Hybrid neural network

About: Hybrid neural network is a research topic. Over the lifetime, 1305 publications have been published within this topic receiving 18223 citations.

Chinese User Service Intention Classification Based on Hybrid Neural Network

Abstract: In order to satisfy the consumers' increasing personalized service demand, the Intelligent service has arisen. User service intention recognition is an important challenge for intelligent service system to provide precise service. It is difficult for the intelligent system to understand the semantics of user demand which leads to poor recognition effect, because of the noise in user requirement descriptions. Therefore, a hybrid neural network classification model based on BiLSTM and CNN is proposed to recognize users service intentions. The model can fuse the temporal semantics and spatial semantics of the user descriptions. The experimental results show that our model achieves a better effect compared with other models, reaching 0.94 on the F1 score.

Research on Malicious TLS Traffic Identification Based on Hybrid Neural Network

Abstract: In this paper, the method of the hybrid neural network is used to identify malicious TLS traffic, and the network traffic anomaly detection algorithm based on logistic regression and decision tree and the distributed denial of service attack detection algorithm based on hybrid neural network algorithm and gradient lifting tree is proposed. It found that there is a general problem of high feature dimensions in network traffic detection. The useless features will increase the computational complexity of traffic anomaly detection and reduce accuracy. Based on the feature selection method of recursive feature elimination and logistic regression, the importance ranking of flow features obtained. Using the accuracy rate as an indicator, a decision tree algorithm used to model and predict network traffic. During network traffic anomaly detection, it is difficult to distinguish between normal traffic and denial of service attack traffic. The network traffic anomaly detection method based on the decision tree has low computational complexity and can save detection time. At the same time, the accuracy of the algorithm when detecting network traffic anomalies has been significantly improved, and the false alarm rate can also be reduced.

Fault Diagnosis Model Based on the Fusion of Hybrid Neural Network And Ant Colony Optimization Algorithm

Abstract: In this paper, fault diagnosis model based on the fusion of hybrid neural network (HNN) and ant colony optimization algorithm (ACOA) is presented. The associated rules are extracted based on rough set theory and are used as the theoretic basis of the connection mechanism of higher-order NN, which was composed with the feedforwardNN, the hybrid NN model is constructed. ACOA was used to optimize solving and to improve the generalization performance of HNN model. Hence the construction of presented model possesses theoretical significance and may ensure to take optimization performance and to enhance the generalization ability. Through the simulation and the analysis of fault-tolerance performance (FTP), it shows that the model based on the fusion of HNN and ACOA can effectively enhance the generalization ability and the FTP.

An integrated multi-task control system for fuel-cell power plants

Abstract: Development of Smart Grid requires power plants to be more intelligent, efficient, and reliable, which raises new challenges of the control system design for modern power plants. Regarding these requirements, an integrated multi-task control system using artificial intelligence technologies is proposed to improve the efficiency and reliability of a hybrid fuel-cell with gas turbine power plant. The integrated control system consists of a hybrid Neural Network plant model with online learning ability, an Optimal Reference Governor generating optimal setpoints as local control references, and a Fault Diagnosis and Accommodation system to detect internal plant faults and to regulate the plant during plant failures. The three subsystems are integrated to provide compressive management for the power plant. The hybrid fuel-cell power plant is introduced; the structure and strategies of the control system are discussed, and simulation results are presented.

Hybrid Neural Network Architecture Based on Self-Organizing Feature Maps

Abstract: An SOM(self-organizing feature maps)-based integrated network,namely ICBP-SOM,is constructed by applying the ICBP network model to the BP-SOM architecture.BP-SOM is a learning algorithm put forward by Ton Weijters,which aims to overcome some of the serious limitations of BP in generalizing knowledge from certain types of learning material.The motivation of presenting the integration is to employ BP-SOM good knowledge interpretation ability and the ICBP good generalization and adaptability to construct an ICBP-SOM,which processes favorable knowledge representation capability and competitive generalization performance.The experimental results on six benchmark data sets validate the feasibility and effectiveness of the integration.