Association for Scientic Computing Electronics and Engineering (ASCEE): Open Journal Systems
Not a member yet
785 research outputs found
Sort by
High Gain Observer Based Backstepping Control Design for Nonlinear Single-Axis Driven Systems
Full text linkIn this paper, a backstepping (BS) control design approach is proposed for tracking angular position control problem of a single-input and single-output (SISO) nonlinear single-axis driven system. To implement proposed BS control, the states of the system should be available. To address this problem, a high gain observer (HGO) is introduced for estimating the states. The design parameters of the HGO based BS controller have been optimized using the circle search algorithm (CSA). Compare to other optimization algorithm, the CSA explores the search space in a circular trajectory which can enhance local exploitation. The CSA uses integral of absolute error (IAE) as the performance index for the tuning process. The effectiveness of the proposed controller is demonstrated through simulations. Firstly, for observer evaluation, simulation outcomes indicate that the HGO is capable to estimate the states of the system successfully. However, to evaluate the BS with other nonlinear controllers for tracking control problem, the synergetic (SG) control is proposed. The simulated data results based on IAE index revealed that the BS control has lower IAE value than the SG control where the value of the IAE of the system with the BS control is reduced by 19.4% in compares with the system with the SG control
Disturbance Observer-Based Intelligent Control for Trajectory Tracking in Redundant Robotic Manipulators
Full text linkRedundant robotic manipulators require advanced control strategies to maintain stability and precision in the presence of dynamic disturbances. This study proposes an intelligent control scheme integrating Active Force Control (AFC) with a Proportional–Integral–Derivative (PID) controller to enhance the performance of a two-degree-of-freedom (2-DOF) robotic manipulator. The proposed AFC-PID controller is designed to suppress the effects of external disturbances, including torque noise. Comparative simulations demonstrate that the AFC-PID approach outperforms the conventional PID controller, providing improved stability and tracking accuracy in both manipulator links. Moreover, it compared with the Sliding Mode Control (SMC) control to verify the efficiency of the proposed controller. Quantitatively, the Integral Square Error (ISE) improvements compared to PID for link 1 and link 2 are 82.83% and 65.57%, respectively. Under disturbance conditions, performance gains are also observed, with ISE reductions of 86.2% and 65.36% for links 1 and 2. These results confirm the robustness and effectiveness of the proposed controller in maintaining consistent performance under challenging conditions. This is a significant improvement, reflecting the superiority over the conventional systems
Impact of Hyperparameter Tuning on ResNet-UNet Models for Enhanced Brain Tumor Segmentation in MRI Scans
Full text linkBrain tumor segmentation in MRI scans is a crucial task in medical imaging, enabling early diagnosis and treatment planning. However, accurately segmenting tumors remains a challenge due to variations in tumor shape, size, and intensity. This study proposes a ResNet-UNet-based segmentation model using LGG dataset (from 110 patients), optimized through hyperparameter tuning to enhance segmentation performance and computational efficiency. The proposed model integrates different ResNet architectures (ResNet18, ResNet34, ResNet50, ResNet101, and ResNet152) with UNet, evaluating their performance under various learning rates (0.01, 0.001, 0.0001), optimizer types (Adam, SGD, RMSProp), and activation functions (Sigmoid). The methodology involves training and evaluating each model using Loss Function, Mean Intersection over Union (mIoU), Dice Similarity Coefficient (DSC), and Iterations per Second as performance metrics. Experiments were conducted on MRI brain tumor datasets to assess the impact of hyperparameter tuning on model performance. Results show that lower learning rates (0.0001 and 0.001) improve segmentation accuracy, while Adam and RMSProp outperform SGD in minimizing segmentation errors. Deeper models (ResNet50, ResNet101, and ResNet152) achieve the highest mIoU (up to 0.902) and DSC (up to 0.928), but at the cost of slower inference speeds. ResNet50 and ResNet34 with RMSProp or Adam provide an optimal trade-off between accuracy and computational efficiency. In conclusion, hyperparameter tuning significantly impacts MRI segmentation performance, and selecting an appropriate learning rate, optimizer, and model depth is crucial for achieving high segmentation accuracy with minimal computational cost
Enhancing the Performance of Grid-Tied Renewable Power Systems Using an Optimized PI Controller for STATCOM
Full text linkIntegrating electrical networks with renewable energy sources in hybrid systems may effectively meet increasing power demands while reducing reliance on traditional energy sources. Wind gusts in wind energy conversion systems (WECSs), along with variations in temperature and irradiance in photovoltaic (PV) systems, render these systems vulnerable. Three-phase faults at the point of common coupling (PCC) can disconnect renewable energy sources (RESs) from the grid, threatening system stability. This study enhances a hybrid PV-WECS system through the implementation of a static synchronous compensator (STATCOM) to mitigate wind gust effects and maintain RES connectivity during three-phase faults at the point of common coupling (PCC). STATCOM manages reactive power exchange between renewable energy sources and the grid through two PI controllers. The gains of the PI controller are optimized through elephant herding optimization (EHO), demonstrating superior performance compared to particle swarm optimization (PSO) in terms of PCC voltage stability and system efficiency. In three-phase faults, the EHO demonstrates superior performance over the PSO, achieving a PCC voltage of 0.7 in contrast to 0.37, thereby maintaining voltage levels within acceptable limits in the connecting zone according to grid codes. The EHO-optimized PI controllers for the STATCOM successfully reduce the SRG current during this fault, decreasing it from 155 (with PSO) to 111 (with EHO). Under wind gust conditions, the power profile obtained from the SRG is markedly enhanced when employing EHO in comparison to PSO
Intelligent Temperature-Controlled Poultry Feed Dispensing System with Fuzzy Logic Algorithm
Full text linkThis study introduces a novel fuzzy logic algorithm tailored to the thermoneutral zone of poultry, offering a precise and adaptive approach to feed dispensation. This involved the utilization of an LCD module to present essential information such as the selected age, real-time ambient temperature, current time, and the dispensed feed quantity. Data gathered during the process were stored in a memory device. The design of the fuzzy logic algorithm centered on the thermoneutral zone of the chicken serves as the determinant for feed dispensed by the system. It's crucial to note that while the system lacked artificial intelligence (AI), its logical analysis operated based on the fuzzy logic algorithm. Rigorous testing ensued, encompassing the comparison of feed dispensation between automated and manual systems and the assessment of feed waste and broiler weight. Significant feed waste reduction in the first week demonstrated the efficacy of the fuzzy-based method, with consistently low p-values of 0.00069, 0.015195, and 0.034 across subsequent weeks confirming the consistent outperformance in broiler weight compared to the traditional feeding technique. The findings contribute to the advancement of temperature-based poultry feed systems, addressing key challenges in optimizing feed quantity. The study successfully met its objectives, demonstrating the system's capability to dispense feeds effectively across varying ambient temperatures. Notably, the study revealed a consistent alignment of system outputs with those obtained from a digital thermometer and digital weighing scale, confirming the accuracy and reliability of the temperature-based feed dispensing system
Classification Of Plants By Their Fruits And Leaves Using Convolutional Neural Networks
Full text linkThe population growth of the world is exponential, this makes it imperative that we have an increase in food production. In this light, farmers, industries and researchers are struggling with identifying and classifying food plants. Over the years, there have been challenges that come with identifying fruits manually. It is time-consuming, labour intensive and requires experts to identify fruits because of the similarity in fruit’s leaves (citrus family), shapes, sizes and colour. A computerized detection technique is needed for the classification of fruits. Existing solutions to fruits classifications are majorly based on fruit or leave used as input. A new model using Convolutional Neural Network (CNN) is proposed for fruits classification. A dataset of 5 classes of fruits and fresh dry leaves plants (Mango, African almond, Guava, Avocado and Cashew) comprising of 1000 images each. The proposed model hyperparameters were: Conv2D layer, activation layer, dense layer, a learning and dropout rates of 0.001 and 0.5 respectively were used for the experiment. Various performances for accuracies of 91%, 97%, 78% and 97% were obtained for proposed model on local dataset, proposed model on benchmark dataset, benchmark model on local dataset and benchmark model on benchmark dataset. The proposed model is robust on both local and benchmark datasets and can be used for effective classification of plant
Intergenerational communication in song “Saat Kau Telah Mengerti†with Hjelmslev’s semiotic perspective
Full text linkThe song “Saat Kau Telah Mengerti†(lit. “When You Have Understoodâ€), recorded by Virgoun, was streamed over a million times on YouTube when it was released in January last year and has been circulated in various edited versions on various online platforms. The lyrics present messages of hopes and wishes from parents to their children, thus touching the hearts of its listeners. Through the song's music, lyrics, and video clips, the objective of this research is to interpret and explore the meaning of parents' communication with their children. This study focuses its research question on elements utilized in the lyrics, music, and video clips of the song. This research analysis uses a qualitative approach with an interpretative paradigm based on Louis Hjelmslev's semiotic method and the validity test, which will be achieved through triangulation. Through Hjelmslev's semiotic research on forms and substance of expression and content, this research found that a communication gap exists between parents and their children. The gap stems from the generational differences between fathers and daughters, which this song seeks to bridge by encouraging the child to empathize with the parents. The actions of parents who strive for their children's benefit can occasionally be misinterpreted by their children as something negative. Based on the results, the study recommends music as an effective tool for conveying messages to mitigate parent-child communication ga
School principals' implementation of institutional talent management for teachers
Full text linkThe domain of educational leadership has progressively acknowledged the significance of institutional talent management in promoting teacher development and improving overall educational results. The domain of educational leadership has progressively acknowledged the significance of institutional talent management in promoting teacher development and improving overall educational outcomes. This research paper aims to explore and evaluate the degree to which school principals in Jordan engage in institutional talent management practices for teachers. Institutional talent management is a crucial aspect of educational leadership that can significantly impact the professional growth and performance of teachers. The study investigates the current state of talent management in Jordanian schools, identifies the prerequisites for successful implementation, and examines the challenges faced within the existing educational system. Generally, most participants saw that there is no specific system for talent management at the education system
Investigating the Influence of Temperature on UAV Signal Quality
Full text linkAdvancements in drone technology make them important in many areas. military, industry, and disaster The efficacy of a drone's communication systems can be greatly impacted by temperature fluctuations, either from environmental conditions or mechanical problems in the drone's construction. This study gives an analysis and computational model of the impact of temperature on the performance of drone communication. Utilizing a one-dimensional convolutional neural network, we aim to forecast the signal-to-noise ratio (SNR) and received signal strength indicator (RSSI). Following the initial stage of dataset creation in the drone laboratory, proceed to reprocess the dataset and divide it into a 70% training set and a 30% testing set. Subsequently, a graphical user interface (GUI) was developed using MATLAB App Designer to enhance user friendliness. The outcome suggests that the efficiency of the drone communication system  declines with rising temperatures.  Using 1DCNN is our contribution to this work; other studies depend only on simulation to assess performance. One benefit of 1DCNN is that the impact may be evaluated by automatically extracting important features from the input dataset. Using 1DCNN is our special addition to this project; other research evaluate the UAV communication system's effectiveness only through simulation. We propose in this work to optimize system characteristics for improved performance, including power transfer, by adding a feedback loop between the CNN result and the communication system. Furthermore, we investigate how different weather conditions, such wind and rain, affect UAV communication systems
Predictive Modeling of Energy Consumption in the Steel Industry Using CatBoost Regression: A Data-Driven Approach for Sustainable Energy Management
Full text linkThis article presents a machine learning model for predicting energy consumption in the steel industry, which aids in energy management, cost reduction, environmental regulation compliance, informed decision-making for future energy investments, and contributes to sustainability. The dataset used for the prediction model comprises 11 attributes and 35,040 instances. The CatBoost prediction algorithm was employed for energy consumption prediction, and hyperparameter optimization was performed using GridSearchCV with 5-fold cross-validation. The developed model has undergone a comparative analysis based on both Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) metrics, demonstrating its promise for accurate energy consumption prediction on both the training and test sets. The proposed model accurately predicts energy consumption for different load types, achieving impressive results on both the training set (RMSE=0.382, R2=0.999, MAPE=1.139) and the test set (RMSE=1.073, R2=0.998, MAPE=1.142). These findings highlight the potential of CatBoost as a valuable tool for energy management and conservation, enabling organizations to make informed decisions, optimize resource allocation, and promote sustainability