Association for Scientic Computing Electronics and Engineering (ASCEE): Open Journal Systems
Not a member yet
785 research outputs found
Sort by
Autonomous Mobile Robots Path Planning with Integrative Edge Cloud-Based Ant Colony Optimization
Full text linkIn recent years, Automated Mobile Robots (AMRs) have gained significant attention in industry and research applications, requiring efficient path-planning algorithms to optimize task performance. While widely adopted, conventional Ant Colony Optimization (ACO) algorithms suffer from low convergence rates and delays in task execution, particularly in dynamic environments due to insufficient exploration of this context. However, traditional Ant Colony Optimization (ACO) algorithms, widely used for AMR path planning, exhibit limitations such as low convergence rates and redundant recalculations, particularly in environments with frequently changing obstacles. To address these challenges, this study proposes an Integrative Edge Cloud-Based Ant Colony Optimization (IECACO) algorithm. IECACO incorporates a novel path retrieval mechanism and edge cloud computing infrastructure to minimize redundant path computation and improve convergence efficiency. The proposed algorithm is tested within a simulated 2D occupancy grid environment using both a 4×4 map for controlled experiments and a 20×20 map for comparative evaluation against a prior Improved ACO (IACO) study. Experimental simulation results, based on 50 independent runs in settings, demonstrate that IECACO achieves at least 4.76% reduction compared to traditional ACO. Based on the observation of 10 independent runs between IECACO and IACO, IECACO leading a significant reduction in both static and dynamic settings. Although this study is conducted in a simulated environment, the findings lay a foundation for future real-world implementations
Third-Order Sliding Mode Control of Five-Phase Permanent Magnet Synchronous Motor Using Direct Torque Control Based on a Modified SVM Algorithm
Full text linkDirect Torque Control (DTC) is a powerful method for multiphase drive systems, offering significant performance and efficiency gains, but its implementation is challenged by complexities like uncertainties and disturbances. This research addresses these issues, particularly the variable switching frequencies of hysteresis controllers with switching table and the limitations of conventional proportional-integral (PI) controllers in the outer loop, to enhance DTC for superior control in multiphase drives. The study proposes an improved DTC technique for a five-phase permanent magnet synchronous motor (5Ph-PMSM). This strategy integrates a robust nonlinear third-order super-twisting sliding mode control (TOSMC) with a modified space vector modulation (MSVM) algorithm. The MSVM is based on calculating the minimum and maximum of the five-phase voltages, contributing to optimized performance. This proposed DTC-TOSMC-MSVM approach significantly outperforms conventional DTC (DTC-Conv). It achieves tighter control, substantially reducing flux and torque ripple, and minimizing response time. Furthermore, it lowers the total harmonic distortion (THD) and improves disturbance rejection. The merits of the proposed strategy of 5Ph-PMSM are demonstrated through various tests. MATLAB simulations confirm these benefits, showing an 88.88% reduction in speed response time compared to DTC-Conv. Additionally, the proposed method reduces flux ripple by 51.85%, torque ripple by 63.15%, and stator current THD by 61.08%. In addition, the proposed method demonstrates robust performance when faced with changes in machine parameters and load disturbances, making it superior to traditional DTC approaches
Improved of Sliding Mode Control for Maximum Power Point Tracking in Solar Photovoltaic Applications Under Varying Conditions
Full text linkThe solar energy generation sector has received widespread interest compared to other types of sustainable energy generation. This is owing to its high efficiency and the availability of environmental factors essential to the operation of these systems in various parts of the world. However, increased the power extracted from these systems are a critical issue as their conversion efficiency is low. Therefore, a maximum power point tracking (MPPT) controller is necessary in a photovoltaic generation system (PV) for maximum power extraction. This study aims to explore the performance of the MPPT system that uses an improved sliding mode controller (SMC) to identify and track a maximum power point (MPP) of a PV system and compares it to synergetic algorithm control (SACT). To implementing this purpose, MATLAB/Simulink model of a stand-alone PV panel is developed. Then, the analysis of the performance efficiency of the PV system based on the proposed MPPT methods are implemented under varying environmental conditions. Being able to track the MPP perfectly in the case of a sudden change in environment conditions, the improved SMC is proven by the results to be superior in stabilizing the boost converter's operation, leading to enhanced PV system stability. This has led to a reduction in power losses and an increase in efficiency
Real-Time Pose Estimation for Autonomous Vehicles Using Probabilistic Landmark Maps and Sensor Fusion
Full text linkThis study introduces a robust and accurate method for estimating autonomous vehicle position, facilitating safe navigation in urban and highway settings. The proposed technique employs a probabilistic particle filter framework, which, unlike approaches constrained by Gaussian assumptions, represents probability densities as samples, enabling more flexible position estimation. A key innovation lies in integrating a finely tuned Unscented Kalman Filter (UKF) to fuse radar and lidar data specifically for robust detection of pole-like static landmarks, whose positions and associated uncertainties are probabilistically modeled within an offline reference map. The particle filter leverages Bayesian filtering, associating UKF-derived landmark observations with this probabilistic map to refine the vehicle's pose. Broad simulation tests validate the method's effectiveness, achieving a mean localization error of approximately 11 cm in both longitudinal and lateral directions. Furthermore, the system demonstrates robustness, maintaining localization accuracy below 30 cm even with landmark position uncertainties up to 2 meters, and confirms real-time capability exceeding 100 Hz. These findings establish the approach as a reliable and precise solution for autonomous vehicle localization across various scenarios
Fuzzy Dynamic Feedback Linearization for Efficient Mobile Robot Trajectory Tracking and Obstacle Avoidance in Autonomous Navigation
Full text linkMobile robots are increasingly used in various applications that require precise trajectory tracking and efficient obstacle avoidance. Dynamic Feedback Linearization (DFL) is powerful method, however, it’s has limitations such as increased computational requirements, model dependency, inability to avoid obstacles, and reduced robustness. In this paper, we address the challenges of trajectory tracking and obstacle avoidance for non-holonomic mobile robots in certain static environments subjected to the challenge of the robot to follow the reference trajectory accurately while avoiding the known obstacle in the trajectory of the robot by switching the two behaviors. The proposed scheme leverages the adaptive performance control to minimize the error between the reference and actual trajectories and avoid the static obstacle successfully. Firstly, the Dynamic Feedback Linearization (DFL) concept is used to develop an efficient tracking control system. Secondly, a Fuzzy Logic Controller (FLC) is used to avoid obstacles in the reference trajectory of the robot . Finally, the simulations are conducted using MATLAB software and the TurtleBot2 mobile robot within the 3D Gazebo simulator. According to the simulation results, the proposed approach cuts tracking accuracy and obstacle avoidance success rate by 93% and 95%, respectively. Additionally, experimental validation is carried out with the Adapt Mobilerobots Pioneer-3DX mobile robot, the results obtained from the Robot Operating System (ROS) prove the efficacy of the proposed approach for efficiency and precision
Indoor Quadcopter Localization Using Fuzzy-Sliding Mode Control for Robust Navigation
Full text linkGrowing demand for warehouse automation requires Unmanned Aerial Vehicles (UAVs), particularly quadcopters, to operate autonomously with a high level of precision and reliability. However, indoor localization poses unique challenges due to the absence of Global Positioning System (GPS) signals, making alternative sensors and robust control strategies essential. This study proposes an indoor UAV navigation system that integrates camera and LiDAR sensors with Fuzzy–Sliding Mode Control (Fuzzy-SMC) to enhance stability and reduce the chattering effects commonly associated with Sliding Mode Control. In the proposed method, the camera provides better accuracy for real-time position tracking compared to LiDAR, while fuzzy logic adaptively adjusts the Sliding Mode Control parameters, which serve as the main controller for stabilizing the quadcopter’s nonlinear dynamics. Research methodology includes mathematical modeling of the UAV quadcopter, the design of the Fuzzy-SMC controller, and simulation-based testing for trajectory tracking in indoor environments. Results show that the developed system achieves high accuracy, with error values ranging from 0 to 4.044%, remaining below the acceptable threshold of 5%. These findings demonstrate that integration of a camera with Fuzzy-SMC provides an effective and reliable solution for indoor quadcopter UAV navigation, while future research will focus on optimizing the fuzzy rule base and conducting hardware validation in real warehouse scenarios
ESI-YOLO: Enhancing YOLOv8 with Efficient Multi-Scale Attention and Wise-IoU for X-Ray Security Inspection
Full text linkSecurity inspection is a priority for preventing threats and criminal activities in public places. X-ray imaging can help with the closed luggages checking process. However, interpreting X-ray images is challenging due to the complexity and diversity of prohibited items. This paper proposes ESI-YOLO, an enhanced YOLOv8-based model for prohibited item detection in X-ray security inspection. The model integrates Efficient Multi-Scale Attention (EMA) and Wise-IoU (WIoU) loss function to improve multi-scale feature representation and detection accuracy. EMA improves multi-scale feature representation, while WIoU enhances bounding box regression, particularly in cluttered and overlapping scenarios. Comprehensive experiments on the CLCXray and PIDray datasets validate the effectiveness of ESI-YOLO. A systematic exploration for the optimal placement of EMA integration on YOLOv8 architecture reveals that the scenario with direct integration in both backbone and neck sections emerges as the most effective configuration without introducing significant computational complexity. Ablation experiments demonstrate the synergistic effect of combining EMA and WIoU in ESI-YOLO, outperforming individual component additions. ESI-YOLO demonstrates notable advancements over the baseline YOLOv8 model, achieving mAP50 improvements of 0.9% on CLCXray and 3.5% on the challenging hidden subset of PIDray, with a computational cost of 8.4 GFLOPs. Compared to other nano-sized models, ESI-YOLO exhibits enhanced accuracy while maintaining computational efficiency, making it a promising solution for practical X-ray security inspection systems
Classification of coronary heart disease using the multi-layer perceptron neural networks
Full text linkCoronary heart disease (CHD) is one of the leading causes of death worldwide. The complexity of risk factors such as blood pressure, cholesterol, smoking history, and unhealthy lifestyles often makes the diagnosis process less effective. With the increasing need for fast and accurate heart disease prediction systems, the use of artificial intelligence-based methods such as Neural Networks is a promising solution. This study aims to evaluate the ability of the Multi-Layer Perceptron (MLP) algorithm to classify CHD risk using the Framingham Heart Study dataset, while comparing it with other commonly used classification methods. This research used the collection of Framingham heart disease data containing 15 medical features. The data was then processed through cleaning, normalization, and class balancing using the SMOTE method. An MLP model was designed with two hidden layers using 200 and 128 neuron architectures, and tested in three training and testing data split scenarios (70:30, 75:25, and 80:20). The model was trained for 100 epochs and evaluated using accuracy, precision, and recall metrics to assess its classification performance. The experiment results show that MLP is able to produce high performance with 86.20% accuracy. 84.40% precision, and 88.56% recall. Compared to other methods such as Decision Tree and SVM, the experiment results show that MLP demonstrated superior classification accuracy. Thus, MLP has the potential to be an effective tool for supporting early diagnosis of coronary heart disease more intelligently and efficientl
Sustainable batik dyeing with ketapang (terminalia catappa) leaves: a practice-led experimental study on color retention and design innovation
No full textThis study investigates the batik production process through a focused experimental approach on three key aspects: motif exploration, technique application, and the use of natural dyes extracted from Ketapang leaves. Employing a practice-led research methodology, the experiments were conducted at Rumoh Batik Malaka in Aceh Besar Regency, Aceh Province, Indonesia. Data were collected via systematic observation, experimental trials, and comprehensive literature review. The color quality of batik samples was quantitatively assessed through RGB value analysis using grayscale imaging processed in MATLAB software. Results revealed that natural dyes derived from Ketapang leaves exhibit a measurable decline in color intensity when applied to batik textiles. Specifically, samples fixed with alum and calcium oxide and subjected to two dipping cycles showed significant fading, with grayscale values increasing from 0.5 to 0.7 post-wax removal (lorod). Conversely, optimal color retention was observed in samples fixed with ferrous sulfate and subjected to four dipping cycles, presenting minimal fading with values rising only from 0.1 to 0.2 after lorod. Six distinct batik pieces were produced, showcasing diverse motifs and color variations derived from the natural dye. The findings confirm that dye concentration and fixation type critically influence the colorfastness and aesthetic outcome, supporting the viability of Ketapang leaf extracts as sustainable natural dyes for cotton batik production. This research contributes to enriching batik design practices by promoting natural dye applications and innovative stamping techniques, offering ecological and cultural value to the textile arts in Indonesia and beyond
The role of self-efficacy in mediating the influence of social support on academic resilience among college students
Full text linkAcademic resilience is an increasingly relevant issue in the digital age, particularly as students face mounting academic demands alongside rapid technological advancement. Students who struggle to adapt to new technologies often experience heightened stress and reduced academic performance. This study investigates the mediating role of self-efficacy in the relationship between social support and academic resilience among university students. Employing a correlational causal design, the study surveyed 424 students from Pasuruan, East Java, selected through stratified random sampling. Data were collected using validated scales measuring perceived social support, self-efficacy, and academic resilience. Path analysis, supported by SPSS 22.0, revealed that self-efficacy significantly mediates the effect of social support on academic resilience (Sobel Z = 13.491, p 0.01). The indirect effect of social support through self-efficacy (β = 0.569) was notably stronger than the direct effect (β = 0.082), indicating that students' belief in their own abilities plays a more critical role in fostering resilience than external support alone. In essence, students with low self-efficacy may perceive themselves as incapable of overcoming academic challenges, even when supported by others. Conversely, those with high self-efficacy remain confident and persistent, even in the face of limited social support. These findings underscore the importance of strengthening both internal psychological resources and external support systems to enhance student resilience. Institutions should prioritize integrated interventions, combining peer support, counseling, and self-efficacy development, to foster adaptive coping mechanisms and long-term academic success