cover
Contact Name
Laurentius Kuncoro Probo Saputra
Contact Email
jutei@fti.ukdw.ac.id
Phone
-
Journal Mail Official
jutei@fti.ukdw.ac.id
Editorial Address
Jurnal Terapan Teknologi Informasi (JUTEI) Fakultas Teknologi Informasi, Universitas Kristen Duta Wacana, Yogyakarta Email: jutei@fti.ukdw.ac.id
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
JUTEI (Jurnal Terapan Teknologi Informasi)
ISSN : 25793675     EISSN : 25795538     DOI : https://doi.org/10.21460/jutei
Core Subject : Science,
Jurnal Terapan Teknologi Informasi (JUTEI) is a journal focusing on theory, practice, and methodology of all aspects in Information Technology and Computer Science, as well as productive and innovative ideas related to new technology and applied sciences. This journal is managed by the Faculty of Information Technology, Duta Wacana Christian University. The subject of articles may cover, but is not limited to: -Artificial Intelligence -Business Intelligence -Cloud & Grid Computing -Computer Networking & Security -Computer Vision -Datawarehouse & Datamining -Decision Support System -Digital Signal Processing -E-System -Enterprise Architecture -Enterprise System (SCM, ERP, CRM) -Human Computer & Interaction -Image Processing -Information Retrieval -Information System -Information Systems Audit -Internet of Things -Knowledge Management -Mobile Computing & Application -Multimedia System -Open Source System & Technology -Semantic Web -Software Engineering -User Interface/ User Experience (UI/UX)
Articles 118 Documents
Pengenalan Gerakan Olahraga (Push Up dan Sit Up) menggunakan Mediapipe Andrew Hendisutio; Azis Dzaffin Alfarabi; Wahidin Wahab; Meirista Wulandari
Jurnal Terapan Teknologi Informasi Vol 10 No 1 (2026): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2026.101.477

Abstract

Motion in sports workouts plays a crucial role in evaluation and learning. This design aims to develop a sports workout movement recognition device based on image processing with high accuracy. The design methodology involves acquiring image data of workout movements and training a recognition model using Mediapipe, which is a deep learning-based object detection algorithm. Image data of workout movements is obtained from push-up and sit-up exercises performed in front of the Sports Movement Acquisition module. The training process of the Mediapipe model utilizes this input data to recognize movements such as push-ups and sit-ups. Initial experimental results indicate that the system can recognize workout movements with satisfactory accuracy. Furthermore, this research includes testing the system with varying distances to determine its accuracy at different ranges. In further experiments, the system can be refined or improved to achieve higher accuracy. This research contributes significantly to the development of sports workout movement recognition technology using the Mediapipe algorithm, focusing on the classification of push-up and sit-up movements. The system can be used in training, evaluation, and assessment of specific workout movements, namely push-ups and sit-ups. The integration of image processing and deep learning in this field holds potential for further development in movement analysis and training for both athletes and beginners. By combining modern technology and sports science, this research opens new opportunities for understanding and enhancing workout movements, particularly in push-up and sit-up exercises, potentially providing significant benefits in athlete training and the development of workout sports.
Perbandingan Kinerja Random Forest dan Gradient Boosting pada Strategi Trading Saham Sektor Energi Berkapitalisasi Besar di Indonesia Gregorius Daniel Jodan Perminas; Michael Chandra
Jurnal Terapan Teknologi Informasi Vol 10 No 2 (2026): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2026.102.483

Abstract

This study compares the performance of Random Forest and Gradient Boosting in developing machine learning-based trading strategies for large-cap energy sector stocks in Indonesia. The analyzed stocks consist of BYAN, DSSA, CUAN, BUMI, ADRO, ADMR, AADI, TCPI, PTRO, and PGAS, selected from the IDNFinancials energy sector list in May 2026. Daily historical data were obtained from Yahoo Finance for the period from 2020 to April 2026. Technical indicators were constructed from momentum, volatility, and trend groups, while feature selection was performed exclusively on the training data using Spearman rank correlation. The final features selected for all stocks were RSI_14, BB_LOWER, and EMA_20. The data were divided chronologically into training, evaluation, and backtesting periods with an approximate 70:20:10 proportion and a five-trading-day purging gap between consecutive periods. Hyperparameter tuning was conducted using five-fold TimeSeriesSplit with a five-observation gap. Random Forest and Gradient Boosting showed relatively similar classification performance, with mean accuracies of approximately 0.528 and 0.531, respectively, indicating that neither model consistently dominated across all stocks. The best financial performance was obtained by Gradient Boosting on TCPI, producing a return of 61.578%, a win rate of 72.727%, and 11 trades, although the result remained below the Buy and Hold return of 103.540%. Sensitivity analysis further showed that classification performance and trading performance did not necessarily move in the same direction. These findings indicate that classification accuracy alone is insufficient for evaluating machine learning-based trading strategies and should be complemented by financial performance and robustness analysis.
Evaluasi Karakteristik Meter Table OpenFlow 1.3 pada Jaringan SDN Berbasis MikroTik RB750GR3 Azlina Isnaeni Nurul'Ain; Rohmat Gunawan; Frimansyah Maulana Sugiartana Nursuwars
Jurnal Terapan Teknologi Informasi Vol 10 No 2 (2026): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2026.102.496

Abstract

The meter table is an OpenFlow 1.3 Quality of Service (QoS) mechanism designed to limit traffic rates for individual flows. However, the implementation characteristics of this feature on MikroTik RouterOS (based on OpenFlow 1.3) have not been extensively evaluated. This study analyzes the characteristics of the OpenFlow 1.3 meter table on an SDN setup using MikroTik RB750Gr3 devices and the Ryu Controller. The implementation involved a single controller, three MikroTik devices, and two hosts, utilizing TCP and UDP traffic with rates of 5 and 10 Mbps, burst sizes of 0, 250, and 500 Mbps, and packet transmission tests ranging from 2 to 20 Mbps over a 60-second duration. Evaluation metrics included the onset of packet dropping, throughput, and packet loss. The results indicate an effective throughput of 50% of the configured rate; furthermore, increasing the burst size delayed the onset of dropping and improved average throughput while burst capacity remained available, though it did not alter the effective throughput once the burst was exhausted. These findings reveal discrepancies between the meter table implementation on the MikroTik RB750Gr3 and the specifications defined in the OpenFlow 1.3 standard. Future research could evaluate meter table performance across different RouterOS versions and devices from other vendors.
Sebuah PENINGKATAN KEAMANAN PROTOKOL MESSAGE QUEUING TELEMETRY TRANSPORT MENGGUNAKAN TRANSPORT LAYER SECURITY DAN HASH-BASED MESSAGE AUTHENTICATION CODE Huda Daulan; Firmansyah Maulana; Rohmat Gunawan
Jurnal Terapan Teknologi Informasi Vol 10 No 2 (2026): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2026.102.526

Abstract

Message Queuing Telemetry Transport (MQTT) is a lightweight communication protocol widely used in Internet of Things (IoT) systems due to its efficiency and low resource consumption. However, MQTT does not provide built-in security mechanisms, making it vulnerable to attacks such as Man-in-the-Middle (MITM). This study aims to analyze the impact of implementing Transport Layer Security (TLS) and Hash-Based Message Authentication Code (HMAC-SHA256) on the security and performance of the MQTT protocol. An experimental method was employed by comparing four communication scenarios: MQTT without security, MQTT with TLS, MQTT with HMAC-SHA256, and MQTT with the combination of TLS and HMAC-SHA256. The system was implemented using an ESP32, a DHT22 sensor, and a Mosquitto broker. Security was evaluated through MITM attack scenarios, while performance was assessed using Quality of Service (QoS) parameters, including latency, throughput, jitter, packet loss, memory usage, and CPU utilization. The results indicate that TLS ensures communication confidentiality, while HMAC-SHA256 provides data integrity and message authentication. The combination of TLS and HMAC-SHA256 offers the highest level of security, although it introduces performance overhead. These findings demonstrate that the selection of security mechanisms should consider the trade-off between communication security and system performance in IoT applications. Keywords: Internet of Things, MQTT, TLS, HMAC-SHA256, security, Quality of Service.
Perbandingan YOLOv11m dan YOLOv12m pada Deteksi Plat Nomor Indonesia dan Pengaruhnya terhadap EasyOCR Arief Setiawan; Ernawati; Funny Farady Coastera
Jurnal Terapan Teknologi Informasi Vol 10 No 2 (2026): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2026.102.530

Abstract

Automatic License Plate Recognition (ALPR) is widely used in Intelligent Transportation Systems (ITS). This study compares the You Only Look Once (YOLO) models YOLOv11m and YOLOv12m for Indonesian vehicle license plate detection and examines how the detection results affect character recognition with EasyOCR as the Optical Character Recognition (OCR) engine. The dataset contains 2,819 vehicle images, consisting of 2,243 training images, 353 validation images, and 223 test images, obtained from Roboflow. Both models were trained for 50 epochs on an NVIDIA Tesla T4 graphics processing unit (GPU) using the same configuration. On the validation set, both models produced nearly identical mean Average Precision (mAP@0.5)values, namely 0.9782 for YOLOv11m and 0.9783 for YOLOv12m. YOLOv11m achieved higher recall (0.9554), a slightly higher test F1-Score (0.9540), and lower validation inference time (24.58 ms). YOLOv12m achieved higher precision (0.9483) and mAP@0.5:0.95 (0.6748). In the OCR evaluation, YOLOv11m detected all 31 test plates and obtained a fuzzy matching score of 0.6632 with a Character Error Rate (CER) of 0.3368. YOLOv12m detected 29 of 31 plates, with a fuzzy score of 0.6139 and CER of 0.3861. The preprocessing sequence used in this study reduced OCR performance for both models compared with the original red, green, and blue (RGB) crops. Based on these results, YOLOv11m provided the better overall balance between detection recall, OCR performance, and inference time in the tested configuration.
Sistem IoT Modular Berbasis ESP32: Media Pembelajaran Transisi Pemrograman Arduino yang Fleksibel dan Berbiaya Efisien Danny Sebastian; Aga Susanto; Yuan Lukito
Jurnal Terapan Teknologi Informasi Vol 10 No 2 (2026): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2026.102.533

Abstract

Arduino programming instruction for elementary and junior HIGH school students is often hindered by HIGH cognitive load resulting from the simultaneous need to assemble hardware, grasp computational logic, and memorize syntax. Existing commercial solutions are generally expensive and offer limited flexibility. This study aimed to develop an ESP32-based Internet of Things (IoT) system using a modular approach to serve as a transitional learning tool from block-based to text-based programming. The system was designed to alleviate cognitive load through plug-and-play physical Sockets and baseline software that simplifies text syntax into intuitive functions. Evaluation was conducted in three main stages using a data triangulation approach. Technical testing (black-box testing) showed the system achieving a 100% Pass rate across 31 functional scenarios. Effectiveness testing, utilizing a between-subjects comparative design (n=9), revealed that the modular group outperformed the comparison group (Tinybit) in both Input-Process-Output (IPO) comprehension scores (3.20 vs. 2.50) and usability satisfaction (88.8% vs. 74.0%). The modular design also successfully prompted independent exploration initiatives in 100% of the participants. In flexibility testing, all seven test subjects successfully transferred their computational understanding to independently program new sensor modules with a perfect success rate. It is concluded that the developed modular IoT system is reliable, effective at reducing initial learning barriers, and HIGHly flexible as a cost-efficient tool for transitioning to Arduino programming.
An Auditable Hybrid Cascade for Network Threat Detection Frowin Kifaru; Daniel Mwakiposa; Shadrack Stephen Madila
Jurnal Terapan Teknologi Informasi Vol 10 No 2 (2026): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2026.102.534

Abstract

Machine-learning intrusion detectors can provide limited decision transparency in shared-server environments, where analysts must distinguish routine service activity from suspicious flows. This study proposes DIRAF (Direction-Aware Rule-Augmented Forest), a two-stage cascade comprising a conservative, interpretable rule gate and a Random Forest (RF) classifier for unresolved flows. The framework is supported by Quadruple-View Flow Engineering (QVFE), which organizes behavioral predictors into temporal, flow-morphology, port-semantics, and TCP-flag views, and by the Triangulated Attribution Protocol (TAP), which reconciles inferential, permutation-based, and SHAP feature rankings. Evaluation used the CIDDS-001 External Server Week 1 benchmark (172.838 flows); the primary binary task included 156.950 flows labeled normal or suspicious, while 15.888 unknown flows were excluded. On the held-out binary test set, DIRAF achieved 100% accuracy, precision, recall, F1-score, and AUC under the evaluated configuration. Its rule gate resolved 42,3% of test traffic, covering 61,9% of suspiciously labeled flows with 100% precision; the remaining flows were classified by the RF. The cascade reduced mean batch decision latency from 8,01 to 4,77 µs per record. These results are specific to this benchmark: direction laundering reduced Model B accuracy to 68,8%, and the direction-label association limits external validity. DIRAF therefore demonstrates an auditable cascade design on CIDDS-001 Week 1, not universal or production-level detection performance.
Implementasi CNN untuk Keamanan Penginapan Wisata melalui Pengenalan Wajah Berbasis CCTV NAWA DARUCANDRA; SON ALI AKBAR; KARTIKA FIRDAUSY
Jurnal Terapan Teknologi Informasi Vol 10 No 2 (2026): Jurnal Terapan Teknologi Informasi
Publisher : Fakultas Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21460/jutei.2026.102.536

Abstract

Security is an important aspect of tourist accommodation management, particularly for monitoring individuals within the accommodation environment. Closed-Circuit Television (CCTV) can support surveillance activities; however, manual identification remains limited in terms of efficiency and consistency. The application of deep learning, particularly Convolutional Neural Network (CNN) architectures, provides an approach for developing automated face recognition systems. This study aims to analyze and compare the performance of MobileNetV2 and VGG16 architectures for face recognition using images obtained from CCTV recordings in a tourist accommodation environment. The dataset consisted of 1,741 images classified into 10 identity classes, including two staff classes, seven guest classes, and one unknown individual class evaluated under a closed-set scheme. The research process consisted of face detection using Haar Cascade, preprocessing, data augmentation, chronological dataset splitting (sequential temporal split) into training, validation, and testing sets, followed by model training using a transfer learning approach. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrix over repeated experimental runs. The experimental results showed that MobileNetV2 achieved a mean accuracy of 84.00% ± 1.20%, precision of 84.50% ± 1.15%, recall of 84.00% ± 1.20%, and F1-score of 84.10% ± 1.10%. Meanwhile, VGG16 achieved a mean accuracy of 78.00% ± 1.80%, precision of 85.00% ± 1.40%, recall of 78.00% ± 1.80%, and F1-score of 78.10% ± 1.75%. These results indicate that MobileNetV2 provided better identification performance and consistency than VGG16 on the CCTV dataset, particularly in terms of accuracy, recall, and computational efficiency. Therefore, MobileNetV2 was more suitable for the face recognition scenario evaluated in this study.

Page 12 of 12 | Total Record : 118