cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Iswanto
Contact Email
-
Phone
+628995023004
Journal Mail Official
jrc@umy.ac.id
Editorial Address
Kantor LP3M Gedung D Kampus Terpadu UMY Jl. Brawijaya, Kasihan, Bantul, Yogyakarta 55183
Location
Kab. bantul,
Daerah istimewa yogyakarta
INDONESIA
Journal of Robotics and Control (JRC)
Published by Universitas Muhammadiyah Yogyakarta
ISSN : 27155056     EISSN : 27155072     DOI : https://doi.org/10.18196/jrc
Core Subject : Science, Engineering,
Aerospace Engineering Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Mechanical Engineering
Journal of Robotics and Control (JRC) is an international open-access journal published by Universitas Muhammadiyah Yogyakarta. The journal invites students, researchers, and engineers to contribute to the development of theoretical and practice-oriented theories of Robotics and Control. Its scope includes (but not limited) to the following: Manipulator Robot, Mobile Robot, Flying Robot, Autonomous Robot, Automation Control, Programmable Logic Controller (PLC), SCADA, DCS, Wonderware, Industrial Robot, Robot Controller, Classical Control, Modern Control, Feedback Control, PID Controller, Fuzzy Logic Controller, State Feedback Controller, Neural Network Control, Linear Control, Optimal Control, Nonlinear Control, Robust Control, Adaptive Control, Geometry Control, Visual Control, Tracking Control, Artificial Intelligence, Power Electronic Control System, Grid Control, DC-DC Converter Control, Embedded Intelligence, Network Control System, Automatic Control and etc.
Arjuna Subject : Teknik (semua kategori) - Teknik Kontrol dan Sistem
Articles 30 Documents
 1   2   3 
Search results for , issue "Vol 5, No 5 (2024)" : 30 Documents clear
Advanced Ensemble Deep Learning Framework for Enhanced River Water Level Detection: Integrating Transfer Learning Tawfeeq, Nisreen; Harbi, Jameelah
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22291

Abstract

The precise monitoring and prediction of river water levels are crucial for effective environmental management, flood prevention, and ensuring water security. This paper introduces an advanced deep learning framework that utilizes an ensemble of state-of-the-art neural networks, namely InceptionV3, VGG16, Xception, MobileNet, and ResNet152, to enhance the accuracy of water level detection from river imagery. The proposed system integrates these models through a robust ensemble methodology that leverages hard voting to improve predictive performance and reliability. Through rigorous preprocessing, including normalization, resizing, and augmentation, alongside strategic transfer learning, the framework achieves an impressive accuracy of 99.5833%, precision of 99.5929%, recall of 99.5762%, and an F1 score of 99.5838%. The ensemble approach not only addresses the variability in image data but also ensures robustness against overfitting and data imbalances. Furthermore, the application of Gradient-weighted Class Activation Mapping (Grad-CAM) enhances the interpretability of the model's decisions, facilitating trust and transparency in its predictions. This study not only demonstrates the potential of ensemble deep learning in hydrological applications but also sets the stage for future enhancements such as real-time processing and integration into comprehensive flood management systems. Future research will explore scalability, the incorporation of additional predictive variables, and the expansion of the model to include real-time monitoring capabilities, aiming to provide a more dynamic tool for disaster readiness and environmental conservation.
Reinforcement Learning-Based Trajectory Control for Mecanum Robot with Mass Eccentricity Considerations Nguyen, Minh Dong; Ngo, Manh Tien; Quang, Hiep Do; Phuong, Nam Dao
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22148

Abstract

This article presents a robust optimal tracking control approach for a Four Mecanum Wheeled Robot (FMWR) using an online actor-critic reinforcement learning (RL) algorithm to address the challenge of precise trajectory tracking problem in the presence of mass eccentricity and friction uncertainty. In order to handle these obstacles, a detailed dynamics model is derived using Lagrange’s equation, and the Hamilton–Jacobi–Bellman (HJB) equation is solved by iteration algorithm with policy evaluation and improvement. The training laws of optimal control law and value function are proposed after minimizing the modified Hamiltonian function. Moreover, to handle the time-varying property of tracking error model, a transform is given with the addition of time derivative term. Simulation Studies demonstrate the approach’s effectiveness, significantly improving trajectory tracking accuracy and robustness against disturbances. This research contributes to mobile robotics by enhancing control precision and reliability in dynamic environments.
Soft Tissue Compliance Detection in Minimally Invasive Surgery: Dynamic Measurement with Piezoelectric Sensor Based on Vibration Absorber Concept Hashem, Radwa; El-Hussieny, Haitham; Umezu, Shinjiro; El-Bab, Ahmed M. R. Fath
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22895

Abstract

Recent research in the medical field has increasingly focused on tissue repair, tumor detection, and associated therapeutic techniques. A significant challenge in Minimally Invasive Surgery (MIS) is the loss of direct tactile sensation by surgeons, as they cannot physically feel the organs they operate on. Tactile feedback enhances patient safety by tissue differentiation and reducing inadvertent damage risks. Addressing this challenge, this study introduces a novel tactile sensor designed for compliance detection to enhance tactile feedback in MIS. The sensor operates on a 2-Degree-of-Freedom (2-DOF) vibration absorber system, utilizing a piezoelectric actuator with a calibrated stiffness of 188 N/m. It interprets tissue stiffness regarding a spring constant, Ko, and measures changes in soft tissue stiffness by analyzing variations in the vibration absorber frequency, specifically at the frequency which causes the first mass to exhibit zero amplitude. The effectiveness of this sensor was evaluated through tests on polydimethylsiloxane (PDMS) specimens, which were engineered to replicate varying stiffness found in human organ tissues. Young's modulus of these specimens was determined using a universal testing machine, showing a range from 10.12 to 226.89 kPa. Additionally, the sensor was applied to measure the stiffness of various chicken tissues – liver, heart, breast, and gizzard with respective Young's moduli being 1.97, 9.47, 19.55, and 96.36 kPa. This sensor successfully differentiated between tissue types non-invasively, without requiring substantial deformation or penetration of the tissues. Given its piezoelectric nature, the sensor also holds significant potential for miniaturization through Micro-Electro-Mechanical Systems technology (MEMS), broadening its applicability in surgical environments.
Human Activity Recognition Using Accelerometer & Gyroscope Smartphone Sensor by Extract Statistical Features Abdullah, Muthana Hmod; Ahmed, M. A.
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22443

Abstract

Understanding behavioral patterns and forecasting the bodily motions of persons heavily relies on detecting human activities. This has profound ramifications in several domains, including healthcare, sports, and security. This study sought to identify and classify 18 human actions recorded by 90 people using smartphone sensors using the KU-HAR dataset. The primary aim of this study is to examine statistical features such as (mean, mod, entropy, max, median …etc.) derived from time-domain sensory data collected using accelerometers and gyroscopes. Activity detection utilizes many machine learning methods such as Random Forest (RF), Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LG), Naïve Bayes (NB), and AdaBoost. The RF model achieves the highest overall accuracy of 99%. While the DT model gets 95%, SVM receives 93%, and the KNN gets 82%. At the same time, the other model didn’t get good results. The research is evaluated using accuracy, recall, precision, and f1-scor. The research contribution is to extract the statistical feature from the raw file of the sensor to create a new dataset. This research recommends employing statistical features in time series. Future research is recommended to solve misclassification in certain activities, which could be achieved using feature selection to reduce the number of features.
Predicting SI Engine Performance Using Deep Learning with CNNs on Time-Series Data Hofny, Mohamed S.; Ghazaly, Nouby M.; Shmroukh, Ahmed N.; Abouelsoud, Mostafa
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22558

Abstract

In this study, deep learning (DL) model is used to predict brake power (BP) of GX35-OHC 4-stroke, air-cooled, single-cylinder gasoline engine. The engine uses E15 (85% gasoline + 15% ethanol) as a fuel due to its high performance and low emissions. A convolutional neural networks (CNN) model is used on time-series data due to their ability to capture temporal patterns and relationships in sequential data, such as engine BP. While studying the performance of the network, it is found that the root mean squared error (RMSE) is 0.0007, explained variance score (EVS) is 0.9999, and mean absolute percentage error (MAPE) is 0.22%. Compared to traditional machine leaning methods, these metrics demonstrate the high accuracy and reliability of the model, confirming its effectiveness in predicting BP. Various performance curves are plotted such as comparing target and predicted values, regression plots (to indicate the generalization capability),  learning curve (to demonstrate the model's effective training progress and convergence), Bland-Altman plot (to show the convergence between the actual and predicted values), histogram and density plot (to show a close fit between predicted and actual values), density plot of actual and predicted outputs, and residual plot (to show randomly distributed errors). This high accuracy and reliability of this DL model help in effective real-time engine performance monitoring, and reducing emission levels, especially for the adoption and use of renewable fuels like E15.
Explainable Ensemble Learning Models for Early Detection of Heart Disease Laftah, Raed Hassan; Al-Saedi, Karim Hashim Kraidi
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22448

Abstract

Coronary diseases (CVD) are a major global health concern, and timely, accurate diagnosis is crucial for effective treatment and management. As machine learning is, has steadily been on the improvement way, and it's there where we find the transformative potential for enhancing the diagnostic accuracy for their predictive accuracy using the Local Interpretable Model-agnostic Explanations technique to ensure the explainability of our models. With the advancement of machine learning, we aim to enhance diagnostic accuracy by developing a high-precision prediction tool for heart disease using various ML models. We utilized a Kaggle dataset to implement several ML models, including Random Forest, Gradient Boosting, CatBoost, K-Nearest Neighbor, Naive Bayes, Support Vector Machine, and AdaBoost, with appropriate data preprocessing. The soft voting ensemble method, combining various models, achieved a notable 98.54% accuracy and 99% precision, recall, and f1-score, with Random Forest, CatBoost, and the Voting Classifier outperforming others. These results indicate that our model is highly reliable and sets a new standard for CVD prediction. Future research should focus on validating this model with larger datasets and exploring deep learning approaches.
Stock Price Forecasting with Multivariate Time Series Long Short-Term Memory: A Deep Learning Approach Furizal, Furizal; Ritonga, Asdelina; Ma’arif, Alfian; Suwarno, Iswanto
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22460

Abstract

Stocks with their inherent complexity and dynamic nature influenced by a multitude of external and internal factors, play a crucial role in investment analysis and trend prediction. As financial instruments representing ownership in a company, stocks not only reflect the company's performance but are also affected by external factors such as economic conditions, political climates, and social changes. In a rapidly changing environment, investors and analysts continuously develop models and algorithms to aid in making timely and effective investment decisions. This study applies a Sequential model to predict stock data using a LSTM neural network. The model consists of a single hidden LSTM layer with 200 units. The LSTM layer, the core element of this model, enables it to capture temporal patterns and long-term relationships within the data. The training and testing data were divided into 80% for training and 20% for testing. The Adam optimizer was chosen to optimize the model's learning process, with a learning rate of 0.001. Dropout techniques were applied to reduce overfitting, with a dropout rate of 0.4, along with batch normalization and ReLU activation functions to enhance model performance. Additionally, callback mechanisms, including ReduceLROnPlateau and EarlyStopping, were used to optimize the training process and prevent overfitting. The model was evaluated using MAE and MSE metrics on training, testing, and future prediction data. The results indicate that the model achieved high accuracy, with an MAE of 0.0142 on the test data. However, future predictions showed higher MAE values, suggesting room for improvement in long-term forecasting. The model's ability to accurately predict future stock closing prices can assist investors in making informed investment decisions.
Enhancing IoT Security: A Deep Learning and Active Learning Approach to Intrusion Detection Mahdi, Hawraa Fadel; Khadhim, Ban Jawad
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v%vi%i.22292

Abstract

In response to the escalating demand for robust security solutions in increasingly complex Internet of Things (IoT) networks, this study introduces an advanced Intrusion Detection System (IDS) leveraging both deep learning and active learning techniques. This research addresses the unique challenges posed by IoT environments, such as limited resources and diverse network components, which traditional security measures fail to adequately protect. Employing a BiLSTM model integrated with an active learning strategy, our approach achieved impressive results, including precision, recall, and F1-scores close to 1, and a total accuracy of 0.99. The inclusion of active learning enables the IDS to focus on the most informative data subsets, enhancing processing efficiency and reducing computational demands essential for IoT contexts. This method demonstrates significant promise for detecting sophisticated cyber threats and providing an effective tool for real-world applications. The performance of the proposed model has been rigorously validated on well-established cybersecurity datasets and through simulations in an IoT network environment, confirming its scalability and efficiency. Future work will address potential limitations such as computational demands and adaptability to diverse IoT device architectures, ensuring broader applicability and robustness of the IDS in varied IoT scenarios.
Towards Resilient Machine Learning Models: Addressing Adversarial Attacks in Wireless Sensor Network Shihab, Mustafa Abdmajeed; Marhoon, Haydar Abdulameer; Ahmed, Saadaldeen Rashid; Radhi, Ahmed Dheyaa; Sekhar, Ravi
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.23214

Abstract

Adversarial attacks represent a substantial threat to the security and reliability of machine learning models employed in wireless sensor networks (WSNs). This study tries to solve this difficulty by evaluating the efficiency of different defensive mechanisms in minimizing the effects of evasion assaults, which try to mislead ML models into misclassification. We employ the Edge-IIoTset dataset, a comprehensive cybersecurity dataset particularly built for IoT and IIoT applications, to train and assess our models. Our study reveals that employing adversarial training, robust optimization, and feature transformations dramatically enhances the resistance of machine learning models against evasion attempts. Specifically, our defensive model obtains a significant accuracy boost of 12% compared to baseline models. Furthermore, we study the possibilities of combining alternative generative adversarial networks (GANs), random forest ensembles, and hybrid techniques to further boost model resilience against a broader spectrum of adversarial assaults. This study underlines the need for proactive methods in preserving machine learning systems in real-world WSN contexts and stresses the need for continued research and development in this quickly expanding area.
Dynamic Motion Control of Two-Link Robots with Adaptive Synergetic Algorithms Abbas, Aya Khudhair; Kadhim, Saleem Khalefa
Journal of Robotics and Control (JRC) Vol 5, No 5 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i5.22985

Abstract

Robotics is advancing to assist with daily tasks by developing human-like robotic limbs, which involves challenges in integrating software, control systems, electronics, and mechanical designs. To address these challenges, Classic Synergetic Controller (CSC) and Adaptive Synergetic Controller (ASC) algorithms were created using mathematical equations to regulate the robot arm's joint angle position and achieve precise tracking. A comparison with Adaptive Sliding Mode Control (ASMC) and Classical Sliding Mode Control (CSMC) demonstrated that CSC and ASC outperform in efficiency and robustness. ASC improved by 63%, providing smoother angular position tracking and faster response times. CSC reached the desired position angle in 1.5 seconds with oscillations, while ASC achieved it in 2.4 seconds without oscillations and eliminated chattering. CSC's Root Mean Square (RMS) was 1.57 rad, whereas ASC had no RMS value. The improvement rate of ASC over CSC was 100%, ensuring seamless motion, better rise time, and eliminating oscillations, thus providing robust control against disturbances and parameter variations.

Page 2 of 3 | Total Record : 30

 1   2   3 

Filter by Year

2024 2024


Reset
Filter By Issues
All Issue Vol. 6 No. 5 (2025) Vol. 6 No. 4 (2025) Vol. 6 No. 2 (2025) Vol. 6 No. 1 (2025) Vol. 5 No. 6 (2024) Vol 5, No 6 (2024) Vol. 5 No. 5 (2024) Vol 5, No 5 (2024) Vol 5, No 4 (2024) Vol 5, No 3 (2024) Vol 5, No 2 (2024) Vol 5, No 1 (2024) Vol 4, No 6 (2023) Vol 4, No 5 (2023) Vol 4, No 4 (2023) Vol 4, No 3 (2023) Vol 4, No 2 (2023) Vol 4, No 1 (2023) Vol 3, No 6 (2022): November Vol 3, No 5 (2022): September Vol 3, No 4 (2022): July Vol 3, No 3 (2022): May Vol 3, No 2 (2022): March Vol 3, No 1 (2022): January Vol 2, No 6 (2021): November (Forthcoming Issue) Vol 2, No 6 (2021): November Vol 2, No 5 (2021): September Vol 2, No 5 (2021): September (Forthcoming Issue) Vol 2, No 4 (2021): July Vol 2, No 4 (2021): July (Forthcoming Issue) Vol 2, No 3 (2021): May Vol 2, No 3 (2021): May (Forthcoming Issue) Vol 2, No 2 (2021): March Vol 2, No 2 (2021): March (Forthcoming Issue) Vol 2, No 1 (2021): January Vol 1, No 6 (2020): November Vol 1, No 5 (2020): September Vol 1, No 4 (2020): July Vol 1, No 3 (2020): May Vol 1, No 2 (2020): March Vol 1, No 1 (2020): January More Issue