The purpose of this paper is to analyze sleep stages accurately using fast and simple classifiers based on the frequency domain of electroencephalography(EEG) signal. To compare and evaluate system performance, the ru...The purpose of this paper is to analyze sleep stages accurately using fast and simple classifiers based on the frequency domain of electroencephalography(EEG) signal. To compare and evaluate system performance, the rules of Rechtschaffen and Kales(R&K rule) were used. Parameters were extracted from preprocessing process of EEG signal as feature vectors of each sleep stage analysis system through representatives of back propagation algorithm and support vector machine (SVM). As a result, SVM showed better performance as pattern recognition system for classification of sleep stages. It was found that easier analysis of sleep stage was possible using such simple system. Since accurate estimation of sleep state is possible through combination of algorithms, we could see the potential for the classifier to be used for sleep analysis system.展开更多
Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient...Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient fluid supply in oil wells based on convolutional neural networks is proposed in this paper. Firstly, 5000 indicator diagrams with insufficient liquid supply were collected from the oilfield site, and a sample set was established after preprocessing;then based on the AlexNet model, combined with the characteristics of the indicator diagram, a convolutional neural network model including 4 layers of convolutional layers, 3 layers of down-pooling layers and 2 layers of fully connected layers is established. The backpropagation, ReLu activation function and dropout regularization method are used to complete the training of the convolutional neural network;finally, the performance of the convolutional neural network under different iteration times and network structure is compared, and the super parameter optimization of the model is completed. It has laid a good foundation for realizing the self-adaptive and intelligent matching of oil well production parameters and formation fluid supply conditions. It has certain application prospects. The results show that the accuracy of training and verification of the method exceeds 98%, which can meet the actual application requirements on site.展开更多
This paper presents a multi-ANN approximation approach to approximate complex non-linear function. Comparing with single-ANN methods the proposed approach improves and increases the approximation and generalization ab...This paper presents a multi-ANN approximation approach to approximate complex non-linear function. Comparing with single-ANN methods the proposed approach improves and increases the approximation and generalization ability, and adaptability greatly in learning processes of networks. The simulation results have been shown that the method can be applied to the modeling and identification of complex dynamic control systems.展开更多
文摘The purpose of this paper is to analyze sleep stages accurately using fast and simple classifiers based on the frequency domain of electroencephalography(EEG) signal. To compare and evaluate system performance, the rules of Rechtschaffen and Kales(R&K rule) were used. Parameters were extracted from preprocessing process of EEG signal as feature vectors of each sleep stage analysis system through representatives of back propagation algorithm and support vector machine (SVM). As a result, SVM showed better performance as pattern recognition system for classification of sleep stages. It was found that easier analysis of sleep stage was possible using such simple system. Since accurate estimation of sleep state is possible through combination of algorithms, we could see the potential for the classifier to be used for sleep analysis system.
文摘Traditional methods for judging the degree of insufficient fluid supply in oil wells have low efficiency and limited accuracy. To address this problem, a method for intelligently identifying the degree of insufficient fluid supply in oil wells based on convolutional neural networks is proposed in this paper. Firstly, 5000 indicator diagrams with insufficient liquid supply were collected from the oilfield site, and a sample set was established after preprocessing;then based on the AlexNet model, combined with the characteristics of the indicator diagram, a convolutional neural network model including 4 layers of convolutional layers, 3 layers of down-pooling layers and 2 layers of fully connected layers is established. The backpropagation, ReLu activation function and dropout regularization method are used to complete the training of the convolutional neural network;finally, the performance of the convolutional neural network under different iteration times and network structure is compared, and the super parameter optimization of the model is completed. It has laid a good foundation for realizing the self-adaptive and intelligent matching of oil well production parameters and formation fluid supply conditions. It has certain application prospects. The results show that the accuracy of training and verification of the method exceeds 98%, which can meet the actual application requirements on site.
文摘This paper presents a multi-ANN approximation approach to approximate complex non-linear function. Comparing with single-ANN methods the proposed approach improves and increases the approximation and generalization ability, and adaptability greatly in learning processes of networks. The simulation results have been shown that the method can be applied to the modeling and identification of complex dynamic control systems.