cover
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)
ISSN : 27155056     EISSN : 27155072     DOI : https://doi.org/10.18196/jrc
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.
Articles 35 Documents
Search results for , issue "Vol. 5 No. 6 (2024)" : 35 Documents clear
A Comprehensive Review of AI and Deep Learning Applications in Dentistry: From Image Segmentation to Treatment Planning Nambiar, Rajashree; Nanjundegowda, Raghu
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23056

Abstract

Deep learning leverages multi-layered neural networks to analyze intricate data patterns, offering advancements beyond traditional methods. This review paper explores the significant impact of deep learning on diagnostic and treatment processes across various dental specialties. In restorative dentistry, deep learning algorithms enhance the detection of dental caries and optimize the design of restorations. Orthodontics benefits from automated cephalometric analysis and personalized treatment planning. Periodontics utilizes deep learning for accurate diagnosis and classification of periodontal diseases, as well as monitoring disease progression. In endodontics, these technologies improve root canal detection and treatment outcome predictions. Prosthodontics and oral surgery leverage deep learning for precise prosthesis design and surgical planning, enhancing patient-specific care. Despite the promising advancements, challenges such as data quality, model interpretability, and regulatory issues persist. To solve these problems and get the most out of deep learning in dentistry, the review stresses the need for ongoing research and collaboration between different fields. In our review, we discuss significant deep learning models such as Convolutional Neural Networks (CNNs) and their applications in dentistry, including tooth segmentation, lesion detection, and orthodontic treatment planning. We also examine the use of Generative Adversarial Networks (GANs) for generating synthetic data to enhance training datasets. This paper reviews recent research to provide a comprehensive overview of how deep learning is transforming dentistry, leading to improved patient outcomes, diagnostic accuracy, and treatment efficiency. The advancements in AI and 3D imaging herald a future of automated, high-quality dental diagnostics and treatments.
Landing Control Based on Energy Prediction for a Quadcopter Under External Disturbances Nguyen, Cuong V.
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23074

Abstract

Unmanned aerial vehicles (UAVs) have recently become one of the most popular research topics. The high diversity in its uses has attracted research attention regarding structure or control capabilities. However, if the energy consumed in each mission cannot be predicted, the available flight time will pose many risks to the UAV and data security. This paper proposes a control algorithm based on predicting the remaining flight time to determine a safe landing station. Suppose the UAV cannot reach the desired destination station. In that case, it will find the nearest landing station to recharge its energy until the SoC (State of Charge) > 90%, then the UAV will continue to perform the mission until the UAV reaches the destination station. In addition, the paper uses a marker-based landing method to improve landing accuracy. The sliding mode controller (SMC) is designed to consider external disturbance factors and consider a solution to reduce chattering.
Trajectory Planning and Tracking Control for 6-DOF Yaskawa Manipulator based on Differential Inverse Kinematics Khoat, Ngo Xuan; Hoa, Cao Thanh Vinh; Khoa, Nguyen Bui Nguyen; Dung, Ngo Manh
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23109

Abstract

In the realm of robotics research, there is a strong focus on trajectory planning and control, driven by the increasing need to integrate robots across diverse industries. Drawing on the traditional Artificial Potential Field (for short, APF) method for path planning, the author proposes modifications on the force field calculation functions and time coefficients. These proposed functions improve the robot arm’s movement to better interact with identified obstacles, regardless of distance conditions. This will help reduce calculation time compared to traditional methods. The research aims to enhance the operational system of the manipulator by developing an external program that interfaces with the central controller. The program guides the robot arm to follow a specific path using the Differential Inverse Kinematics (for short, DIK) method to ensure the smoothness of trajectory tracking. Facing the issue of the invertibility of the Jacobian matrix, the research team addressed it by adding a Moore–Penrose right pseudoinverse of the Jacobian and avoiding the shock velocity around the singularity using a Damping Constant technique. In this research, the proposed APF is validated and compared to the traditional method using MATLAB. The DIK method utilizes the optimal path from previous to control the Yaskawa MotoMINI manipulator - the physical robot arm system.
Overvoltage and Oscillation Analysis for a Full-Bridge Isolated DC-DC Converter Avdeev, Boris A.; Vyngra, Aleksei V.; Zhilenkov, Anton A.; Chernyi, Sergei G.; Degtyarev, Andrey; Kustov, Aleksandr; Zinchenko, Anton
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23120

Abstract

The paper deals with determining and eliminating overvoltage’s and ripples from the output of a high-frequency inverter bridge in a full-bridge DC converter. These oscillations can cause overvoltage on the elements of the power converter, which in turn can lead to false triggering of semiconductor keys or their failure. Schematic diagrams of the bridge are given; the principle of its operation is described. A simplified equivalent circuit replaces the classic bridge. A qualitative analysis of transient processes in the resulting scheme is made. The voltage at the output of the bridge is found using the operator method. The findings have been compared with the simulation model executed in MATLAB/Simulink. The presented method is less labor-intensive than simulation modeling and allows for faster and easier verification of the permissible overvoltage level and oscillation frequency, which is especially important in devices containing a large number of nonlinear elements. It is shown how the parameters of the bridge affect the performance of the transient, in particular the overshoot and oscillation frequency. The attained dependencies are shown in graphical form. The ways of improving the quality of the transition process are given. The findings have been verified on an experimental setup. The obtained theoretical results are consistent with the results of the experiment with the data of other researchers.
Design and Analysis of a Hybrid Intelligent SCARA Robot Controller Based on a Virtual Reality Model Al Mashhadany, Yousif; Abbas, Ahmed K.; Algburi, Sameer; Taha, Bakr Ahmed
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23158

Abstract

SCARA robots have been used in various fields of robotics, such as biomedical engineering, automation, industrial, and gaming. However, our SCARA (Selective Compliance Assembly Robot Arm) VR model stands out with its realistic design and construction assumptions. The VR testing of the robot's motion envelope has facilitated a more precise inverse kinematics solution and verification of the dynamic process. The intelligent controller of this application, based on the Adaptive Neuro-Fuzzy Inference System (ANFIS) technique and a classical proportional-integral-derivative (PID) controller, offers an optimized solution to the accuracy problem. The hybrid ANFIS controller starts with the PID setting parameters of the resultant solution. Following thorough testing of the suggested SCARA manipulator with an intelligent controller in a virtual reality environment, researchers recognized the physical system's potential for implementation utilizing multiple control approaches. Despite the intricacy of its design and implementation, the intelligent controller's software ensures that the system runs at top efficiency. This application replicates the user interface of the MATLAB/SIMULINK var (2022b), which produced promising robotics results, demonstrating its trustworthiness as a realistic, intelligent model, and virtual reality was critical in the development of the SCARA manipulator. It digs into the design and analysis of a hybrid intelligent controller for SCARA robots, which are widely used in assembly lines and manufacturing. Finally, the proposed controller combines the best features of an Adaptive Neuro-Fuzzy Inference System (ANFIS) with a conventional proportional-integral-derivative (PID) controller to resolve application accuracy difficulties as efficiently as possible. 
Enhanced Dynamic Control of Quadcopter PMSMs Using an ILQR-PCC System for Improved Stability and Reduced Torque Ripples Saleh, Ziyaad H.; Mejbel, Basim Ghalib; Radhi, Ahmed Dheyaa; Hashim, Abdulghafor Mohammed; Taha, Taha A.; Gökşenli, Nurettin; Hussain, Abadal-Salam T.; Sekhar, Ravi
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23159

Abstract

Quadcopter technology has developed fast because it’s flexibility and capacity for high maneuvers. What makes PMSM suitable for Quadcopter is their high power to weight ratio, reliability and efficiency. These motors allow the operation of torque and speed control which are important for stability and maneuverability in the flight of the aircraft. Nevertheless, certain and smooth flight caused by regulation of PMSM speed and current is necessary for stable and maneuverable movement. This work presents a new control strategy connecting the ILQR control to govern the speed while the PCC profit the dynamic response and control torque ripples. A comparison is made on the performance of the ILQR-PCC system with nominal Proportional-Integral (PI) control and ILQR.  From the results it is evident that the ILQR-PCC system is far superior to both the PI & ILQR controller in regards to the dynamic response, the disturbances rejection capacity as well as reducing the current signal distortions hence reducing the torque ripples. Its working was evidenced in a nonlinear LQR-controlled quadcopter to track the reference accurately and to have minimum distortion in current regulation. The presented work improves the control systems of quadcopters: it introduces a reliable method that improves stability and increases the performance of the quadcopter; therefore, this paper contributes to the existing knowledge.
Enhanced Stacked Ensemble-Based Heart Disease Prediction with Chi-Square Feature Selection Method Sarra, Raniya R.; Gorial, Ivan Isho; Manea, Reham Raad; Korial, Ayad E.; Mohammed, Mustafa; Ahmed, Yousif
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23191

Abstract

Heart disease (HD) is the primary cause of death globally, requiring more accurate, affordable diagnostic technologies. Traditional HD diagnostic methods are adequate but expensive and limited, creating a need for creative alternatives. Machine learning (ML) is one of the many sophisticated technologies healthcare systems use to predict diseases. This work aims to enhance the accuracy and efficiency of HD diagnosis by developing a stacked ensemble classifier that combines predictions from different ML classifiers and uses chi-square feature selection to prioritize significant features. Combining predictions from three basic ML classifiers—decision trees (DT), support vector machines (SVM), and multilayer perceptron (MLP)—the paper creates a stacked ensemble classifier. To raise diagnostic accuracy, this stacked ensemble classifier maximizes the strengths of base classifiers and reduces their errors. Furthermore, applying the chi-square feature selection approach, the study finds five important features for training the classifiers on the Cleveland dataset with thirteen (13) features. Selecting only important features through feature selection minimizes dimensionality, simplifies the classifier, and improves computational performance. This also reduces overfitting, increases generalizability, and speeds up diagnosis, making it more viable for real-time clinical applications. Before and following the feature selection procedure, the ensemble classifier performance is assessed against the base classifiers concerning the accuracy, recall, precision, and f1-score. These metrics are chosen for their ability to validate the effectiveness of the proposed diagnostic tool.  With an accuracy of 85.5%, the stacked ensemble classifier exceeded base classifiers before feature selection. After feature selection, the stacked ensemble classifier’s accuracy improved to 90.8%. These results underline the proposed method as an inexpensive and more efficient diagnostic tool for HD as compared to current methods, enabling earlier HD detection and lowering healthcare costs. In conclusion, this creative method could alter healthcare systems by providing a highly accurate and affordable diagnostic tool for clinical use.
On New Results of Stability and Synchronization in Finite-Time for Fitiz-Nagamo Model Using Grownal Inequality and Lyapunov Function Batiha, Iqbal M.; Bendib, Issam; Ouannas, Adel; Jebril, Iqbal H.; Alkhazaleh, Shawkat; Momani, Shaher
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23211

Abstract

Ionic diffusion across cytomembranes plays a critical role in both biological and chemical systems. This paper reexamines the FitzHugh-Nagumo reaction-diffusion system, specifically incorporating the influence of diffusion on the system’s dynamics. We focus on the system’s finite-time stability, demonstrating that it achieves and maintains equilibrium within a specified time interval. Unlike asymptotic stability, which ensures long-term convergence, finite-time stability guarantees rapid convergence to equilibrium, a crucial feature for real-time control applications. We prove that the equilibrium point of the FitzHugh-Nagumo system exhibits finite-time stability under certain conditions. In particular, we provide a criterion for finite-time stability and derive results using new lemmas and a theorem to guide the system’s design for reliable performance. Additionally, the paper discusses finite-time synchronization in reaction-diffusion systems, emphasizing its importance for achieving coherent dynamics across distributed components within a finite time. This approach has significant implications for fields requiring precise control and synchronization, such as sensor networks and autonomous systems. Practical simulations are presented to elucidate the theoretical principles discussed earlier, using the finite difference method (FDM) implemented in MATLAB.
Computational Approaches to Two-Energy Group Neutron Diffusion in Cylindrical Reactors Batiha, Iqbal; Abdelnebi, Amira; Shqair, Mohammed; Jebril, Iqbal H.; Alkhazaleh, Shawkat; Momani, Shaher
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23392

Abstract

This study addresses the critical need for accurate neutron diffusion modeling in cylindrical reactors, focusing on the two-energy groups neutron diffusion system. Such modeling is essential for optimizing reactor design and safety in nuclear engineering. The research primarily aims to enhance computational methods by transitioning from a traditional integer-order model to a more sophisticated fractional-order model, which can capture complex physical phenomena with greater precision. The study employs the Laplace Transform Method (LTM) to first solve the integer-order system and then extends this approach to a fractional-order system using the Caputo derivative, a method well-suited for systems with memory effects. To efficiently solve the resulting fractional-order model, we introduce the Modified Fractional Euler Method (MFEM), designed to improve numerical accuracy and stability. The effectiveness of this approach is demonstrated through specific numerical applications, such as simulating neutron flux distributions, which validate the model’s accuracy and its potential impact on advancing reactor physics. These applications showcase the practical relevance of the proposed methods and their contribution to improving nuclear reactor simulations.
Enhancing Voice Authentication with a Hybrid Deep Learning and Active Learning Approach for Deepfake Detection Ahmed, Ali Saadoon; Khaleel, Arshad M.
Journal of Robotics and Control (JRC) Vol. 5 No. 6 (2024)
Publisher : Universitas Muhammadiyah Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.18196/jrc.v5i6.23502

Abstract

This paper explores the application of active learning to enhance machine learning classifiers for spoofing detection in automatic speaker verification (ASV) systems. Leveraging the ASVspoof 2019 database, we integrate an active learning framework with traditional machine learning workflows, specifically focusing on Random Forest (RF) and Multilayer Perceptron (MLP) classifiers. The active learning approach was implemented by initially training models on a small subset of data and iteratively selecting the most uncertain samples for further training, which allowed the classifiers to refine their predictions effectively. Experimental results demonstrate that while the MLP initially outperformed RF with an accuracy of 95.83% compared to 91%, the incorporation of active learning significantly improved RF's performance to 94%, narrowing the performance gap between the two models. After applying active learning, both classifiers showed enhanced precision, recall, and F1-scores, with improvements ranging from 3% to 5%. This study provides valuable insights into the role of active learning in boosting the efficiency of machine learning models for dynamic spoofing scenarios in ASV systems. Future research should focus on designing advanced active learning techniques and exploring their integration with other machine learning paradigms to further enhance ASV security.

Page 2 of 4 | Total Record : 35