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 505 Documents
 33   34   35   36   37 
A Comparative Study of Modern Activation Functions on Multi-Label CNNs to Predict Genres Based on Movie Posters Al Wafi, Ahmad Zein; Nugroho, Anan
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 3 (2024): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i3.29540

Abstract

Categorization of images based on their visuals into various genres has a crucial role in the recommendation system. However, multilabel classification poses significant challenges due to the complexity of assigning multiple labels to each instance. This study contributes to the understanding of how activation functions influence the efficiency and accuracy of multilabel CNNs and provides practical insights for selecting appropriate functions in movie poster classification tasks. This investigation focused on identifying the activation function that provided the fastest convergence, highest accuracy, and lowest computational cost or training time. The results show that the Leaky ReLU activation function achieved the fastest convergence and highest training accuracy with an top accuracy of 99.7% and GELU demonstrated the highest validation accuracy at 91.5% across the training iteration. Softplus showed convergence characteristics at epoch 14 while other in 30. The computational cost analysis revealed that ReLU was computationally efficient with training time of 1896 seconds. Overall, the Leaky ReLU activation function is identified as the most effective for multilabel CNNs, balancing convergence speed, accuracy, and computational cost.
Image-Based Position Control for Three-Wheel Omni-Directional Robot Sukamta, Sri; Nugroho, Anan; Subiyanto, Subiyanto; Rezianto, Rizal; Soambaton, Muhammad Febrian; Ardiyanto, Agus
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 3 (2024): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i3.29601

Abstract

Robotic technology continues to advance, but real-time position tracking of robot movements still faces challenges, especially in dynamic and irregular environments. Sensors often fail to maintain accuracy due to environmental disturbances. This study introduces an innovation using omnidirectional wheels on a three-wheeled robot and image-based position control to improve maneuverability and precision. This method utilizes an infrared camera mounted on the ceiling to detect the robot's position. Image processing algorithms are used to determine waypoints and direct the robot. Omni-directional wheels allow the robot to move freely in all directions, which is important for accurate navigation on complex trajectories. The robot was tested on the "X" and "Square" trajectories in a 1.8-meter x 1.8-meter room to rotate vertical, horizontal, and diagonal movements. The test results showed that on the "X" trajectory, the second movement had the most significant error with a Mean Absolute Error (MAE) of 134.96, while the third movement had the slightest error with an MAE of 52.49, with an average error of 91.36. The first and third movements in the “Square” trajectory showed more significant errors than the second and fourth movements, with MAE of 105.37 and 100.47, respectively. The second and fourth movements had MAE of 67.20 and 59.65, with an average error of 83.17. These results indicate that the image-based control system and omnidirectional wheels improve accuracy compared to conventional methods, which is important for robot navigation applications. Practical implications of this technology include potential applications in the robotics and automation industry. Future research should focus on developing more precise control algorithms and sensors to improve accuracy. Directions for future research include exploring more sophisticated image processing techniques and applying this technology to various industrial scenarios. 
A Novel of PSO Modified Carrier-Based PWM Technique to Reduce Total Harmonic Distortion in The Inverter Topology 7-level Cascade H-Bridge Triple Voltage Boosting Gain Falah, Moh Zainul; Sujito, Sujito; Aripriharta, Aripriharta
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.v10i4.29645

Abstract

This research focuses on optimizing the Particle Swarm Optimization (PSO) method in switching modulation to reduce total harmonic distortion (THD) in a 7-level Cascade H-Bridge Multi-Level Inverter (MLI) topology with triple voltage boosting gain. MLI Cascade H-Bridge is an inverter topology that is widely used in power conversion applications because of its ability to produce high voltage output with low harmonics. However, the resulting THD is still a major challenge in improving power quality. In this research, the PSO method is applied to find optimal parameters in switching modulation that can minimize THD. The research results show that the PSO method succeeded in reducing THD significantly with a THD value of 7.80% whereas the previous THD was 17.27%. The implementation of PSO in switching modulation is expected to be an effective solution for inverter applications in industry and power systems. The THD value from the PSO optimization is stated to be in accordance with IEEE 519 standards with a maximum permitted THD of 8%. This value is better than previous research, namely 17.27%.
Comparative Analysis of Optimizer Effectiveness in GRU and CNN-GRU Models for Airport Traffic Prediction Riyadi, Willy; Jasmir, Jasmir
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 3 (2024): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i3.29659

Abstract

The COVID-19 pandemic has posed significant challenges to airport traffic management, necessitating accurate predictive models. This research evaluates the effectiveness of various optimizers in enhancing airport traffic prediction using Deep Learning models, specifically Gated Recurrent Units (GRU) and Convolutional Neural Network-Gated Recurrent Units (CNN-GRU). We compare the performance of optimizers including RMSprop, Adam, Nadam, AdamW, Adamax, and Lion, and analyze the impact of their parameter tuning on model accuracy. Time series data from airports in the United States, Canada, Chile, and Australia were used, with preprocessing steps like filtering, cleaning, and applying a MinMax Scaler. The data was split into 80% for training and 20% for testing. Our findings reveal that the Adam optimizer paired with the GRU model achieved the lowest Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) in the USA. The study underscores the importance of selecting and tuning optimizers, with ReduceLROnPlateau used to adjust the learning rate dynamically, preventing overfitting and improving model convergence. However, limitations include dataset imbalance and region-specific results, which may affect the generalizability of the findings. Future research should address these limitations by developing balanced datasets and exploring optimizer performance across a broader range of regions and conditions. This study lays the groundwork for further investigating sustainable and accurate airport traffic prediction models.
Optimizing Disaster Response: A Systematic Review of Time-Dependent Cumulative Vehicle Routing in Humanitarian Logistics Hartama, Dedy; Wanayumini, Wanayumini; Damanik, Irfan Sudahri
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 3 (2024): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i3.29686

Abstract

Effective delivery of aid during disasters is crucial for mitigating impacts and ensuring well-being. A major challenge in humanitarian logistics is optimizing vehicle routing to maximize efficiency and minimize delivery times. which included 50 studies published between 2012 and 2022. We used the prism method to guide the process of choosing a study, which started from 200 Abstract which is identified and ends with 50 appropriate studies for in -depth analysis. This systematic literature review (SLR) examines the Time-Dependent Cumulative Vehicle Routing Problem (TDCVRP) in humanitarian logistics, identifying VRP variants, their applications, and effectiveness in disaster scenarios. Using a comprehensive search and PRISMA guidelines, the review highlights the importance of optimization models and advanced algorithms. Applications include aid delivery, evacuation management, and facility location optimization, though challenges like computational complexity and reliance on real-time data persist. The review identifies research gaps and suggests future research should focus on integrating advanced methods and improving practical applicability in disaster responses.
Optimization of YOLOv4-Tiny Algorithm for Vehicle Detection and Vehicle Count Detection Embedded System Muwardi, Rachmat; Nugroho, Ivan Prasetyo; Salamah, Ketty Siti; Yunita, Mirna; Rahmatullah, Rizky; Chung, Gregorius Justin
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 10 No. 3 (2024): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v10i3.29693

Abstract

Currently, the implementation of object detection systems in the traffic sector is minimal. CCTV cameras on highways and toll roads are primarily used to monitor traffic conditions and document violations. However, the data recorded by these cameras can be further utilized to enhance traffic management systems. The author proposes a vehicle detection and counting system using YOLOv4-Tiny. The research aims to improve vehicle detection and counting accuracy by employing a median filter and grayscale processing, which simplify object detection. The proposed YOLOv4-Tiny algorithm has shown impressive results on various datasets, including MAVD, GRAM-RTM, and author dataset. The system achieved a detection accuracy of 98.95% on the MAVD dataset, 99.5% on the GRAM-RTM dataset (comparable to YOLOv4), and 99.1% on the author dataset. Furthermore, the system operates at 25 frames per second (FPS), a notably high rate compared to other methods. While the system demonstrates excellent accuracy in counting cars, it encounters some accuracy loss with other vehicle classifications. The author concludes that the system is highly suitable for real-world applications but notes that inaccurate labeling can lead to vehicle counting errors.
Fault Detection in Continuous Stirred Tank Reactor (CSTR) System Using Extended Luenberger Observer Mursyitah, Dian; Son Maria, Putut; Pebriani, Sovi; Delouche, David; Zhang, Tingting; Kratz, Frédéric
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.v10i4.29797

Abstract

This research proposes fault detection in a Continuous Stirred Tank Reactor (CSTR) system using an Extended Luenberger Observer (ELO). The ELO is chosen due to the non-linearity of the CSTR system. Accurate state estimation is critical for effective fault diagnosis; therefore, the performance of the ELO is initially tested using two indicators: robustness and sensitivity in estimating the level and concentration within the CSTR system. The sensitivity test yields promising results, with the ELO accurately estimating the actual system despite variations in input and initial conditions, and with a fast convergence time of 1 seconds. The robustness test also demonstrates positive outcomes, as the ELO continues to estimate the system accurately even in the presence of noise with standard deviation 2.5% of measurements. Furthermore, faults that can be related to sensor malfunctions or the disturbances in the CSTR process were successfully detected using the ELO. Performance analysis and fault detection in the CSTR system are presented through simulation. The contributions of this research include development of ELO for non-linear dynamics CSTR system and evidence of its effectiveness in detecting fault within the in CSTR system.
Raspberry Pi 4 and Ultrasonic Sensor for Real-Time Waste Classification and Monitoring with Capacity Alert System Yuliza, Yuliza; Muwardi, Rachmat; Kusuma, Prima Wijaya; Lenni, Lenni; Rahmatullah, Rizky; Yunita, Mirna; Dani, Akhmad Wahyu
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.v10i4.30036

Abstract

The problem of waste management creates daily rubbish buildup due to thorough sorting. garbage sometimes accumulates in public garbage receptacles due to officials' ignorance of bin capacity and collectors' schedules, causing unclean conditions and the development of deadly diseases. Internet of Things technology was used to create a smart waste classification system with a notification mechanism in this study. This system classifies waste into plastic, metal, B3, and organic using a Raspberry Pi 4, camera module, and deep learning model. The classification uses a Convolutional Neural Network to speed up waste processing and separation. This research can be linked with research on separating trash types in one container and then allocated to garbage bins by type. Ultrasonic sensors and Raspberry Pi 4 can continuously monitor waste levels by sending data to the Ubidots IoT platform over HTTP. Based on experimental device data, system analysis shows 90% classification accuracy for all four waste categories. A Wireshark network analysis showed 61,098 bytes/s of throughput, 16 ms of delay, and zero data loss, demonstrating the system's ability for real-time monitoring and alerting. This research provides a realistic, cost-effective, and minimal solution to improve garbage classification and reduce collection costs to promote sustainability.
Using Graph Neural Networks and CatBoost for Internet Security Prediction with SMOTE Sunge, Aswan Supriyadi; Hendric, Spits Warnars Harco Leslie; Pramudito, Dendy K.
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.v10i4.30157

Abstract

Internet security is the most important issue in cyberspace, on the other hand, cybercrime occurs, and the most serious threat is the theft of personal data and its misuse for the benefit of others. Although cyberspace is while internet security cannot eliminate all risks, predictive models can significantly reduce cybercrime by identifying vulnerabilities if you know how to prevent it. One of the most important things is that many internet users do not know what measures are used to avoid and whether it is safe to visit or explore, on the other hand, in system development existing studies on internet security prediction often rely on generic models that lack precision in identifying influential features or ensuring class balance in developing internet security. In this case, Deep Learning (DL) helps learn patterns from recorded data, find relevant patterns, and use the model effectively. The purpose of this study is to identify the most influential features in internet security and evaluate the effectiveness of advanced machine learning models, such as Graph Neural Networks (GNNs) and Categorical Boosting (CatBoost), for predicting internet safety. So far other studies have tested the entire data set and used a model that is generally. This is expected to lead to the design or development of systems and programs that are useful for internet security. The study used a dataset of 11,055 records with 30 features and binary classification labels ('Safe' and 'Not Safe'). To address the class imbalance, SMOTE was applied before splitting the data into training and testing sets. In testing the Graph Neural Networks (GNNs) model achieved 93.58% accuracy, 93.63% precision, 93.58% recall, and 93.55% F1-score, demonstrating its effectiveness for internet security prediction. From the results of testing the CatBoost model was used to identify key features, revealing that the 'URL of Anchor,' 'SSLFinal State,' and 'Web Traffic' have the most significant impact. From the experiments conducted, the CatBoost effectively identified features with the highest on prediction accuracy, and the GNNs model is very accurate and precise for developing applications or systems to predict internet security.
Estimation of Ro and Vc Parameters Using Recursive Least Square, as Well as OCV Parameters at Rest Conditions in Pulse Test for the Thevenin Battery Model Implemented on Raspberry Pi Zero Topan, Paris Ali; Fardla, Dinda
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.v10i4.30191

Abstract

Lithium polymer (Li-Po) batteries are one of the most widely used batteries, especially on everyday devices such as mobile phones and laptops. One of the main reasons for using this type of Lithium battery is its high energy density. In its use, this battery needs to be monitored to prevent unwanted things from happening. A model is needed to describe the characteristics of Li-Po batteries well in monitoring changes in the battery system. In general, the model that is often used is the Thevenin battery model. In this study, the parameters in the Thevenin model, such as Ro and Vc, are estimated using the RLS algorithm, while the OCV is estimated according to the terminal voltage value during the rest condition in the pulse test. The entire estimation process is carried out using a low-computing device, the Raspberry Pi Zero, with the help of an INA 260 sensor to read the battery current and voltage. The battery capacity used in this study is 5200mAh with a voltage of 11.1V. The pulse test device in this study uses a constant current discharge and a microcontroller device for the timing process. Before the voltage and current data are used for parameter estimation, the data is filtered using a one-dimensional Kalman filter. The estimation results for OCV, Ro, and Vc show quite good performance, with an MSE value of 5.42× 10−6 V and an RMSE of 0.0023 V.

Page 35 of 51 | Total Record : 505

 33   34   35   36   37 

Filter by Year

2015 2025


Reset
Filter By Issues
All Issue Vol. 11 No. 4 (2025): December 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. 3 (2023): September Vol 9, No 2 (2023): June Vol. 9 No. 2 (2023): June Vol. 9 No. 1 (2023): March 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 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