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 yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI)
Published by Universitas Ahmad Dahlan
ISSN : 23383070     EISSN : 23383062     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
JITEKI (Jurnal Ilmiah Teknik Elektro Komputer dan Informatika) is a peer-reviewed, scientific journal published by Universitas Ahmad Dahlan (UAD) in collaboration with Institute of Advanced Engineering and Science (IAES). The aim of this journal scope is 1) Control and Automation, 2) Electrical (power), 3) Signal Processing, 4) Computing and Informatics, generally or on specific issues, etc.
Arjuna Subject : -
Articles 401 Documents
 35   36   37   38   39 
Tailoring Data Storage Configuration for Efficient Fraud Detection Model Training Syarif, Abdusy; Satria, Muhammad Haikal; Gabteni, Hanene
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 4 (2024): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i4.30013

Abstract

The rapid growth of e-commerce in Indonesia, with a record 88.1% growth rate, has been accompanied by a surge in online fraud, leading to an estimated loss of 4.62 trillion rupiahs. Current fraud prevention methods, such as the widely used 3D-Secure system, though effective, result in a high rate of transaction abandonment (approximately 16%), which is undesirable for merchants. To address this, we propose an AI-based fraud detection system that leverages machine learning models to identify potentially fraudulent transactions. By employing a combination of classification algorithms, including logistic regression and neural networks, security protocols are activated only for high-risk transactions, optimizing transaction processing efficiency and improving detection accuracy. Our study focuses on fine-tuning key parameters of the AI-Fraud Detector model, specifically some parameters such as ∆ttrain, ∆tlag and f rac hr pass, to enhance detection performance over time. Simulation performances using ROCAUC, false positive rate (fpr), and true positive rate (tpr) metrics show that a configuration with a training period (∆ttrain) of 180 days, a lag period (∆tlag ) of 90 days, and a high-risk pass fraction (f rac hr pass) of 10% yields a balance between detection efficiency (∼ 50%) and a reduced false positive rate. It means that the model is able to identify approximately 50% of the actual high-risk events while minimizing the number of times it incorrectly identifies a low-risk event as high-risk. However, further research is required to refine these results, explore parameter optimization strategies, and enhance the model’s adaptability to evolving fraud patterns. Future work will focus on optimizing thresholds, improving model robustness over time, and ensuring effective detection of new fraud schemes. This research improves model performance by optimizing key parameters and enhancing detection accuracy while minimizing false positives
Application of Solar Cell on Organic Waste Shredding Machine for Compost Fertilizer Production Especially Manure from Pig Farms: A Case Study in Sustainable Energy Development Liga, Marthen; Sampe, Aris; Lefaan, Yosef; Oktaviani, Theresia Wuri; Khaliq, Idham
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 4 (2024): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i4.30261

Abstract

Organic waste management in Indonesia faces significant challenges due to the high greenhouse gas emissions produced. In 2020, greenhouse gas emissions from waste management in Indonesia especially the waste sector contributes around 3.2% of total global emissions. The use of organic waste shredders is one solution to minimize waste volume; althought still heavily rely on conventional energy, which is not environmentally friendly. This study aims to evaluate the implementation of solar photovoltaic (PV) technology in organic waste shredding machines to enhance energy efficiency and reduce environmental impacts. An experimental approach was used in this research. Data were collected through measurements of energy generated by the solar cells, energy consumed by the machine, and the organic waste shredding output processed into compost fertilizer. The results showed that use of solar cells could generate an average of 5.8 kWh of energy per day, with machine energy efficiency reaching 72%. Compared to conventional energy, the use of solar cells increased the shredder machine's productivity to 25 kg/hour and reduced greenhouse gas emissions by up to 70%. Additionally, machine operating time increased by 20% compared to machines using conventional energy.  This increase is due to the solar cell technology itself. In conclusion, application of solar cell technology in organic waste shredders not only improves operational efficiency but also significantly contributes to carbon emission reduction. The research  contribution is to offer concrete solutions that support the achievement of national and global carbon emission reduction targets, as well as creating a waste management model that can be applied in various regions in Indonesia and the world.
Design and Implementation of an Autonomous Service Robot for Hospital Isolation Room Using Robot Operating System 2 and Navigation 2 Muhammad Nurul Puji; Dwinandana, Tubagus Ahmad; Kasih, Tota Pirdo; Lee, Edmond; Kamalo, Giovanni Benedict Davin; Anthony, Patrick; Kunaifi, Matthew
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 4 (2024): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i4.30353

Abstract

Healthcare-associated infections or nosocomial infections are infections that are acquired after admission to a hospital. This type of infection extends the length of stay, increases the cost of healthcare, and increases the mortality rate. This infection is caused by pathogens that are present in the hospital environment. These pathogens are transmitted when a hospital worker comes in contact with a patient or their environment. Thus, it is important to reduce the contact between them to stop the spread of pathogens. To reduce contact an autonomous service robot is utilized to deliver food or medicine to patients. This robot will be able to go to multiple target positions autonomously and will be controlled by a web application. Furthermore, the robot can provide a video call if the patient needs help. The robot platform used is the turtlebot3 and the software framework used is robot operating system 2 humble. The inflation radius and cost scaling parameters are tuned to increase the navigation success rate. Problems encountered during testing include glass windows not being detected by lidar, noisy lidar data, and obstacles being too low to be detected. These problems are solved using tape, costmap and laser filter, and keepout zones respectively. To evaluate the performance and capability of the app the robot is tested using a set of target locations entered on the app. During testing poor odometry causes localization error that causes recovery behaviors. The final system has a navigation success of 95%, with an average navigation speed of 0.17 m/s, and an average distance to target of 0.0587 m.
Enhancing Network Security Through Real-Time Threat Detection with Intrusion Prevention System (Case Study on Web Attack) Rahmawati, Tia; Karna, Nyoman; Shin, Soo Young; Putra, Made Adi Paramartha
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 4 (2024): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i4.30380

Abstract

Cyberattacks on government websites in Indonesia have been steadily increasing, with over 109 million incidents recorded in 2023 by the National Cyber Security Operations Center (BSSN). A Netcraft survey revealed that more than one billion websites globally face similar threats, highlighting the urgent need for improved security measures, especially given infrastructure limitations and inadequate security implementations. Approximately 51% of Micro, Small, and Medium Enterprises in Indonesia reported experiencing web attacks, with 95% stating that these attacks severely disrupted their operations. This study implements a Suricata-based Intrusion Prevention System (IPS) to protect web servers from attacks such as SQL Injection, XSS, and command injection. Suricata monitors network traffic and blocks threats in real time. Detection logs in JSON format are managed through Filebeat, processed by Logstash, stored in Elasticsearch, and visualized using Kibana. The key contribution of this research lies in designing a comprehensive set of rules and integrating all components into a single Docker container, streamlining the deployment process. Testing confirmed that the designed rules effectively detect and block attack payloads by leveraging a rule structure in suricata and nfqueue capable of identifying all suspicious traffic. The novelty of this research lies in deploying a fully operational real-time security system on low-resource computers, demonstrating effective threat management under constrained conditions.
KNN-Based Music Recommender System with Feedforward Neural Network Loiz, Andhika; Baizal, Z.K. Abdurahman
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 4 (2024): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i4.30526

Abstract

Music, as a form of entertainment, is now an essential element in the lives of many individuals. Access to music-related information has become widespread through various websites and applications, leading to a significant increase in music data. Technological advancements have driven the development of music recommendation system research, which utilizes multiple methods, algorithms, and classification techniques to present recommendations that match user preferences. This research contributes to integrating the K-Nearest Neighbors (KNN) method for initial classification and the more advanced Feedforward Neural Network (FNN) model. In addition, this research also recommends songs with similar audio features. The main focus of this research is to design and evaluate a song recommendation system by combining such methods while comparing various hyperparameter results to find the most suitable model. The best model found will be incorporated into Content-Based Filtering (CBF) to provide song recommendations based on genre. This research uses the GTZAN dataset of 1,000 audio data from ten music genres. The K-NN model test assesses how well the model maintains consistency and achieves optimal performance. This study conducted three tests to find the best-performing model by integrating the model and hyperparameters. The results showed that the third FNN model showed the best performance after being optimized using the SGD optimizer. Furthermore, this model was combined with the CBF method using cosine similarity calculation. The system effectively recommended songs based on the blues genre, with five relevant nearest neighbors and an average score reaching 98%.
Estimating Forest Carbon Stocks Using CNN and Vegetation Texture Features Extracted from UAV and Satellite Data in Telkom University Aydin, Raditya; Setiawan, Erwin Budi
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 4 (2024): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i4.30546

Abstract

Forests play a crucial role in mitigating climate change by acting as carbon sinks, yet traditional methods of carbon stock estimation, reliant on manual tree measurements, are costly, time-consuming, and geographically limited. Recent advancements in remote sensing technologies, such as the combination of Unmanned Aerial Vehicles (UAVs) and Google Earth Engine (GEE), offer a promising alternative by integrating high-resolution local observations with global-scale data. Using the power of Convolutional Neural Networks (CNNs), this study suggests an integrated method for classifying carbon stocks by fusing textural parameters like homogeneity and entropy with spectral indices like Green Chromatic Coordinates (GCC) and Excess Green Index (ExG). CNNs are used to capture the spectral richness and structural complexity of vegetation because of their propensity to extract hierarchical spatial characteristics. The research compares the performance of various feature combinations—color-based, texture-based, and mixed features—using a hybrid framework of UAV and GEE data. It is anticipated that the results will demonstrate how spectral and textural features work together to increase classification accuracy. In addition to tackling major issues in carbon stock estimation, this scalable and integrated framework is made to adapt to a variety of forest ecosystems and aid in the creation of conservation policies and the mitigation of climate change.
Solution Stirring Design Using Magnetic Stirrer on DC Motor with PLC-Based PID Method Natawangsa, Hari; Furizal, Furizal; Ma'arif, Alfian; A. Salah, Wael
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 1 (2025): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v11i1.26534

Abstract

Along with the development of the times, the industrial and manufacturing world also develops. One of the activities that is widely carried out in the industrial and manufacturing world is stirring production raw materials, either in the form of solutions or liquids. The purpose of the stirring process is to get a perfectly mixed (homogeneous) stirring. For this reason, a device is needed that can stir the solution as desired. One type of tool that can be used is a magnetic stirrer placed on a DC motor. However, when the DC motor is given a load, the DC motor tends to become unstable so a controller is needed. To solve this problem used PID controller. PID controllers use control constants in the form of PB, Tick, and Tdk. To obtain the controlling constant, a process of trial and error is carried out. The most stable results obtained from the testing process were PB = 600%, Tik = 1.2 s, and Tdk = 0.2 s. With system response in the form of rise time 0.7778 s, peak time = 5s. settling time 5.4286 s, overshoot = 2.8571 RPM and steady state error = 0%. The setpoint used is 700 RPM with a sampling time of 60 ms. The developed system successfully achieves stable and well-controlled stirring. The results of this research contribute to the improvement of solution stirring processes in the industrial and manufacturing domains. The developed system can be effectively utilized for stirring solutions, enhancing the efficiency and quality of production processes.
Early Mobilization Therapy Robot for Medical Rehabilitation Purpose Sutyasadi, Petrus; Parikesit, Elang; Widodo, Bernardinus Sri
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 1 (2025): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v11i1.30383

Abstract

Impairments in ambulation may result from neurological dysfunction. The expense of therapy constitutes a substantial obstacle to recovery following neurological disorders. An uncomplicated and cost-effective two-degree-of-freedom early mobilization trainer robot has been conceived and constructed. This device is intended for early training or adaptation before ready for mobilization training on the ground. The early mobilization trainer assists persons with mobility impairments during their early therapy phase. This research analyses the design and construction of an early mobilization trainer positioned within the patient's bed. The experimental findings indicate that in the condition with load at the hip joint, the output of this device can follow the trajectory input precisely. For the knee joint, the output of this device can follow the trajectory input, but with 0.9 degree of a steady-state error. This amount of steady state error does not affect the therapy because it is too small in term of knee movement precision during therapy.
Malware Classification and Detection using Variations of Machine Learning Algorithm Models Maslan, Andi; Hamid, Abdul
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 1 (2025): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v11i1.30477

Abstract

Malware attacks are attacks carried out by an attacker by sending malicious codes to various files or even many packages and servers. Therefore, reliable network operations are a factor that needs to be considered to prevent attacks as early as possible in order to avoid more severe system damage. Types of attacks can be Ping of Death, flooding, remote-controlled attacks, UDP flooding, and Smurf Attacks.  Attack data was obtained from the ClaMP dataset, which has an unbalanced data set, and has very high noise, so it is necessary to analyze data packets in network logs and optimize feature extraction which is then analyzed statistically with machine learning algorithms. The purpose of the study is to detect, classify malware attacks using a variety of ML Algorithm models such as SVM, KNN and Neural Network and testing detection performance. The research stage starts from pre-Processing, extraction, feature selection and classification processes and performance testing. Training and testing data in the study used a mixed model, namely data division, split model and cross validation. The results of the study concluded that the best algorithm for detecting malware packages is the Neural Network for the Feature Combination category with an accuracy rate of 96.91%, Recall of 97.35% and Precision of 96.78%. So that the study can have implications for cyber experts to be able to prevent malware attacks early. While further research requires a special algorithm to improve malware attack detection, in addition to KNN, SVM and Neural Network. And another research challenge is to focus on feature extraction techniques on datasets that have unbalanced or varied features with the Natural Language Processing (NLP) approach. So this research can be used as a reference for researchers who are conducting research in the same field.
The Use of Attention-RNN and Dense Layer Combinations and The Performance Metrics Achieved in Palm Vein Recognition Indriani, Indriani; Syukriyah, Yenie
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 1 (2025): March
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v11i1.30517

Abstract

The utilization of palm veins in vascular biometrics is widely recognized, offering significant potential and challenges for advancing individual recognition technology. Deep learning has played a crucial role in enhancing the accuracy of these recognition systems. In this study, we proposed combining Attention-RNN and Dense Layer. To validate this proposed method, three deep learning model scenarios were implemented: (1) a combined Dense Layer with RNN, (2) an Attention-RNN model, and (3) a combined Attention-RNN with a Dense Layer for palm vein recognition. Experimental results demonstrated that the Attention-RNN combined with the Dense Layer achieved the highest accuracy, outperforming the other two models. The model’s performance was evaluated on two datasets, achieving 95% accuracy on the Kaggle dataset and 83% on the CASIA dataset, confirming its effectiveness in palm vein recognition.

Page 37 of 41 | Total Record : 401

 35   36   37   38   39 

Filter by Year

2015 2025


Reset
Filter By Issues
All Issue Vol. 11 No. 3 (2025): September Vol. 11 No. 2 (2025): June Vol. 11 No. 1 (2025): March Vol. 10 No. 4 (2024): December Vol. 10 No. 3 (2024): September Vol. 10 No. 2 (2024): June Vol. 10 No. 1 (2024): March Vol. 9 No. 4 (2023): December Vol 9, No 4 (2023): December Vol 9, No 3 (2023): September Vol 9, No 2 (2023): June Vol 9, No 1 (2023): March Vol 8, No 4 (2022): Desember Vol 8, No 3 (2022): September Vol 8, No 2 (2022): June Vol 8, No 1 (2022): March Vol 7, No 3 (2021): December Vol 7, No 2 (2021): August Vol 7, No 1 (2021): April Vol 6, No 2 (2020): December Vol 6, No 1 (2020): June Vol. 6 No. 1 (2020): June Vol 5, No 2 (2019): December Vol 5, No 1 (2019): June Vol 4, No 2 (2018) Vol 4, No 2 (2018) Vol 4, No 1 (2018) Vol 4, No 1 (2018) Vol 3, No 2 (2017) Vol 3, No 2 (2017) Vol 3, No 1 (2017) Vol 3, No 1 (2017) Vol 2, No 2 (2016) Vol 2, No 2 (2016) Vol 2, No 1 (2016) Vol 2, No 1 (2016) Vol 1, No 1 (2015) Vol 1, No 1 (2015) More Issue