Applied Mechanics and Materials Vols. 543-547

Abstract: This paper introduces an overview on services and functions and the process of connection reestablishment provided by the RRC sublayer in the E-UTRAN of the LTE system. Then describe the process of connection reestablishment in detail. It also provides the specific designed flow chat to explain more exactly.In the design process,it simplifies signaling interaction between layers and the corresponding process is optimized and improved combined with the specific characteristics of major projects and the failure of connection reestablishment is analyzed in brief. Finally, the GFT chart was generated to verify the correctness of TTCN co-simulation.

Abstract: According to the structural characteristics of the plant itself, this paper Improved plant topology parsing classic language L-system and defined the basic unit of a reasonable scale. We combined basic growth unit, which consists of the chain of growth state, and ecological model. Applying C++ language to define L-system rules, rules for parsing, character iteration, physiological and ecological model program; combining with OpenGL graphics library for rendering three-dimensional structure of plant expression. Using classical topology of Botany Roux as experimental model simulation. We compare the simulation results and conventional classical model. At least, we prove this model is applicable.

Abstract: To reduce the prediction error rate of earthquake casualties, the paper proposed a prediction model with two steps: (1) screening of the earthquake casualties correlation factors; (2) improving the predictive veracity of general BP(Back Propagation) neural network model.By the analysis of 9 kinds of correlation factors, the paper established the MIV(Mean Impact Value) model based on BP neural network to screen the final correlation factors, and the paper got 6 main correlation factors according to the size of output weights of the factors. Finally, the paper verified the accuracy and practicability of the model through the validation of the model and the solving of prediction error of relevant factors hasn't been selected.

Abstract: One problem in NEAT is too difficult to get the adaptive function value , Basing on some hypothesizes, we only need to widen the distance of features of speciation in the population the more the better. So the fitness function is to find the average characteristic distance of every speciation in current population, choose first n biggest speciation to leave, and remove others.

Abstract: The current China railway freight transport has always been faced with the situation of limited transport resources. Many relative studies have been done to solve the problem of resource shortage. And railway freight volume prediction is the basis of all these studies. With accurate volume prediction, railway freight transport administrations can precisely allocate the transport resources, such as wagons and locomotives. In order to overcome the limitations of traditional prediction methods, in this study, we design four artificial neural network models for prediction, including BP neural network model, linear neural network model, RBF neural network model and generalized regression neural network model. The results of simulation and comparison show that all these models can reach high prediction accuracy and generalized regression neural network has both higher prediction accuracy and better curve fitting capacity compared with other models.

Abstract: The eigenvalues of some liquid drop fingerprints are of high similarity, which decreases the recognition accuracy rates of BP neural network. In order to solve this problem, recognition method based on cluster analysis and BP neural network is proposed in this paper. Cluster analysis is used to classify liquid samples according to the similarity of eigenvalues and narrow the recognition range for samples under study. The experimental results have proved that this method is able to increase the recognition accuracy rate from 83.42% to 99.83%.

Abstract: In TD-LTE system, the transmitter generates PUCCH format 2a/2b information, including reference signal with 1/2 bits ACK/NACK feedback information, and the receiver first must use blind estimate to get the ACK/NACK feedback information, and then get the channel response of the reference signal symbols, then the channel response of the data symbols is obtained by time domain interpolation algorithm. This paper first introduces the traditional algorithm of d (10) and the existing algorithm, and then proposes an improved algorithms. Though simulation analysis, the improved algorithms are superior to the traditional algorithm, and the LS algorithm is to implement by DSP, after trade-offs between complexity and performance.

Abstract: Based on the particle swarm optimization (PSO) and BP neural network (BPNN), an algorithm for BP neural network optimized particle swarm optimization (PSOBPNN) is proposed. In the algorithm, PSO is used to obtain better network initial threshold and weight to compensate the defect of connection weight and thresholds of BPNN, thus it can make BPNN have faster convergence and greater learning ability. The efficiency of the proposed prediction method is tested by the simulation of the chaotic time series for Lori mapping. The simulations results show that the proposed method has higher forecasting accuracy compared with the BPNN, so it is proved that the algorithm is feasible and effective in the chaotic time series prediction.

Abstract: This paper transforms a common conjugate gradient algorithm, based on the fuzzy neural network for line. This thesis systematically studies the performances and learning algorithms of two FNN models, monolithic FNN and polygonal FNN, based on the past progress of FNN theory and application. The major issues in the thesis are the perturbation of monolithic FNN, the learning algorithms and universal approximation of polygonal FNN and the achievements obtained here are applied to fuzzy control area.

Abstract: This paper mainly to the ant colony algorithm ant colony system (application pseudo-random proportional rules) and add adaptive learning, momentum BP algorithm of these three together was improved, established a hybrid algorithm, to a certain extent overcome the BP algorithm is easy to fall into local minimum value, slow convergence speed, and achieved satisfactory results. Generally speaking, the performance of BP network is composed of two components: the topology of the network and network learning algorithm. The topology of the network design especially hidden node number should be how to choose the number of neurons more reasonable there is no unified theory, the solution actual problem at present is more of the experience and the method of combining the test to determine the optimal number of hidden nodes. This paper mainly discussed the structure of neural network to determine later, network learning process problems.