With the acceleration of urbanization in the world, urban traffic congestion has become an urgent challenge in most cities. Adaptive traffic signal control is the most approved control method to solve the problem, and...
详细信息
With the acceleration of urbanization in the world, urban traffic congestion has become an urgent challenge in most cities. Adaptive traffic signal control is the most approved control method to solve the problem, and accurate real-time traffic information is critical to this solution. This paper presents distributed cooperative reinforcement learning-based traffic control that integrates V2X networks' dynamic clustering algorithm. To obtain traffic flow information accurately and instantaneously, it is important to improve the cluster stability in V2X networks. A dynamic clustering algorithm is proposed based on the enhanced affinity propagation. The proposed clusteringalgorithm introduces the initial cluster partition to maintain a proper cluster size and adds the lane and destination factors to improve the cluster's stability. The algorithm can provide efficient and accurate traffic state information to traffic signal controls. By integrating the clusteringalgorithm, a cooperative reinforcement learning control scheme is proposed to balance the traffic load. To address the tough dimensionality curse of reinforcement learning, a distributed mechanism for intersection cooperation is introduced, and a fast gradient-descent function approximation method is proposed to improve the controls' real-time performance. The proposed intelligent traffic control scheme that integrates the stable clusteringalgorithm can effectively improve the traffic throughput, reduce the average waiting time, and avoid congestion. Numerical simulations on real scenarios validate the performance of the proposed approach.
It is a great challenge for regions of interest-based image retrieval(ROIBIR) system how to retrieval efficiently images from large images *** this paper,the dynamic clustering algorithm is proposed,and it is used to ...
详细信息
It is a great challenge for regions of interest-based image retrieval(ROIBIR) system how to retrieval efficiently images from large images *** this paper,the dynamic clustering algorithm is proposed,and it is used to construct our proposed hierarchy indexing tree.A search method with A* tree,triangle inequality principle and N-nearest neighbor is applied to achieve an optimal search for ROIBIR *** with Corel image database are carried out that the proposed method with the hierarchical indexing tree,and our proposed method achieves the better retrieval efficiency.
An express delivery mode based on automatic parcel machine (APM) is put forward and the delivery system is optimized in this paper. The optimization problem is described as a mathematical programming model, and the im...
详细信息
ISBN:
(纸本)9783037859926
An express delivery mode based on automatic parcel machine (APM) is put forward and the delivery system is optimized in this paper. The optimization problem is described as a mathematical programming model, and the improved twice dynamic clustering algorithm and the C-W saving algorithm are developed for solving it. Obtained results show that the mode and the express delivery system have great practical application value and popularized significance.
A novel dynamic evolutionary clusteringalgorithm is proposed in this paper to overcome the shortcomings of fuzzy modeling method based on general clusteringalgorithms that fuzzy rule number should be determined befo...
详细信息
ISBN:
(纸本)9783540742012
A novel dynamic evolutionary clusteringalgorithm is proposed in this paper to overcome the shortcomings of fuzzy modeling method based on general clusteringalgorithms that fuzzy rule number should be determined beforehand. This algorithm searches for the optimal cluster number by using the improved genetic techniques to optimize string lengths of chromosomes;at the same time, the convergence of clustering center parameters is expedited with the help of Fuzzy C-Means algorithm. Moreover, by introducing memory function and vaccine inoculation mechanism of immune system, at the same time, dynamic evolutionary clusteringalgorithm can converge to the optimal solution rapidly and stably. The proper fuzzy rule number and exact premise parameters are obtained simultaneously when using this efficient dynamic evolutionary clusteringalgorithm to identify fuzzy models. The effectiveness of the proposed fuzzy modeling method based on dynamic evolutionary clusteringalgorithm is demonstrated by simulation examples, and the accurate non-linear fuzzy models can be obtained when the method is applied to the thermal processes.
A hybrid methodology is proposed to take advantage of the unique strength of Autoregressive Integrated Moving Average (ARIMA) and RBF (Radial Basis Function) neural networks in linear and nonlinear modeling, which is ...
详细信息
ISBN:
(纸本)1424403316
A hybrid methodology is proposed to take advantage of the unique strength of Autoregressive Integrated Moving Average (ARIMA) and RBF (Radial Basis Function) neural networks in linear and nonlinear modeling, which is an error correction method to create synergies in the overall forecasting process. ARIMA model is used to generate a linear forecast in the first stage, and then RBFN is developed as the nonlinear pattern recognition to correct the estimation error in ARIMA forecast. A dynamic clustering algorithm is developed to optimize the network structure, which makes the RBFN adapt to the specified training set, reduces computation complexity and avoids overfitting. With two real datasets, in terms of forecasting accuracy, empirical results evidently show that the hybrid model outperforms noticeably ARIMA and RBFN model used in isolation.
A new algorithm for detecting and extracting discontinuous lines is presented against the shortcomings of the usual method for lines extraction. Firstly almost all of the line segments were acquired by the means of Ho...
详细信息
ISBN:
(纸本)9781424405701
A new algorithm for detecting and extracting discontinuous lines is presented against the shortcomings of the usual method for lines extraction. Firstly almost all of the line segments were acquired by the means of Hough transform, and then the line segments were grouped by the method of improved dynamic clustering algorithm. The improvement of the dynamic clustering algorithm are the initial cluster is based on the method of the standardized pattern transform and a kernel of every class replaces the centre of the class as the patterns of every class obey the norm distribution. In the next step the fine segments belong to the same group are fitted into possible longer lines and the long lines' existence is further defined by judging whether the total number of marginal points in the neighbourhood of the lines is large enough or not. At last, the redundant lines are also excluded by the means of dynamic clustering algorithm. Experiments demonstrate that the proposed algorithm is valid.
An intelligent controller for the trajectorycontrol of the free disc (the simplified model of thesatellite m 2-dimension space) is proposed in this *** a classifier is constructed relying on the dynamicclustering algo...
详细信息
An intelligent controller for the trajectorycontrol of the free disc (the simplified model of thesatellite m 2-dimension space) is proposed in this *** a classifier is constructed relying on the dynamicclusteringalgorithm. Then, a back propagation neuralnetwork is trained to learn the inverse dynamics modelof the free disc. The newly proposed method has theadvantage of simplicity and intelligence for thetrajectory control of the free disc.
暂无评论