The COVID-19 has become a pressing public health concern recently due to its dramatic impact. It spreads quickly, and it is beyond the ability of health staff to detect patients with the disease immediately. However, the ability to diagnose SARS-CoV-2 in a short time is critical for fighting the disease. The primary objective of this study is to develop deep neural networks to diagnose disease in a quick, safe, and cheap way. We classify the cases as normal, COVID-19, and pneumonia. Deep neural networks are developed to perform a three-class classification task. Ten deep learning models are evaluated on a large dataset. Although all DCNNs demonstrated promising potential for classification, hybrid neural networks delivered the most promising outcome with the highest accuracies. The first hybrid model is named MICOVID. The second hybrid model is named VVCOVID. These models are developed through transfer learning by using pre-trained deep learning models. Performance metrics results showed that MICOVID and VVCOVID models have an accuracy of 94% for COVID-19 detection. This is higher than other classification models. These findings suggest that two novel hybrid models that we proposed have great potential to be embedded into computer-aided systems to predict disease in radiology departments.

The maximum performance to be obtained by applying the Proportion-IntegralDerivative (PID) controller on a system depends on the optimum adjustment of its parameters. This study aims to present a design method for tuning the PID control parameters. In this method, PID controller design is made based on the optimal proportional gain from the system to the desired settling time and overshoot. The infrastructure of the technique is based on obtaining the other PID controller parameters by adjusting the optimum proportional gain (kp), which minimizes the settling time in a stable loop and the error rate of the overshoot. Routh Hurwitz criterion is used to guarantee stability in the control system. The effectiveness of the proposed method is tested as an active control application of the PID controller on a single degree of freedom (SDOF) structural system. The efficiency of the PID controller designed with this method, which does not require the destruction of parameters and does not contains complex mathematical formulations, is proven by its successful suppression of SDOF structural system responses.

We proposed a new conjugate gradient type hybrid approach in this study, which is based on merging Hestenes-Stiefel and Dai-Yuan algorithms using the spectral direction conjugate algorithm, we showed their absolute convergence. Under some assumptions and they satisfied the gradient property. The numerical results demonstrate the efficacy of the developed feedforward neural network training approach. To estimate the size of the population using the Thomas Malthus population model, and Our numerical results were very close to the model of the Tomas Malthose Model, we can use the method to predict other problems through the use of ann.

Permutation flow shop scheduling problem (PFSP) is an NP-complete problem with a wide range of applications in many real-world applications. Social spider optimization (SSO) is a swarm intelligence algorithm proposed for continuous optimization problems. Recently, SSO has received increased interest in the field of combinatorial optimization as well. For this reason, in this paper, SSO algorithm is proposed to solve the PFSP with make span minimization. The proposed algorithm has been tested on 141 well-known benchmark instances and compared against six other conventional and best-so-far metaheuristics. The obtained results show that SSO outperforms some of the compared works although they are hybrid methods.

In the study, it has been observed that there are many alternatives for the usage areas of nanofluids formed by dispersing solid particles of nanometric size (1-100 nm) in a basic fluid, as well as these fluids are efficient in both solar energy systems and other thermal systems. In this study, widely used nanofluids in heating and cooling systems and their application areas were investigated. It was observed that when nanofluids with different parameters are used, it affects thermal conductivity efficiency