Search

Sleep apnea (SA) is a common respiratory disorder, especially among obese people. It is caused by either the relaxation of the upper respiratory tract muscles or the failure of the neural signal to reach the muscles responsible for breathing, both of which interrupt the patient's sleep–wake cycles. The traditional method for diagnosing this disorder, based on polysomnography, is complicated, vexing, expensive, time-consuming, and requires both sleep centers and specialized staff capable of connecting electrodes to the patient's body. This paper proposes an SA prediction system based on merging five soft computing algorithms, specifically, combining the multi-verse optimizer (MVO) with an artificial neural network (ANN) to leverage measurements from heart rate, SpO2, and chest movement sensors. The most substantial novelty of this research is the hybridization of MVO and ANN (MVO-ANN), which improves the ANN performance by selecting the best learning rate and number of neurons in hidden ANN layers. This enables highly accurate prediction of sleep apnea events. This work's experimental results reveal that the MVO-ANN performs better than other algorithms, with mean absolute errors of 0.042, 0.202, and 0.166 for training, testing, and validation of the ANN. In addition, the SA prediction system achieved an accuracy of 98.67%, a sensitivity of 96.71%, and a specificity of 99.24%. These results provide good evidence that the proposed method can reliably predict respiratory events in people suffering from SA. [ABSTRACT FROM AUTHOR]

This paper offers an electromagnetism-like (IEM) algorithm to estimate the five parameters of a single-diode PV module's model. IEM uses local search and improves movement step to increase the convergence to optimal solutions. The key of improvement is performed by adding a nonlinear equation to adjust the length of the particle in each iteration. Moreover, the total force formula is simplified to speed up the exploration for an optimal solution. Analyses are carried out by experimental data points at various operational conditions to show the stability and reliability of the proposed methods. The results of the proposed IEM algorithm show a better convergence speed and high accuracy compared with other models in the literature, which involves various statistical errors. The values of average root mean square error, mean bias error, standard deviation, average absolute error, and average test statistic of the proposed method are 589%, 0.51%, 0.19%, 46%, and 0.53, respectively. As a conclusion, the IEM algorithm presents better performance than other methods in the literature in terms of accuracy and convergence. [ABSTRACT FROM AUTHOR]

The parameter determination based on experimental data aids in providing an accurate assessment for predicting the output current of the PV cells. This may be extremely helpful both practically and theoretically in the PV system simulation, optimization, and evaluation. Numerous stochastic methods have been widely utilized in recent decades to tackle the parameter extraction optimization problem. Hybrid methods that take advantage of two or more algorithms have been proposed by many to further enhance their accuracy, stability, and overall performance. However, the majority of the methods in the literature concentrate on the methodology, with few studies considering the formulation of the objective function, resulting in a theoretical gap in this area of study. In this work, a new improved arithmetic optimization method based on the adaption of Newton–Raphson and Levenberg–Marquardt damping parameter (IAOANRaLMp) is presented to globally extract the parameter of the single- and double-diode PV models. The experimental findings demonstrate that the proposed IAOANRaLMp approach performs exceptionally well in terms of minimizing error to zero for both models, as indicated by various statistical criteria and comparison with experimental data. [ABSTRACT FROM AUTHOR]