Stroke is a disease that is caused due to the blockage and burst in the blood vessels of the brain, thus resulting in abrupt brain dysfunction, like sensory or motor disorders, unconsciousness, limb paralysis, and pro...
详细信息
Stroke is a disease that is caused due to the blockage and burst in the blood vessels of the brain, thus resulting in abrupt brain dysfunction, like sensory or motor disorders, unconsciousness, limb paralysis, and pronunciation disorders. The existing stroke prediction algorithms have some limitations because of the lengthy testing procedures and hefty testing expenses. The main goal of this study is to develop and implement the proposed fusion-based, optimized deep learning model for stroke disease prediction using multimodalities. For that, this research considers the Computed Tomography (CT) and electroencephalogram (EEG) signals as input, and all of these inputs are processed separately to predict the stroke disease. While predicting the stroke disease with a CT image, the bilateral filter performs the pre-processing and the disease prediction is done with the DenseNet model, which is tuned by the proposed Jaya Fractional reptile search algorithm (Jaya FRSA). Similar to how the proposed FRSA does CNN-LSTM training, the Convolutional Neural Network-Long Short Term Memory (CNN-LSTM) predicts the stroke disease using the EEG data as an input after the Gaussian filter removes signal noise. Additionally, the CT image and the EEG signal are processed independently from the image and signal properties. Additionally, the CNN-LSTM model and DenseNet model results are combined using the overlap coefficient to get the final disease prediction. According to the experimental study, the suggested method achieved the maximum image accuracy, sensitivity, and specificity of 0.924, 0.930, and 0.935.
Distributed generation (DG) sources that are randomly placed cause voltage fluctuations, which in turn affect power quality problems and degrade system efficiency. The placement of DG sources in a distribution network...
详细信息
Distributed generation (DG) sources that are randomly placed cause voltage fluctuations, which in turn affect power quality problems and degrade system efficiency. The placement of DG sources in a distribution network to achieve economic and technical system benefits is a pressing issue that this work aims to investigate. An analysis has been conducted to incorporate the recently proposed reptile search algorithm (RSA) into the optimization framework for determining the optimal size of photovoltaic (PV)-powered DGs, while a distribution load flow method is used to determine their optimal location by minimising the combined placement index (CPI). The CPI is calculated by adding the combined power loss sensitivity factor and the voltage stability factor. The former minimises the net active and reactive loss sensitivity of the system, whereas the latter maximises the voltage sensitivity of all buses. A single DG source has been employed to strike a balance between the economics of DG integration and its effectiveness in improving voltage stability. The Lambert-W function is introduced to model PV system dynamics, which simplifies calculations by eliminating numerical solution complications while reducing computational time while also estimating maximum power point variables via direct closed-form equations. The system results indicate that the addition of optimally sized and appropriately placed PV-DGs maintains the voltage profile within permissible limits while reducing overall system losses, leading to an in-crease in the system's efficiency. The system is simulated on IEEE-33 and IEEE-69 bus test systems in MATLAB, and the results are compared with a traditional genetic algorithm (GA) to highlight the applicability of the presented method.
In this study, the effects of copper nanoparticles are taken into account to create a new hybrid metaheuristic for solving the nonlinear MHD Jeffery-Hamel blood flow problem. Since copper nanoparticles are effective i...
详细信息
In this study, the effects of copper nanoparticles are taken into account to create a new hybrid metaheuristic for solving the nonlinear MHD Jeffery-Hamel blood flow problem. Since copper nanoparticles are effective in lowering the hemodynamics of stenosis, the subject has scientific and biological implications. The coupled partial differential equations are converted to ordinary differential equations using suitable transformations. Considering an artificial neural network as a solution, the error function has been formed for the differential equations. A hybrid of the reptile search algorithm (RSA) and the interior point algorithm (IPA) is used to minimise the error function (<= 10-05). The initial weights are first updated using the RSA algorithm (maximum 20 iterations), which is used as a tool for global search;later, IPA is used for quick local convergence. To validate the proposed technique's accuracy, comparison studies are conducted using the fourth-order Runge-Kutta method and the hybrid PSO-IPA algorithm. Statistical analysis is provided using multiple performance indices to demonstrate the suggested approach's precision, efficiency, and reliability. The research findings indicate that the outcomes achieved by the developed RSA-IPA technique exhibit superior performance compared to previously established methodologies, with an accuracy level of 10-04. The findings indicate that a rise in the volume fraction of cunanoparticles results in a decrease in the rate of blood flow. The research advances studies of blood flow in the medical sciences.
暂无评论