cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Serpian
Contact Email
serpian@poliupg.ac.id
Phone
+6285241204400
Journal Mail Official
intek@poliupg.ac.id
Editorial Address
Politeknik Negeri Ujung Pandang Kampus 1 Gedung Administrasi Lantai II Jalan Perintis Kemerdekaan KM.10 Tamalanrea Makassar 90245
Location
Kota makassar,
Sulawesi selatan
INDONESIA
INTEK: Jurnal Penelitian
Published by Politeknik Negeri Ujung Pandang
ISSN : 23390700     EISSN : 26155427     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Engineering
INTEK is a journal managed by the Journal and Publication Development Unit of Ujung Pandang State Polytechnic, which is published twice a year, in April and October. The journal INTEK has also been indexed. The INTEK Journal accepts research scripts in the fields of technology and engineering such as: Electrical, Mechanical, Civil and Chemical Engineering.
Arjuna Subject : Umum - Umum
Articles 6 Documents
 1 
Search results for , issue "Vol 12 No 1 (2025): April 2025" : 6 Documents clear
Intelligent Fault Prediction in Diesel Engines: A Comparative Study of SVM and BPNN for Condition-Based Maintenance Nurdin, Fadli; Effendi, Mohammad Khoirul
INTEK: Jurnal Penelitian Vol 12 No 1 (2025): April 2025
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/intek.v12i1.5362

Abstract

This study discusses the application of Support Vector Machine (SVM) and Back Propagation Neural Network (BPNN) in predicting diesel engine health based on operational data relabeled using K-Means Clustering. Two types of SVM kernels were tested, namely Radial Basis Function (RBF) and Sigmoid, with various parameter combinations. The results indicate that SVM with Sigmoid kernel achieved an accuracy of 94.06%, but was less sensitive in detecting unhealthy engine conditions. In comparison, the BPNN method with a three-hidden-layer configuration (1-2-1 neurons) and tansig activation function showed superior performance with 97.13% accuracy, MSE of 0.03, recall of 94%, precision of 100%, and F1-score of 97%. These findings prove that BPNN outperforms SVM in capturing complex data patterns and is more accurate in detecting unhealthy engine conditions. Additionally, relabeling the dataset significantly improved predictive accuracy from 72.3% to 97.13%, highlighting the importance of balanced data in modeling. Overall, this study demonstrates that optimally configured BPNN is more effective in predicting diesel engine health than SVM, making it a more reliable approach for engine condition monitoring.  
Pemodelan Denial of Service: Pengukuran Waktu dan Penggunaan CPU pada Serangan GraphQL Ginting, Debora Natalia; Widjajarto, A.; Hediyanto , Umar Yunan Kurnia Septo
INTEK: Jurnal Penelitian Vol 12 No 1 (2025): April 2025
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/intek.v12i1.4943

Abstract

GraphQL is a query language that allows clients to request specific data from an API, making it more efficient and flexible compared to traditional REST APIs. This makes applications faster and more efficient by reducing data over-fetching, combining various data sources into a single request, and supporting schema changes without disrupting the integrity of existing applications. This study focuses on security testing and exploiting Denial of Service (DoS) vulnerabilities within GraphQL APIs. As a query language that is growing in popularity, GraphQL offers flexibility in data retrieval but is also vulnerable to DoS attacks. The research centers on DoS attacks using various exploitation techniques such as Circular Queries, Field Duplication, Alias Overloading, and Object Limit Overriding. Testing was conducted using the Kali Linux operating system and testing applications such as Altair and DVGA, employing the Threat Modeling Attack Tree method. The results of the testing show that the Field Duplication attack is the most effective, with the fastest execution time and relatively high CPU usage (2.5 seconds/88.5% reduced to 1.86 seconds/75.50%), while the lowest risk was found in Alias Overloading (1412.05 seconds/99% reduced to 691.29 seconds/93%). Although Alias Overloading posed the lowest risk, it still resulted in high CPU usage, burdening the server significantly. This study provides an understanding of the importance of testing and strengthening API security to prevent DoS attacks. Keywords— API GraphQL, Attack Tree, Denial of Service, exploitation, Cpu, Time
Investigating the Effect of PV Panel Mounting Orientation under Partial Shading Conditions (A Simulation-Based Study) Usman, Usman; Achmad , Alamsyah; Sofyan , Sofyan; Sirad, Mochammad Apriyadi Hadi; Hidayatullah, Syarif; Isman, Muh
INTEK: Jurnal Penelitian Vol 12 No 1 (2025): April 2025
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/intek.v12i1.5174

Abstract

This study aims to investigate the effect of shading on the mounting orientation of PV panel and the availability or unavailability of Bypass Diodes on the performance of PV panel under partially shading conditions. In this study, for each PV panel mounting orientation, the number of PV cells that received shading was grouped into three categories: 9 cells, 18 cells and 27 cells respectively with the shading fixed vertically. The study also considers the availability and unavailability of bypass diodes. The simulation results show that with vertical shading partially covering the PV cells, the landscape mounting orientation is the best orientation for PV panels with bypass diodes to avoid the partial shading effect
Algoritma Reversible Data Hiding dalam Mengamankan Karya Seni Gambar Digital Sadewa, I Made Aditya Putra; Wahyudi, Bambang Ari; Palupi, Irma
INTEK: Jurnal Penelitian Vol 12 No 1 (2025): April 2025
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/intek.v12i1.5193

Abstract

In today's digital era, protecting digital artworks, particularly images, has become increasingly important to prevent copyright infringement and forgery. This paper proposes a novel method for embedding secret data into images using Reversible Data Hiding (RDH) techniques that leverage histogram shifting and random sub-blocks. The method is designed to maintain the visual integrity of the image while allowing the insertion of critical information, such as copyright metadata. The dataset used consists of 13 digital artworks sized 1280x720 pixels in PNG format, reflecting a diversity of textures and colors. Experimental results demonstrate that the proposed method achieves a high embedding capacity with PSNR values exceeding 37 dB, indicating excellent image quality post data insertion. Additionally, the method exhibits resilience against illegal modifications, with the ability to detect changes in images that have had data embedded. By integrating a PIN-based authentication system, the method enhances the security and integrity of the embedded information. This research significantly contributes to the field of digital artwork protection, offering an effective solution to preserve the authenticity and aesthetic value of images while enabling secure and reversible data insertion. The findings underscore the potential of RDH techniques in safeguarding sensitive information across various applications, ensuring that digital artworks can be both protected and enjoyed without compromising their quality.
Perbandingan Analisis Sentimen pada Ulasan Aplikasi Sirekap Menggunakan Support Vector Machines dan Naive Bayes Khalid, khalid; Wijaya, Rifki; Bijaksana, Moch Arif
INTEK: Jurnal Penelitian Vol 12 No 1 (2025): April 2025
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/intek.v12i1.5196

Abstract

This research analyzes the sentiment reviews of the SIREKAP application on the Google Play Store using two machine learning algorithms, namely Naïve Bayes and Support Vector Machine (SVM). The dataset used consists of 19,925 reviews that have gone through preprocessing stages, including text cleaning, stopword removal, stemming, and tokenization. To overcome data imbalance, oversampling and undersampling techniques were applied. Furthermore, TF-IDF is used for feature extraction, converting text into numerical representation. The dataset is divided into 80% training data (15,940 data) and 20% test data (3,985 data). The results show that oversampling provides better performance than undersampling. In the oversampling method, the SVM algorithm achieved the highest accuracy of 95%, with consistent precision, recall, and F1-score values across all sentiment classes. The Naïve Bayes algorithm also performed quite well, with an accuracy of 77% on the oversampled data. In contrast, in the undersampling method, both algorithms have the same accuracy of 61%. This study confirms that the combination of oversampling technique and SVM algorithm is the best approach to handle imbalanced data and provides important insights into user perception of the SIREKAP application.
Investigasi Sifat Mekanik terhadap Perbedaan Media Pendingin pada Proses Induction Hardening Baja AISI 1015 Azmy, Ilham; Adhitya Muhamadika , Chandra
INTEK: Jurnal Penelitian Vol 12 No 1 (2025): April 2025
Publisher : Politeknik Negeri Ujung Pandang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31963/intek.v12i1.5322

Abstract

AISI 1015 steels have been vigorously used to numerous automotive parts. Unfortunately, it has several mechanical shortcomings due to poor hardness, wear resistance, and strength. To tackle its crucial problem, the AISI 1015 steels have been treated by induction hardening treatment at 850 oC which subsequently cooling to the ambient temperature using different cooling media of water, salt bath, and oil. The as-prepared AISI 1015 steels were then investigated its mechanical properties involving spectrometry, microstructure observation, hardness, wear, and tensile test. The AISI 1015 treated steels after induction hardening in water cooling media exhibited intriguing microstructure of vast pearlite encircle ferrite matrix. The sample also garnered significant enhancements of hardness, wear resistance, and tensile properties. These superior mechanical characteristics are believed to be catered for the induction treatment using water cooling media which boost crystalline structure transformation deliberately. Therefore, this research affords significant promise for improved mechanical properties of the AISI 1015 steels.

Page 1 of 1 | Total Record : 6

 1 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 12 No 1 (2025): April 2025 Vol 11 No 2 (2024): October 2024 Vol 11 No 1 (2024): April 2024 Vol 10 No 2 (2023): October 2023 Vol 10 No 1 (2023): April 2023 Vol 9 No 2 (2022): October 2022 Vol 9 No 1 (2022): April 2022 Vol 8 No 2 (2021): October 2021 Vol 8 No 1 (2021): April 2021 Vol 7 No 2 (2020): October 2020 Vol 7 No 1 (2020): In Press Vol 6 No 2 (2019): October 2019 Vol 6 No 1 (2019): April 2019 Vol 5 No 2 (2018): Oktober 2018 Vol 5 No 1 (2018): April 2018 Vol 4 No 2 (2017): Oktober 2017 Vol 4 No 1 (2017): April 2017 Vol 3 No 2 (2016): Oktober 2016 Vol 3 No 1 (2016): April 2016 More Issue