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.

Optimization of Hybrid Neural Network Predictor for Spatial Traffic Flow Data Treatment: Genetic Phase-Space Reconstruction

Abstract: The present paper proposes a hybrid neural predictor that consists of temporal structure of Multilayer Perceptrons for encompassing traffic flow series from sequential points in a traffic network to improve short-term traffic flow prediction. Each of the temporal structures is genetically optimized to provide the optimum embedding of the series attached.

Hybrid Neural Network Based Prediction of Inverse Kinematics of Robot Manipulator

Abstract: The fundamental of the inverse kinematics of robot manipulator is to determine the joint variables for a given Cartesian position and orientation of an end effector. Conventional methods to solve inverse kinematics such as geometric, iterative and algebraic are complex for redundant manipulators. There is no unique solution for the inverse kinematics thus necessitating application of appropriate predictive models from the soft computing domain. Although artificial neural network (ANN) can be gainfully used to yield the desired results, but the gradient descent learning algorithm does not have ability to search for global optimum and it gives a slow convergence rate. This paper proposes structuring ANN with hybridization of Particle Swarm Optimization to solve the inverse kinematics of 6R robot manipulator. An investigation has been made on accuracies of adopted algorithm. The ANN model used is multi-layered perceptron neural network (MLPNN) with back-propagation (BP) algorithm which is compared with hybrid multi layered perceptron particle swarm optimization (MLPPSO). An attempt has been made to find the best ANN configuration for the problem. It has been observed that MLPPSO gives a faster convergence rate and improves the problem of trapping in local minima. It is found that MLPPSO gives better result and minimum error as compared to MLPBP.

Hybrid Artificial Neural Networks Based Models for Electricity Spot Price Forecasting - A Review

Abstract: Electricity price forecasting plays a crucial role in a liberalized electricity market. In terms of forecasting approaches, artificial neural networks are the most popular among researchers due to their flexibility and efficiency in handling complexity and non-linearity. On the other hand, a single neural network presents certain limitations. Therefore, in recent years, hybrid models that combine multiple algorithms to balance out the advantages of a single model have become a trend. However, a review of recent applications of hybrid neural networks based models with respect to electricity price forecasting is not found in the literature and hence, the motivation of this paper is to fill this research gap. In this study, methodologies of existing forecasting approaches are briefly summarized, followed by reviews of neural network based hybrid models concerning electricity forecasting from year 2015 onwards. Major contributions of each study, datasets adopted in experiments as well as the corresponding experiment results are analyzed. Apart from the review of existing studies, the novelty and advantages of each type of hybrid model are discussed in detail. Scope of the review is the application of hybrid neural network models. It is found that the forecast horizon of the reviewed literature is either hour ahead or day ahead. Medium and long term forecasting are not comprehensively studied. In addition, though hybrid models require relatively large computational time, time measurements are not reported in any of the reviewed literature.

A hybrid neural network and freight volumes application

Abstract: Since the BP neural network algorithm has some unavoidable disadvantages, such as slowly converging speed and easily running into local minimum, the genetic algorithm and simulated annealing algorithm with the overall search capability have been put forward to optimize authority value and threshold value of BP nerve network. In this paper, a new neural network model which is optimized by genetic algorithm and simulated annealing algorithm has been established and applied into the freight volumes forecast. The result shows that the optimized neural network has significant advantages inspect of fast convergence speed, good generalization ability and not easy to yield minimal local results. In generally, the optimized neural network exhibits good representation and strong prediction ability, and is a helpful tool in the future freight volumes prediction.