cover
Contact Name
Teguh Wiyono
Contact Email
indexsasi@apji.org
Phone
+6285727710290
Journal Mail Official
indexsasi@apji.org
Editorial Address
Jl. Watunganten I No.1, Karangrawa, Batursari, Kec. Mranggen, Kabupaten Demak, Jawa Tengah 59567
Location
Kab. demak,
Jawa tengah
INDONESIA
Jurnal Teknik Informatika dan Teknologi Informasi
ISSN : 28279379     EISSN : 28279387     DOI : 10.55606
Core Subject : Science,
Jurnal Teknik Informatika dan Teknik Informasi (JUTITI) adalah jurnal ilmiah peer review yang diterbitkan oleh Politeknik Pratama. Jurnal Teknik Informatika dan Teknik Informasi (JUTITI) terbit dalam tiga edisi dalam setahun, yaitu edisi Februari, Juni dan Oktober. Kontributor Jurnal Teknik Informatika dan Teknik Informasi (JUTITI) berasal dari peneliti, akademisi (dosen dan mahasiswa) di bidang Teknik Informatika dan Teknik Informasi. Jurnal Teknik Informatika dan Teknik Informasi. memiliki fokus dan ruang lingkup yang terdiri dari: Computer Architecture Parallel and Distributed Computer Pervasive Computing Computer Network Embedded System Human—Computer Interaction Virtual/Augmented Reality Computer Security Software Engineering (Software: Lifecycle, Management, Engineering Process, Engineering Tools and Methods) Programming (Programming Methodology and Paradigm) Data Engineering (Data and Knowledge level Modeling, Information Management (DB) practices, Knowledge Based Management System, Knowledge Discovery in Data) Network Traffic Modeling
Articles 238 Documents
Sistem Deteksi Penggunaan Helm Pada Pengendara Sepeda Motor di Indonesia Menggunakan Perbandingan Model YOLOv8 dan RT-DETR Samuel Orief Rosario; Agustinus Aditya Bintara; Muhammad Rifki Zhaki; Rachmat Adi Purnama; Rame Santoso; Veti Apriana
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6314

Abstract

Road safety is an important aspect in reducing accident risks, especially for motorcycle riders. To improve compliance with helmet use, this study compares the performance of two deep learning–based object detection models, namely YOLOv8 and RT-DETR, using a Roboflow dataset consisting of 3,735 images with two classes: with helmet and without helmet. The research process includes data acquisition, preprocessing (512×512 pixels), model training conducted in Visual Studio Code using an Nvidia GTX 1070 Ti GPU with the Ultralytics framework (100 epochs, AdamW optimizer, 0.0005 learning rate, 25 patience), testing on images, videos, and real-time inputs using last.pt, as well as evaluation through precision, recall, mAP, and confusion matrix, followed by implementation of the best algorithm in a local Streamlit web application.The results show that RT-DETR achieved slightly better training performance in terms of mAP50–95, while YOLOv8 performed better during real-world testing with more stable accuracy, particularly for the with helmet class. YOLOv8 reached up to 100% accuracy in video and real-time testing, whereas RT-DETR performed better in the without helmet class, achieving 95% accuracy on image data and up to 100% in video testing. Overall, YOLOv8 was selected as the best model for implementation in the Streamlit-based helmet detection application because it is faster, more stable, and more accurate. This system has the potential to support intelligent ETLE enforcement to enhance traffic safety in Indonesia.
Perancangan dan Implementasi Sistem Informasi Nasabah pada BSI KCP Gunung Tua Studi Kasus Data Nasabah Laila Syarifah; Emmi Juwita Siregar; Afelia Anggraini; Rahmadhani Hasibuan; Riskha Armida Dewi
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6331

Abstract

The development of information technology has influenced the way various sectors work, including banking. Previously, customer data management was done manually, which often led to data duplication and time delays. This study aims to create and implement a more effective customer information system at Bank Syariah Indonesia (BSI) Gunung Tua Branch Office (KCP), so that the data management process becomes faster and more accurate. This study used the R&D method with the Waterfall model. The system was created using the PHP or Laravel programming language and relied on a MySQL database. The results showed that the system was successfully created and implemented. This system supports two main types of users: Admin/Customer Service who can log in, manage customer data (input, change, delete, and search), and print reports; and Customers who can view personal data, monitor savings status, and create new accounts. In conclusion, this system has an integrated database structure (Admin, Customer, Account, Transaction tables) and successfully meets user needs, thereby increasing efficiency and accuracy in customer data management at BSI Gunung Tua KCP.
Klasterisasi K-Means dan Model Markowitz dalam Pembentukan Portofolio Optimal Saham Syariah Muhammad Kildah Namariq
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6332

Abstract

This research seeks to construct an optimal portfolio of Sharia-compliant stocks listed in the Jakarta Islamic Index (JII) by integrating the Markowitz model with K-Means clustering. The dataset comprises the daily closing prices of JII constituent stocks and the risk-free return of BI-rate for the period of June–October 2025. The analysis begins with calculating the mean of stock returns and its corresponding standard deviation to identify the characteristics of each stock. The Silhouette Index is employed to determine the most suitable number of clusters, which indicates that three clusters provide the best separation. A representative stock is then selected from each cluster based on the Sharpe Ratio, resulting in BRPT, ASII, and UNVR as the primary candidates for portfolio construction. The Markowitz model is subsequently applied to determine the optimal portfolio weights, yielding an allocation of 16.29% for BRPT, 70.80% for ASII, and 12.91% for UNVR. The performance evaluation shows that the optimal portfolio achieves a Sharpe Ratio of 0.232872, higher than the JII index value of 0.118273, indicating superior risk–return efficiency. These findings demonstrate that a hybrid approach combining K-Means clustering and Markowitz optimization can enhance investment decision-making for Sharia-compliant stocks.
Klasifikasi Indikator Kesehatan Diabetes Menggunakan Algoritma Random Forest Haura Syahla; Haris Izzudin; Fariz Aditya Pratama; Beni Rahmatullah; Ahmad Jurnaidi Wahidin; Ika Kurniawati
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6338

Abstract

Diabetes continues to rise as a global health concern, highlighting the need for analytical methods that can assist in earlier and more accurate detection. This study aims to classify diabetes conditions using the Random Forest algorithm implemented through the Orange Data Mining platform. The dataset used contains various health-related attributes such as glucose levels, blood pressure, body mass index, age, and other clinical indicators associated with diabetes risk. Random Forest was selected due to its ability to produce stable models, handle large and complex datasets, and minimize overfitting by combining multiple decision trees. The research process includes data preprocessing, splitting the dataset into training and testing portions, building the Random Forest model, and evaluating its performance using metrics such as accuracy, precision, recall, F1-score, and confusion matrix. The results indicate that Random Forest delivers strong and consistent performance in classifying diabetes conditions based on the given health indicators. These findings suggest that employing data mining techniques especially Random Forest within Orange—can serve as a practical and reliable approach to support medical analysis and assist healthcare practitioners in achieving earlier and more accurate diabetes detection.                                                          
Sistem Pendukung Keputusan Berbasis Web untuk Penerimaan Bantuan Langsung Tunai Menggunakan Metode Multi Attribute Utility Theory (MAUT) di Desa Selemak Irham Nabiza Trisna; Asbon Hendra Azhar
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6359

Abstract

This study aims to develop a web-based decision support system to assist the selection process for Direct Cash Assistance (BLT) recipients in Selemak Village. The current manual selection process often leads to unfairness and subjectivity. This system was developed using the Multi-Attribute Utility Theory (MAUT) method, which is capable of providing selection results based on predetermined criteria and weighting. The research stages include collecting data on potential recipients, determining criteria, weighting, and implementing the system using PHP and MySQL. The system was evaluated using the K-Nearest Neighbor (KNN) algorithm to measure the accuracy of the calculation results. The results showed that the system was able to provide recipient recommendations with an accuracy of 96%, with 68 eligible families and 107 ineligible families. With this system, the process of determining BLT recipients is faster, more objective, and more transparent.
Klasifikasi Wajah untuk Rekomendasi Gaya Rambut Menggunakan SVM dan Random Forest Mochamad Rizky Ainur Ridho; Mahatma Mahesa; Bagus Adi Wibowo; Rachmat Adi Purnama; Veti Apriana; Rame Santoso
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6360

Abstract

The goal this project is to create a face-shape classification and hairstyle recommendation system by combining Support Vector Machine (SVM) and Random Forest (RF) algorithms with Histogram of Oriented Gradients (HOG) feature extraction. This study is motivated by the growing demand for individualized appearance support, as many users find it difficult to find haircuts that complement their face features. The method first preprocesses facial photos, uses HOG to extract key geometric and texture-based features, and then uses SVM and RF models to categorize the images. For training, validation, and testing, a dataset of five different face shapes is utilized. According to experimental results, the Random Forest model has an accuracy of about 89%, while the SVM model achieves an accuracy of about 95%. These findings suggest that SVM is better suited for managing high-dimensional feature spaces generated by HOG extraction. A recommendation system that offers hairstyle recommendations based on the anticipated face shape is then integrated with the trained model. The system is useful for real-time use since it can process pictures taken with the camera or uploaded from the gallery. Overall, this study shows that integrating HOG with SVM offers a dependable basis for creating customized hairdo recommendations as well as an efficient method for face-shape classification.  
Penerapan Algoritma Association Rule Mining (Apriori) untuk Analisis Pola Pembelian (Market Basket Analysis) pada Data Transaksi Ritel Jadiaman Parhusip; Tyara Rahmidasari; Erina Ekanova Safitri; Tety Citra Natha; Nur Haniatin Jannah
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6362

Abstract

Market Basket Analysis (MBA) is a data mining technique used to identify product combination patterns that frequently occur together within a single transaction. This study applies the Apriori Algorithm as the primary method for discovering Association Rules from a large-scale e-commerce retail transaction dataset consisting of approximately 500,000 records, focusing on consumer purchasing behavior in the United Kingdom market. The research follows a systematic data mining process that includes data integration, data cleaning to remove anomalies such as negative prices and quantities, and data transformation using One-Hot Encoding to convert transaction records into a suitable binary matrix format. The Apriori Algorithm is then used to generate frequent itemsets, which are evaluated using Support, Confidence, and Lift to determine their strength and significance. The results show several strong Association Rules with Lift values greater than 1.0, indicating positive correlations between specific product pairs. These findings offer useful insights into consumer purchasing tendencies and can support various retail strategies, such as improving product recommendation systems, optimizing store layout, enhancing promotional bundles, and strengthening targeted marketing efforts. Overall, this study demonstrates that Apriori-based MBA is capable of extracting actionable knowledge from large-scale retail datasets and contributes to more effective, data-driven decision-making in the retail sector.
Pengaplikasian Algoritma C4.5 untuk Menganalisis Hubungan Kebiasaan Harian Siswa terhadap Prestasi Akademik Muhammad Zikri Ansyari; Muhammad Yasin
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6364

Abstract

This study aims to analyze the relationship between students’ daily habits and their academic performance using the C4.5 algorithm. The daily habit variables examined include study duration and intensity, sleep quality and patterns, frequency and type of gadget use, attendance consistency, and students’ engagement in learning activities both inside and outside the classroom. The data were collected through questionnaires and combined with students’ academic grades as indicators of performance. The C4.5 algorithm was employed to construct a decision tree model capable of identifying the daily habit attributes that have the most significant influence on academic achievement. The findings reveal that study intensity, sleep quality, and attendance consistency serve as dominant factors in predicting students’ performance levels. Furthermore, the resulting decision tree model demonstrates a relatively high accuracy level, making it a useful tool for evaluation, student development planning, and decision-making processes by educators. These results confirm that the application of the C4.5 algorithm is effective in uncovering the relationship patterns between daily habits and academic achievement and has the potential to serve as a reference for efforts to improve students’ learning quality.
Klasifikasi Resiko Depresi Berdasarkan Durasi Layar dan Pola Hidup Digital Mengguanakan Metode K-Nearest Neighbor (KNN) Heri Setiawan; Helmi Fauzi Siregar
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6366

Abstract

This study aims to classify depression risk levels based on screen time and digital lifestyle patterns using the K-Nearest Neighbor (KNN) method. The dataset used includes several important variables, such as daily screen time, frequency of social media use, and sleep duration and quality. These variables were chosen because they are considered to have a strong association with mental health, particularly depressive symptoms that often arise from excessive digital device use. A KNN model was then developed and tested to categorize individuals into three depression risk categories: low, medium, and high. The evaluation results showed that the model with a k value of 5 achieved a predictive accuracy of 85%, indicating that this method is quite effective as a data-driven classification tool. The findings of this study suggest that digital lifestyle patterns can be an early indicator in predicting depression risk, thus requiring more systematic monitoring. However, this model still needs to be combined with clinical assessment for a more comprehensive and accurate diagnosis.  
Sistem Informasi Penerbitan Surat Izin Berlayar Menggunakan Metode First In First Out (FIFO) di Kantor Kesyahbandaran dan Otoritas Pelabuhan Utama Belawan Muhammad Reynaldi; Ria Eka Sari
Jurnal Teknik Informatika dan Teknologi Informasi Vol. 5 No. 3 (2025): Desember: Jurnal Teknik Informatika dan Teknologi Informasi
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jutiti.v5i3.6367

Abstract

The issuance of sailing permits at the Belawan Harbormaster and Main Port Authority Office (KSOP) still faces various obstacles, particularly related to the accumulation of application files, irregular queues, and long document processing times. These problems impact service efficiency and user satisfaction. This study aims to design and implement a web-based information system that applies the First In First Out (FIFO) method to improve the effectiveness of the sailing permit issuance process. The study uses a Waterfall approach, which includes the stages of needs analysis, system design, implementation, and functional testing using Blackbox Testing. The results show that the application of the FIFO method to the web-based system is able to organize the service flow more fairly based on the chronological order of submissions, thereby reducing the risk of service discrimination and minimizing input errors that previously often occurred in manual processes. The system is also able to accelerate the process of verification, data validation, and printing of permits, resulting in more efficient service times. In addition, transparency of the service process is increased through real-time monitoring of application status. Overall, the information system developed has been proven to improve service quality and public trust in the performance of KSOP Belawan