEKNIK INFORMATIKA Vol 12, No 1 (2019): JURNAL TEKNIK INFORMATIKA Vol. 12 No. 1 (2019): JURNAL TEKNIK INFORMATIKA Vol 11, No 2 (2018): Jurnal Teknik Informatika Vol 11, No 1 (2018): Jurnal Teknik Informatika Vol. 10 No. 2 (2017): Jurnal Teknik Informatika Vol 10, No 2 (2017): Jurnal Teknik Informatika Vol 10, No 1 (2017): Jurnal Teknik Informatika Vol 9, No 2 (2016): Jurnal Teknik Informatika Vol 9, No 1 (2016): Jurnal Teknik Informatika More Issue