cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Puji Winar Cahyo
Contact Email
teknomatika.unjaya@gmail.com
Phone
+628562636509
Journal Mail Official
teknomatika.unjaya@gmail.com
Editorial Address
Jl. Siliwangi, Ring Road Barat, Banyuraden, Gamping, Yogyakarta
Location
Kab. sleman,
Daerah istimewa yogyakarta
INDONESIA
Teknomatika: Jurnal Informatika dan Komputer
Published by Universitas Jenderal Achmad Yani Yogyakarta
ISSN : 19797656     EISSN : 30310865     DOI : 10.30989
Core Subject : Science,
Computer Science & IT
Teknomatika: Jurnal Informatika dan Komputer ISSN: 3031-0865 (Online), 1979-7656 (Print) is a free and open-access journal published by Fakultas Teknik dan Teknologi Informasi Universitas Jenderal Achmad Yani Yogyakarta, Indonesia. Teknomatika publishes scientific articles from scholars and experts worldwide related to the computer science, informatics, computer systems and information systems. This journal accommodates articles covering: Mathematics and Statistics Algorithms and Programming Intelligent System Artificial Intelligence Software Engineering Computer Architecture Distributed System Cyber Security Electronics and Embedded Systems Data and Information Management Information Systems Enterprise System All published articles will have a Digital Object Identifier (DOI). The Journal publication frequency is twice a year (sixth monthly: Maret and September).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 271 Documents
 24   25   26   27   28 
Kajian Keamanan Sistem Informasi Akademik Menggunakan Framework COBIT 5 Supit, Yonal; Edy Irwansyah
Jurnal Teknomatika Vol 17 No 1 (2024): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v17i1.1330

Abstract

This study examines the security of academic information systems using the COBIT 5 Framework. Key issues are uncertainty in protecting student and staff data, the potential for cyberattack vulnerabilities, and non-compliance with international security standards. The goal is to evaluate the security level of the system and suggest improvement recommendations according to COBIT 5 principles. Research methods include Renstar IT policy analysis, system audits, and interviews with IT personnel and related academic communities. Data is analyzed quantitatively to identify weaknesses and opportunities for improvement. The COBIT 5 framework is used as a security assessment framework. The results highlight the need for improvement, including access management, activity monitoring, and continuous improvement plans. Using COBIT 5, substantial measures such as strengthening access controls and developing disaster recovery plans can be identified. The research emphasizes the importance of a structured approach in improving the security of academic information systems, with COBIT 5 as a useful tool. With the right measures, system security can be enhanced to protect the integrity, confidentiality, and availability of critical data for educational institutions. In conclusion, these measures demonstrate how important COBIT 5 implementation is in addressing information security challenges in academic environments.
Sistem Pakar Penyakit Sapi Menggunakan Rule Based Reasoning dengan Forward Chaining Alfian, Muhammad; Aprianti, Winda; Rhomadhona, Herfia; Permadi, Jaka
Jurnal Teknomatika Vol 17 No 2 (2024): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v17i2.1541

Abstract

Tanah Laut Regency is a district in South Kalimantan known as a livestock farming hub, particularly for beef cattle farming. The beef cattle population in this regency reached 88,420 heads in 2023. This large number of beef cattle requires greater attention from the local government. The Livestock and Animal Health Office of Tanah Laut Regency has Field Extension Officers (PPL) stationed in every village to monitor and inspect the condition of beef cattle owned by farmers. The issue is that monitoring results are still recorded manually, and farmers lack sufficient knowledge about beef cattle diseases. As a result, diseases are often not detected early, leading to severe conditions and even death. An expert system with forward chaining reasoning is necessary to reduce farmers' dependence on PPL due to their limited knowledge of beef cattle diseases. The expert system was developed based on a knowledge base derived from literature studies and interviews with an expert (one of the PPL officers). Data collected includes 21 diseases and 62 symptoms. The database used for the system consists of six tables. The system's functionality was tested using Blackbox Testing, and all functionalities performed well. The accuracy of the expert system was tested using 10 test data samples, achieving an accuracy rate of 90%.
Klasifikasi Data Tak Seimbang Menggunakan Algoritma Random Forest dengan SMOTE dan SMOTE-ENN: (Studi Kasus pada Data Stunting) Anju Fauziah; Julan Hernadi
Jurnal Teknomatika Vol 17 No 2 (2024): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v17i2.1530

Abstract

Algoritma random forest merupakan salah satu metode klasifikasi pembelajaran mesin yang banyak digunakan karena memiliki keunggulan dalam mengurangi resiko overfitting sekaligus meningkatkan kinerja prediksi secara umum. Namun untuk data dengan kelas tidak seimbang, algoritma ini tidak mampu mencapai performa maksimal khususnya dalam memprediksi data pada kelas minoritas. Untuk itu artikel ini menawarkan dua metode resampling untuk menyeimbangkan data, yaitu Synthetic Minority Oversampling Technique (SMOTE) dan Synthetic Minority Oversampling Technique with Edited Nearest Neighbors (SMOTE-ENN). Untuk klasifikasi data diterapkan algoritma random forest terhadap data asli dan hasil resampling baik menggunakan SMOTE maupun SMOTE-ENN. Studi kasus diterapkan pada data stunting yang berjumlah 421 pada kelas mayoritas dan 79 pada kelas minoritas. Diperoleh akurasi 89% pada data asli, 90% pada data hasil resampling dengan SMOTE-ENN, dan 91% pada data resampling dengan SMOTE. Walaupun tidak terlalu signifikan, teknik resampling dengan SMOTE memberikan akurasi terbaik.
Curve Fitting Kurva Tegangan Keluaran Sensor GP2Y0A02YK untuk Unjuk Kerja yang Lebih Akurat Priyanto, Agung; Buntoro Irawan; Titik Rahmawati; Ari Cahyono
Jurnal Teknomatika Vol 17 No 2 (2024): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v17i2.1540

Abstract

Sensors in the internet of things (IoT) and wireless sensor networks (WSN) for various purposes often require recalibration. The datasheet that accompanies the sensor usually displays a table of sensor’s output with minimum, typical and maximum values. This means that there is a tolerance of the values ​​that are still allowed by the manufacturer. For sensors with variable output voltage, it is usually displayed graphically. If the graph is not linear, curve fitting is needed to obtain the curve equation. In this research, curve fitting will be carried out using the least sum of squared errors method using a matrix. The curve equation resulting from curve fitting is needed for data processing or if it is needed to predict fixed variables if the independent variables are known. One of the sensors that has an output voltage curve that is not a straight line is the distance sensor from Sharp, the GP2Y0A02YK series. According to the datasheet, this sensor can be used to measure distances from 20 centimeters to 150 centimeters. The graph of the output voltage measuring distances from 20 cm to 150 cm is in the form of a curved curve. With calibration using curve fitting, it is hoped that the accuracy of sensor measurements and the processing of its output data will increase.
Perbandingan Deteksi Objek Kemeja Putih dan Hitam menggunakan ANN dan CNN.: Indonesia Jane Arnecia, Zahra; Wiliani, Ninuk
Jurnal Teknomatika Vol 17 No 2 (2024): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v17i2.1552

Abstract

This study discusses the comparison of object detection of white shirts and black shirts using the Artificial Neural Network and Convolutional Neural Network methods. The purpose of this study is to analyze the performance of the two algorithms in recognizing color differences in objects and characteristics of shirts. The dataset used is a dataset of white and black shirts from various angles. In this study, it is known that the CNN method is superior in detecting black and white shirts with an accuracy of 41% compared to ANN, which reaches an accuracy of 29%.
Perbandingan Perbandingan Kinerja ANN dan CNN dalam Tugas Klasifikasi Citra Berbasis Pembelajaran Mesin Akbar Nugroho, Faathir; Wiliani, Ninuk
Jurnal Teknomatika Vol 18 No 1 (2025): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v18i1.1561

Abstract

Advances in machine learning have brought great impact on image recognition through Artificial Neural Network (ANN) and Convolutional Neural Network (CNN) approaches. This study compares the performance of both algorithms in image classification with a dataset of two classes, namely Green and Red Keychains. The dataset consists of 100 images processed through augmentation and data division of 65% for training and 35% for testing. The evaluation results show that CNN has higher accuracy, which is 88.24% to 93.94%, compared to ANN which reaches 62.12% to 67.65%. CNN is also more efficient in training time. The advantage of CNN lies in its ability to extract spatial features through convolution layers, while ANN is more suitable for simple data. This study concludes that CNN is superior for color-based image classification, although further research is needed with larger datasets.
Perbandingan Model CNN dan SVM untuk Klasifikasi Jenis Footwear pada Dataset Alas Kaki Berbasis Citra Gina Annisa; Ninuk Wiliani
Jurnal Teknomatika Vol 18 No 1 (2025): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v18i1.1564

Abstract

The classification of footwear types, such as boots, sandals, and shoes, is a significant challenge in the development of image recognition systems powered by artificial intelligence. This study aims to compare the performance of two popular classification models, namely Convolutional Neural Network (CNN) and Support Vector Machine (SVM), in recognizing footwear types. The dataset used is the Footwear-Shoe vs Sandal vs Boot Image Dataset, consisting of 3000 images for each category with a resolution of 136x102 pixels in RGB format. The methodology includes training and testing both models using optimized parameters to measure accuracy, precision, and computational efficiency. The results show that CNN achieves an accuracy of 98%, while SVM reaches an accuracy of 96%. The findings indicate that CNN is more suitable for applications requiring high accuracy, while SVM is an effective alternative in resource-constrained scenarios. This study offers significant contributions to understanding model performance in image-based footwear classification using machine learning.
Analisis Akurasi Perbandingan Jumlah Layer Deteksi Warna Objek Menggunakan Algoritma Convulutional Neural Network Prasetyo, Dio; Wiliani, Ninuk
Jurnal Teknomatika Vol 18 No 1 (2025): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study evaluates the impact of variations in the number of layers on the implementation of the Convolutional Neural Network (CNN) algorithm in a color-based object identification and categorization system, using python language supported by the TensorFlow/Keras framework. The data used is a collection of visual data in the form of red and white cups divided into a proportion of 90% training data and 10% testing data in the dataset in this study which amounted to 62 red cup data and 59 white cup data. Testing was carried out by comparing three different convolution layer configurations of 1, 2, and 3 layers, where each configuration was integrated with a max pooling and fully connected layer. The results of the study showed an accuracy of 92%, precision of 93%, recall of 92%, and f1-score of 92%. On the other hand, the application of two and three convolution layers actually showed a significant decline with an accuracy of only 46%.
Sistem Deteksi Dini Anemia pada Anak Usia 0-59 Bulan Menggunakan Naïve Bayes dan Optimasi Particle Swarm Optimization Aksan, Azzikra; Anggraini, Deviana Dyah; Ridwan, Muhamad Fikry Maulana; Santoso, Herdiesel
Jurnal Teknomatika Vol 18 No 1 (2025): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v18i1.1574

Abstract

Anemia in children aged 0–59 months poses a serious health concern with long-term effects on growth and development. This study aims to develop a web-based early detection system for childhood anemia using a Naïve Bayes algorithm enhanced with Particle Swarm Optimization (PSO). The system uses secondary data from the 2018 Demographic and Health Survey in Nigeria, which includes variables such as age, nutritional status, and medical history. Although the dataset is from Nigeria, the variables are universal and relevant, making the findings applicable for similar model development in other regions.The Naïve Bayes algorithm is employed for classifying anemia levels, while PSO is applied to improve prediction accuracy by optimizing feature weights and tuning model parameters. Results show an increase in accuracy from 92.17% to 95.71% after optimization. This demonstrates PSO’s effectiveness in improving model performance, especially in datasets with imbalanced class distributions.The system is implemented as a user friendly website, allowing quick and accessible anemia detection. This solution is particularly useful in regions with limited healthcare access. The findings indicate that combining Naïve Bayes with PSO can enhance predictive accuracy and support broader efforts to improve child health outcomes.
Efektivitas dan Efisiensi Penerapan Rekayasa Sistem Pengelolaan Reservasi Gedung Aula Berbasis Kepuasan Pengguna Sistem Prayitno, Seno Wiji; Darsanto; Margana, Ferry Kurniawan
Jurnal Teknomatika Vol 18 No 1 (2025): TEKNOMATIKA
Publisher : Fakultas Teknik dan Teknologi Informasi, Universitas Jenderal Achmad Yani Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30989/teknomatika.v18i1.1603

Abstract

The hall is a place used to hold events with a large space. Hall reservations are made by contacting the manager directly or coming directly to the hall building. This research aims to build a hall reservation management system and make it easier for tenants to make reservations online. The research was conducted using descriptive statistical methods with the Rational Unified Process (RUP) as a system development framework. White box and black box testing are alpha system testing. ISO 9241-11 standard and heuristic evaluation as system beta testing. White box testing begins with creating a flow graph, calculating cyclomatic complexity, and determining independent paths. While the black box starts by determining the test case and expected results, the actual results will be obtained. The results of measuring the usability level with ISO 9241-11 obtained an effectiveness level value of 100%, an efficiency level value of 100% with a total time of about 594 seconds, and a user satisfaction level value of 73 with a good category, grade B scale, acceptable description and passive NPS. The results of the heuristic evaluation obtained that there are still problems with the system, and each problem has a different problem severity rating.

Page 27 of 28 | Total Record : 271

 24   25   26   27   28 

Filter by Year

2010 2025


Reset
Filter By Issues
All Issue Vol 18 No 1 (2025): TEKNOMATIKA Vol 17 No 2 (2024): TEKNOMATIKA Vol 17 No 1 (2024): TEKNOMATIKA Vol 16 No 2 (2023): TEKNOMATIKA Vol 16 No 1 (2023): TEKNOMATIKA Vol 15 No 2 (2022): TEKNOMATIKA Vol 15 No 1 (2022): TEKNOMATIKA Vol 14 No 2 (2021): TEKNOMATIKA Vol 14 No 1 (2021): TEKNOMATIKA Vol 13 No 2 (2020): TEKNOMATIKA Vol 13 No 1 (2020): TEKNOMATIKA Vol 12 No 2 (2020): TEKNOMATIKA Vol 12 No 1 (2019): TEKNOMATIKA Vol 11 No 2 (2019): TEKNOMATIKA Vol 11 No 1 (2018): TEKNOMATIKA Vol 10 No 2 (2018): TEKNOMATIKA Vol 10 No 1 (2017): TEKNOMATIKA Vol 9 No 2 (2017): TEKNOMATIKA Vol 9 No 1 (2016): TEKNOMATIKA Vol 8 No 2 (2016): TEKNOMATIKA Vol 8 No 1 (2015): TEKNOMATIKA Vol 7 No 2 (2015): TEKNOMATIKA Vol 7 No 1 (2014): TEKNOMATIKA Vol 6 No 2 (2014): TEKNOMATIKA Vol 6 No 1 (2013): TEKNOMATIKA Vol 5 No 2 (2013): TEKNOMATIKA Vol 5 No 1 (2012): TEKNOMATIKA Vol 4 No 2 (2012): TEKNOMATIKA Vol 4 No 1 (2011): TEKNOMATIKA Vol 3 No 2 (2011): TEKNOMATIKA Vol 3 No 1 (2010): TEKNOMATIKA Vol 2 No 2 (2010): TEKNOMATIKA More Issue