This study proposes a new hybrid machine learning (ML) model for the early and accurate diagnosis of heart disease. The proposed model is a combination of two powerful ensemble ML models, namely ExtraTreeClassifier (ETC) and XGBoost (XGB), resulting in a hybrid model named ETCXGB. At first, all the features of the utilized heart disease dataset were given as input to the ETC model, which processed it by extracting the predicted probabilities and produced an output. The output of the ETC model was then added to the original feature space by producing an enriched feature matrix, which is then used as input for the XGB model. The new feature matrix is used for training the XGB model, which produces the final result that whether a person has cardiac disease or not, resulting in a high diagnosis accuracy for cardiac disease. In addition to the proposed model, three other hybrid DL models, such as convolutional neural network + recurrent neural network (CNN-RNN), convolutional neural network + long short-term memory (CNN-LSTM), and convolutional neural network + bidirectional long short-term memory (CNN-BLSTM), were also investigated. The proposed ETCXGB model improved the prediction accuracy by 3.91%, while CNN-RNN, CNN-LSTM, and CNN-BLSTM enhanced the prediction accuracy by 1.95%, 2.44%, and 2.45%, respectively, for the diagnosis of cardiac disease. The simulation outcomes illustrate that the proposed ETCXGB hybrid ML outperformed the classical ML and DL models in terms of all performance measures. Therefore, using the proposed hybrid ML model for the diagnosis of cardiac disease will help the medical practitioner make an accurate diagnosis of the disease and will help the healthcare society decrease the mortality rate caused by cardiac disease.
Flexible robot systems are often regarded as the most vital in a variety of academic and industrial settings. Introducing innovative ideas for outperforming this system’s performance is always valuable since its application to real domains makes it so applicable. Compared to traditional methods, the utilization of soft computing techniques can improve overall performance by predicting and optimizing its outcomes. This research proposes a hybrid control method that combines input shaping with fuzzy active disturbance rejection control for a flexible joint robotic manipulator with unknown perturbation and parametric uncertainty. The suggested algorithm’s control objective is to adapt and learn in different real-world scenarios to accurately follow the required trajectories while dampening the system’s vibration. Overshoot is reduced, and reaction time is increased by employing an input shaping approach, while the extended state observer is built to handle unexpected perturbations and uncertainties in parameters. Additionally, fuzzy logic adjusts the linear feedback control law gains online to boost the control system’s dynamic capability. As a result of comparing the experimental results with active disturbance rejection controller (ADRC), interval type–2 fuzzy logic controller (IT2FL-C), input shaping–active disturbance rejection controller (IS+ADRC), modified linear active disturbance rejection controller (MLADRC), genetic algorithm–fuzzy logic controller (GA-FLC), and Fuzzy–tuned PID (FPID), the authors ensure that the hybrid input shaping enhanced fuzzy based active disturbance rejection controller (HIS-FADRC) control law is efficient and resilient. The advised controller achieves the highest robustness regarding position control, disturbance rejection, trajectory tracking, and parameter variation, which is superior to other hybrid controllers in most IAE, ITAE, ISE, and ITSE performance indexes. QUANSER’s Rotary Flexible Joint Manipulator (RFJM) system is excellent at tracking and suppressing disturbances, despite uncertainties and nonlinearity of flexible joints.
1 March 2025 in Journal of Robotics and Control (JRC)
Improving the quality of the produced artwork would require the development of computer numerical control (CNC) technology for various wood shaping processes. This paper presents the development and implementation of a CNC wood carving machine. This project aims to produce wood carvings with high precision and low cost. The electronic components were selected, the mechanical frame of the machine was built, and all parts of the machine were assembled and installed. The presented wood carving machine is based on the principle of drawing the desired shape, translating it into G-code, and then sending it to the microcontroller program. The microcontroller sends instructions to the CNC shield, which drives three stepper motors in a synchronized manner in order to produce the desired carving model. The maximum workpiece of the caving machine designed to be 30x30 cm. Experiments were conducted to test the functionality of the proposed CNC wood carving machine. The results showed that the carved models created by this machine had a carving precision range from ±0.1 to ±0.15 mm and a carving speed of approximately 500 rpm. The proposed CNC can be used to produce low-cost artisanal woodwork applications.
1 March 2026 in Journal of Electronic Science and Technology
High-energy lithium-ion batteries demand cathode architectures capable of sustaining high areal capacities without compromising electrochemical or thermal stability. Among layered oxide cathodes, LiNi 0.8 Mn 0.1 Co 0.1 O 2 (NMC811) offers high specific capacity (∼200 mAhg −1 ) and reduced cobalt content, but thick, high-mass-loading electrodes typically exhibit severe Li + transport limitations, polarization, and thermal heterogeneity. To address these issues, an integrated framework is developed, combining COMSOL-based pseudo-two-dimensional (P2D) simulations with machine learning algorithms to enable rapid prediction and optimization of structure-property-performance relationships. High-fidelity simulations are performed across electrode thicknesses of 60–240 μm and porosities of 20%–45%, generating datasets that capture coupled ion diffusion, charge transport, and heat generation. Trained ensemble learning and deep neural network models achieve R 2 > 0.95 for key electrochemical and thermal outputs. Bayesian multi-objective optimization identifies Pareto-optimal electrode architectures, achieving 178 mAhg −1 with minimized overpotential (<45 mV) and temperature rise (<8 °C). This hybrid physics-ML strategy establishes a scalable platform for accelerating thick-electrode design and provides quantitative insights into the critical role of transport and thermal dynamics in next-generation high-energy lithium-ion batteries.
1 September 2025 in International Journal of Power Electronics and Drive Systems (IJPEDS)
The increasing demand for sustainable and reliable power sources in portable and implantable medical devices has led to growing interest in photovoltaic (PV) energy harvesting. Traditional power sources, such as batteries, are limited by finite energy capacity and frequent replacement or recharging needs, particularly in implantable devices where surgical intervention is required for battery replacement. Photovoltaic energy harvesting, which converts light into electrical energy, offers a promising alternative, especially in environments with consistent light exposure. This review provides an in-depth analysis of the advancements in PV technologies for powering medical devices. It covers various types of PV materials, design innovations, and the integration of energy storage systems. Additionally, the review highlights the application of PV systems in both external and implantable medical devices, while addressing critical challenges such as ensuring biocompatibility, optimizing performance in low-light conditions, and miniaturizing PV systems for implantation. The potential of PV energy harvesting to improve device longevity and reduce the need for invasive procedures is emphasized. This review concludes by outlining the current challenges and future directions needed to achieve widespread clinical adoption, aiming to contribute to the development of sustainable power solutions in healthcare.