“… According to Fig. 4 , a crow, or a solution to a problem can learn from other solutions (Al-Sorori and Mohsen 2020 ). Fig.…”
Section: New Caledonian Crow Learning Algorithmmentioning
confidence: 99%
“… Fig. 3 Crow learning mechanism for hunting (Al-Sorori and Mohsen 2020 ) Fig. 4 Update and learning mechanism in Crow algorithm (Dong et al 2020 ) …”
Section: New Caledonian Crow Learning Algorithmmentioning
confidence: 99%
“…The position of each crow or solution to the problem is indicated by Crow population members and their families are placed in a matrix such as Eq. ( 1 ) (Al-Sorori and Mohsen 2020 ): …”
Section: New Caledonian Crow Learning Algorithmmentioning
confidence: 99%
“…A way to diagnose a person with cod is to use a learning method such as a neural network, but only if the main features are considered for training. In this study, a feature selection method based on the Caledonian crow learning algorithm is proposed (Al-Sorori and Mohsen 2020 ). The purpose of using the crow learning algorithm is to consider only the essential features of COVID-19 disease for learning in artificial neural networks and to refuse the less important features.…”
In this study, feature selection methods based on the new Caledonian crow learning algorithm has been introduced. In the proposed algorithms, in the first stage, the best features related to COVID-19 disease are selected by the crow learning algorithm. Coronavirus (COVIDE-19) disease using as training input to the artificial neural network. Experiments on the COVID-19 disease dataset in a Brazilian hospital show that the crow learning algorithm reduces the feature selection objective function by iteration. Decreasing the feature selection function is due to reducing the error of classifying infected people as healthy and reducing the number of features. The experimental results show that the accuracy, sensitivity, precision, and F1 of the proposed method for COVID-19 patients diagnosing are 94.31%, 94.15%, 94.38%, and 94.27%, respectively. The proposed method for identifying COVID-19 patients is more accurate than ANN, CNN, CNNLSTM, CNNRNN, LSTM, and RNN methods.
“… According to Fig. 4 , a crow, or a solution to a problem can learn from other solutions (Al-Sorori and Mohsen 2020 ). Fig.…”
Section: New Caledonian Crow Learning Algorithmmentioning
confidence: 99%
“… Fig. 3 Crow learning mechanism for hunting (Al-Sorori and Mohsen 2020 ) Fig. 4 Update and learning mechanism in Crow algorithm (Dong et al 2020 ) …”
Section: New Caledonian Crow Learning Algorithmmentioning
confidence: 99%
“…The position of each crow or solution to the problem is indicated by Crow population members and their families are placed in a matrix such as Eq. ( 1 ) (Al-Sorori and Mohsen 2020 ): …”
Section: New Caledonian Crow Learning Algorithmmentioning
confidence: 99%
“…A way to diagnose a person with cod is to use a learning method such as a neural network, but only if the main features are considered for training. In this study, a feature selection method based on the Caledonian crow learning algorithm is proposed (Al-Sorori and Mohsen 2020 ). The purpose of using the crow learning algorithm is to consider only the essential features of COVID-19 disease for learning in artificial neural networks and to refuse the less important features.…”
In this study, feature selection methods based on the new Caledonian crow learning algorithm has been introduced. In the proposed algorithms, in the first stage, the best features related to COVID-19 disease are selected by the crow learning algorithm. Coronavirus (COVIDE-19) disease using as training input to the artificial neural network. Experiments on the COVID-19 disease dataset in a Brazilian hospital show that the crow learning algorithm reduces the feature selection objective function by iteration. Decreasing the feature selection function is due to reducing the error of classifying infected people as healthy and reducing the number of features. The experimental results show that the accuracy, sensitivity, precision, and F1 of the proposed method for COVID-19 patients diagnosing are 94.31%, 94.15%, 94.38%, and 94.27%, respectively. The proposed method for identifying COVID-19 patients is more accurate than ANN, CNN, CNNLSTM, CNNRNN, LSTM, and RNN methods.
“…This optimization problem should be solved in the on-board controller of the control system in real time, therefore, the time for its solution should not be large and should be placed in on-board controller cycle with the time for solving other tasks. For nonsmooth functions, more complex global optimization methods are used, for example [10,24,28]. In our case the control quality functions (7) or ( 8)-( 10) are smooth, the search for the optimal solution does not present much difficulty and can be carried out in a small number of iterations.…”
Section: Experiment Results and Discussionmentioning
The article considers the issues of automatic control of the vessel movement with a redundant control structure. Redundant structures are now widely used on all vessels with a dynamic positioning system to improve control efficiency (accuracy, maneuverability, reduce energy consumption and emissions), reliability and environmental safety. A brief review of the literature on the use of redundant structures to improve control efficiency is made. In open sources, the authors have not found solutions that improve the efficiency of the control by using redundant structures of actuators. Therefore, it was concluded that the development of such systems is relevant. Several schemes for splitting control into executive devices of a redundant structure, including an optimal splitting scheme, are considered. A comparative analysis of the considered splitting schemes with the optimal one is carried out. Comparative analysis showed that the use of optimal control of the redundant structure of actuators allows increasing the accuracy of dynamic positioning by (20-40)%, depending on the direction of the created control, as well as reducing fuel consumption by (30-100)%, which determines its advantages over known solutions. The mathematical and software support for an automatic optimal control system with redundant control has been developed. The operability and efficiency of the mathematical and software support were tested in a closed circuit with a control object in the MATLAB environment. The conducted experiments confirmed the operability and efficiency of the developed method, algorithms and software and allow to recommend them for practical use in the development of vessel control systems with redundant control structures.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
