Association for Scientic Computing Electronics and Engineering (ASCEE): Open Journal Systems
Not a member yet
785 research outputs found
Sort by
Ensemble learning approaches for predicting heart failure outcomes: A comparative analysis of feedforward neural networks, random forest, and XGBoost
Full text linkHeart failure is a leading cause of morbidity and mortality worldwide, and early prediction of outcomes is critical for timely intervention and improved patient care. Accurate prediction models can help clinicians identify high-risk patients, optimize treatment strategies, and reduce healthcare costs. In this study, we developed and evaluated machine learning models to predict mortality in patients with heart failure using a medical dataset of 299 patients with 13 clinical variables collected in 2015. Four models were tested, including a Feedforward Neural Network (FNN), Random Forest, XGBoost, and an ensemble model combining all three models. The experimental process included data preprocessing, feature scaling, and stratified cross-validation to ensure robust evaluation. The results showed that the ensemble model achieved the best performance with an ROC-AUC of 0.9134 and an F1 score of 0.7439, outperforming individual models such as Random Forest (ROC-AUC: 0.9117) and XGBoost (ROC-AUC: 0.9130). FNN, despite having the highest accuracy (0.8455), showed lower performance in terms of recall and precision, likely due to its sensitivity to overfitting on small datasets. These results highlight the effectiveness of ensemble learning in medical prediction tasks, especially for handling complex, high-dimensional health data. The proposed ensemble model has the potential to be integrated into clinical decision support systems, enabling real-time risk assessment and personalized treatment plans for heart failure patients. Future research should explore larger, multicenter datasets, incorporate advanced feature engineering techniques, and investigate the integration of deep learning architectures such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs) to process sequential data such as ECG signals
Automated Water Cooling and Solar Tracking for Efficiency Improvement of PV Systems: A Systematic Review
Full text linkThis article presented previous efforts for overcoming low photovoltaic (PV) solar panel electrical efficiencies resulted from excess heat problem reached in hot climates. Utilizing water cooling, temperature-controlled water cooling and solar tracking solar systems are discussed in this paper. Water is a perfect medium can be used for absorbing excess heat due to its high thermal capacity, availability and low cost. In addition to, utilizing control systems for water cooling systems based on Arduino unit and microcontroller chip which can be interfaced with Bluetooth, WIFI, and Internet of Things (IOT) enhances saving time and effort in large PV solar plants and PV performance. Solar tracking systems, depend on light-dependent resistors (LDRs) which are resistors operated by incident light, or ultraviolet (UV) sensors which are detectors based on incident ultraviolet radiation sensing enhances PV performance. Solar tracking systems enhances PV electrical efficiency compared to fixed PV panels. PV efficiencies of latest studies were presented and compared. Utilizing water cooling systems enhances PV electrical efficiency up to 30%, using an ON-OFF temperature-controlled water-cooling systems increased overall efficiency up to 51.4% and can reduce consumption of water up to 29.28%. In addition to, using two solar tracking systems enhances PV solar panel efficiency up to 65%. The increase in PV installation faces challenges includes millions of solar waste tons that harms environment and human health. However, it can be eliminated utilizing recycling technologies. Artificial intelligence (AI), machine learning techniques would enhance PV performance analyzing and data collection
A Technological Review on Fast Chargers for Electric Vehicles: Standards, Architectures, Power Converter Topologies, Fast Charging Techniques, Impacts and Future Research Directions
Full text linkWithin a universe in which concerns about petroleum resources depletion and ecological issues are increasing, the technological evolution of electric mobility has quickened to overcome these concerns. Vehicle electrification technology is seen as a promising and viable substitute for prospective transport systems. Electric vehicles (EVs) offer a solution for reducing the reliance on fossil fuels, improving air quality, integrating easily with renewable energies, and enhancing energy efficiency, especially when smart grids have become omnipresent. However, range anxiety and long charging times remain substantial barriers to the extensive embrace of these vehicles, impeding a seamless shift from conventional vehicles to EVs. Reducing EV recharging time is considered a pivotal element in promoting consumer interest and increasing their market appeal. Thus, EV commercial deployment relies heavily on the presence of an adequate fast-charging infrastructure. Fast-charging infrastructure will decrease drivers' wait times for vehicle charging, providing a refueling experience like that of gasoline vehicles. Hence, a significant portion of research efforts have been dedicated to the advancement of fast chargers (FCs) designed to rapidly recharge EV batteries. It is crucial to opt for the appropriate power electronic interfaces for these chargers to avoid possible grid-related issues and improve overall system efficiency. This review is concentrated on presenting pertinent information regarding EV FCs, including various standards, architectures, power converter topologies, compatible battery chemistries, and fast-charging techniques. Finally, the significant impacts of the integration of fast-charging with both the AC grid and traction batteries are presented in detail.Â
Design and Quality Evaluation of the Position and Attitude Control System for 6-DOF UAV Quadcopter Using Heuristic PID Tuning Methods
Full text linkNowadays, UAV quadcopters are widely used in many fields, specially in transporting the lightweight goods parcels. This article aims to design and evaluation of the quality of the 6-DOF UAV quadcopter control system using heuristic PID tuning methods to ensure stable control of flight position and attitude. Firstly, the article presents the dynamic mathematical model of the 6-DOF UAV quadcopter, including 3 Euler angle variables and 3 flight position and altitude variables. From there, the article proposes the 6-DOF UAV control syste structure with two single control loops for flight attitude, yaw angle and two dual control loops for roll-pitch angles, flight position. And then, the article presents the application of the heuristic PID tuning methods to each control loop of a 6-DOF UAV quadcopter to calculate the PID controller parameters to ensure stable control the desired flight position and altitude. The simulation results and evaluating the 6-DOF UAV quadcopter control system quality in Matlab, using the proposed heuristic PID controllers, show that the PID controllers according to the Tyreus-Luyben method gives the best quality, with a steady-state error of less than 1%. The main contribution of this article is the comparative analysis of three heuristic PID tuning methods - Ziegler-Nichols, Tyreus-Luyben, PID tuner - for controlling the position and attitude of a 6-DOF UAV quadcopter. Â These findings demonstrate that the proposed PID controllers can be effectively implemented in practical UAV applications, enhancing the stability and performance of quadcopters in various fields
Enhanced Hybrid Robust Fuzzy-PID Controller for Precise Trajectory Tracking Electro-Hydraulic Actuator System
Full text linkThe Electro-Hydraulic Actuator (EHA) system integrates electrical and hydraulic elements, enabling it to generate a rapid reaction, a high power-to-weight ratio, and significant stiffness. Nevertheless, EHA systems demonstrate non-linear characteristics and modeling uncertainties, such as friction and parametric uncertainty. Designing a controller for accurate trajectory tracking is greatly challenging due to these limitations. This paper introduces a hybrid robust fuzzy proportional-integral-derivative (HFPID) and (HF+PID) controller. The controller is designed to effectively control a third-order model of an EHA system for trajectory tracking. It is a significant contribution to the development of an intelligent robust controller that can perform well in different environments. Initially, a mathematical model for the EHA system was created using a first-principle approach. Subsequently, the Ziegler-Nichols method was employed to fine-tune the PID controller, while a conventional Fuzzy Logic Controller (FLC) was constructed in MATLAB Simulink utilizing linguistic variables and rule-based control. Without further tuning, the FL and PID controller are combined as a hybrid controller with different structures: Hybrid Fuzzy-PID (HFPID) and Hybrid Fuzzy+PID (HF+PID) controller. The Mean Square Error (MSE) and Root Mean Square Error (RMSE) are utilized as indices to assess the tracking accuracy and robustness of the four controllers. A greater value of MSE and RMSE indicates poorer performance of the controller. The results demonstrate that the HF+PID controller surpasses the other controllers by reaching the lowest MSE and RMSE values. It showcases the efficacy and accuracy in monitoring sinusoidal, multi-sinusoidal, and point-to-point trajectory tracking. Â Future work should focus on implementing the designed controller on hardware for real-time performance and experimenting with various types of FLC or Hybrid controllers, such as self-tuning fuzzy-PID, to further explore their potential
Comparison of Convolutional Neural Networks and Support Vector Machines on Medical Data: A Review
Full text linkMedical image processing has become an integral part of disease diagnosis, where technological advancements have brought significant changes to this approach. In this review, a comprehensive comparison between Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) in processing medical images is conducted. Automated medical analysis is becoming increasingly important due to issues of subjectivity in manual diagnosis and potential treatment delays. This research aims to compare the performance of Machine Learning (ML) in medical contexts using MRI, CT scan, and X-ray data. The comparison includes the accuracy rates of CNN and SVM algorithms, sourced from various studies conducted between 2018 and 2022. The results of the comparison show that CNN has higher average accuracy in processing MRI and X-ray data, with average values of 98.05% and 97.27%, respectively. On the other hand, SVM exhibits higher average accuracy for CT scan data, reaching 91.78%. However, overall, CNN achieves an average accuracy of 95.58%, while SVM's average accuracy is at 94.72%. These findings indicate that both algorithms perform well in processing medical data with high accuracy. Although based on these average accuracy rates, CNN demonstrates slightly better capabilities than SVM. Further research and development of more complex models are expected to continue improving the effectiveness of both approaches in disease diagnosis and patient care in the future
Development of a Sensor-Based Glove-Controlled Mobile Robot for Firefighting and Rescue Operations
Full text linkRobots are important in preventing hazards. This paper presents the construction and testing of a mobile robot equipped with a sensor-based glove for firefighting and rescue operations. The main idea is based on the ability to control the mobile robot through the movement of a gloved hand. The glove circuit is connected to the robot circuit through Bluetooth. The MPU6050 gyroscope sensor detects the movement of a gloved hand and sends the direction of the hand’s inclination to the microcontroller, which in turn uses this information to direct the mobile robot’ movement in the desired direction. Experiments were conducted to test the mobile robot and its control system. Results showed that the robot prototype works effectively with satisfactory response to the intended direction of robot movement. An increase in safety level and a reduction in firefighting risks were also observed. The proposed robot can assist effectively in rescue operations, creating opportunities for future improvements
“The teacher did not explain the lesson, just giving us a taskâ€: Self-reflections of pre-service English teachers in an online learning mode
Full text linkIn the post-pandemic era, online learning has been the focus of many educational institutions nowadays, including English as a foreign language classes. However, with the current rapid changes in online learning, little attention has been paid to uncovering the self-reflection of pre-service English teachers in learning English online. This brief report seeks to construe how three Indonesian pre-service English teachers negotiate the meaning of their past learning experiences in English as a foreign language classes during the online learning mode. We employed a narrative inquiry in this study in order to capture the participants’ experiences. Data were garnered through WhatsApp-based semi-structured interviews and were analyzed narratively. Findings suggest that the participants negotiated their multifaceted learning experiences and complexities during the online learning process. In addition, from the participants’ narratives, teaching and learning enactment done by the teachers was ill-performed. The pedagogical implications of this study are discussed at the end of this paper
The power of a brand ambassador twice influences brand image and purchase intention on Scarlett whitening beauty product
Full text linkMany beauty products, including Scarlett Whitening products, use brand ambassadors in their promotions. One of the hype beauty products among Indonesians is Scarlett Whitening by Felicya Angelista. Regarding the influence of brand ambassadors on purchase intention, previous studies have shown inconsistent results. This research aims to determine the power of brand ambassadors in influencing brand image and purchase intention for Scarlett Whitening beauty products. This research replicates previous model by differentiating the research context. The concepts used to support this research are brand ambassador, brand image, and purchase intention. The object of this research is Scarlett Whitening's product. Data were collected using questionnaires distributed through Google Forms to 151 respondents who had ever bought and used Scarlett Whitening, selected judgmentally. Using Structural Equation Modeling (SEM) with the help of WarpPLS 8.0 as the data analysis tool, the study found that brand ambassadors' power positively influences the brand image and purchase intention. The author suggests companies consider adding product variants for other skin types. Future researchers can add or use different variables to enrich these research findings
The Utilization of Fuzzy Logic Controllers in Steering Control Systems for Electric Ambulance Golf Carts
Full text linkThis study investigates methods to improve steering control for electric ambulance golf carts by conducting a comparative analysis of fuzzy logic controllers. The research assesses four control systems, PD controller, fuzzy PD controller, fuzzy PD+I controller, and PBC and PD+I type fuzzy logic controller, to determine their effectiveness in enhancing steering control. Simulink simulations are employed to evaluate the performance of these controllers under various conditions. Results indicate that the PBC and PD+I type fuzzy logic controller demonstrates superior performance, showing significant reductions in both rise time and settling time with minimal overshoot compared to other controllers. The findings underscore the potential of fuzzy logic controllers in enhancing steering control for electric vehicles. Future research should explore alternative control strategies and assess controller robustness under diverse operating conditions