Applied Mechanics and Materials Vols. 321-324

Abstract: In order to improve the depth performance of AUV in parking, a PSO-BP algorithm for the depth control is presented. The algorithm can use the standard particle swarm (PSO) as BP neural network learning method, and which can be evolved in the AUV depth adaptive control. The adaptive controller has adopted the double neural network unit. One of controllers is made use the input terminal to output control quantity on the basis of current displacement and vertical acceleration of the AUV. The other can be recognized on-line by the AUV model identifier. The numerical simulations are given to verify the AUV depth adaptive control by the controller. The results show that the proposed algorithm can significantly improve the AUV depth control performance. The convergence speed of AUV depth control is 4.5 times than the PID algorithm, so the efficiency of the AUV depth is vastly perfected.

Abstract: Abstract. In order to reduce air traffic controller workload, optimized terminal sector partition was studied. The terminal way point capacity evaluation model was built, power polygon divided the terminal area into several units according to the vital way points, each unit workload could be calculated by the European method “RAMS”, and the sector optimum mathematical model was built. One improved ant colony optimization was adopted to solve the model. At last, an example of one terminal airspace sector partition was given. The results show it is an effective method to be applied into sector optimum partition based on way points.

Abstract: Automatic route design will help to develop electronic chart intelligence, hence to improve safety, economy and reliability of the route. In the paper rasterizing charts are used to expressed the navigation environment of the ship and the modified A* algorithm is used to compute the near optimum trajectory of a ship in given environment based on electronic chart dispiay and information system (ECDIS). By tracing Safety contours, computing obstacle areas and taking into account certain boundaries of the manoeuvring region, the problem of avoiding collisions at sea was reduced to optimization task with static constrains. Simulation using MATLAB is conducted to verify the proposed ship path planning method. The good results show the promise of this method for ship at sea.

Abstract: This paper studies the way to solve extreme value of the nonlinear multi-peak function by using the multi-population genetic algorithm (MPGA). With the analysis of the advantages and defects of the standard genetic algorithm (SGA),the paper, This paper is use the population genetic algorithm to achieve the optimization and verification with Simulation for solving the extreme value of the nonlinear multi-peak function, which in order to achieve the solution with higher accuracy and higher efficiency. And make the analysis for the premature convergence that existed in SGA by comparing the standard genetic algorithm simulation results with that form the MPGA.

Abstract: In this paper, we propose a path prediction approach using behavioral data of user that it contains the meaningful locations extracting and predicting method. The proposed method has a difference to the previous methods that is considering the interaction data for defining the meaningful location and predicting the future paths. Using these interaction and path data, the proposed method calculates the proximities of adjacency people. For extracting the meaningful locations, we consider the calculated proximity of people around user and stay time based on path data. And we simplify the paths using these extracted meaningful locations. Finally, in prediction step, the method predicts the destination using the simplified paths, and finds detail path from current location to destination using modified Dynamic Time Warping (DTW) algorithm. For verifying the usability of proposed method, first, we analyze the effect of people around the user for predicting the future paths of user. We verify the effectiveness of the proposed method by comparing the prediction accuracies of each method.

Abstract: The PERT network diagram optimization and the node layout optimization were studied in order to solve the difficulty of using manual methods to generate the PERT network chart in large-scale software project management. The new methods of optimization the node of PERT was proposed based on ant colony optimization algorithm (ACO) and genetic algorithms (GAs). The high adaptability and population optimization technology of GAs are discussed and also the ACO is introduced to realize the nodes layout global adjustment. In the end, calculation and simulation results show that the methods proposed can make the number of nodes of PERT network diagram generated automatically minimum. Meanwhile, it can make the layout of nodes of PERT network diagram more efficient and effective, so as to effectively solve the large-scale software project assessment problem.

Abstract: Choosing in the more practical soft time Windows the logistics pickup and delivery path choice is discussed. Setting up a more comprehensive model to get the minimum cost including the distance and time. Then improving the genetic algorithm to solve the vehicle routing optimization problems better.

Abstract: Marine ecosystems are affected by aromatic hydrocarbons. The predicting ability based on the quantitative structureactivity relationships (QSAR) model of unknown aromatic hydrocarbons toxicity is one of the tasks of security precaution. To establish the QSAR model between the physical and chemical properties of aromatic hydrocarbons and the inhibited activity of Chlorella vulgaris(C. Vulgaris), the optimized geometries, based on the 96 hr-EC₅₀ of 25 aromatic hydrocarbons with C. Vulgaris were carried out at the B3LYP/6-311G** level by density functional theory (DFT) calculation. With matlab2 010(a) software, genetic algorithm principal components regression (GAPCR) methods was used to develop the QSAR model and compared to traditional PCR model. PC1+PC3+PC5+PC6+PC8 were finally selected by GAPCR method. The of training, prediction data set and LOO cross validation are 0.918, 0.956 and 0.933, respectively. Meanwhile, the results of PCR were 0.949, 0.755 and 0.825, respectively. The results of this work showed that the GAPCR method has great results and good generalization capability. Comparing two motheds results indicting that GAPCR gives superior results to traditional PCR procedure.

Abstract: In view of the existing circumstances and problems in the medical services of chronic disease health consulting and guidance, an intelligent question-answering (QA) system based on B/S pattern is proposed in this paper. The system adopts a way combining automatic intelligent searching with semi-automatic assistant QA technology. Firstly, a structural model is established, and then the function of each module is discussed. Besides, an improved similarity algorithm is put forward and illustrated to have a good matching effect by experiment analysis.

Abstract: The research of traveling salesman problem (TSP) is important in logistics distribution. Because many stochastic cost factors affecting logistics distribution in real life, a class of stochastic programming model is considered in TSP in this paper. Through given a class of synthesizing effect functions which synthesis expectation and variance of cost factors, stochastic programming model of TSP with stochastic cost can be converted into a class of crisp programming models. A genetic algorithm based on real coding is used in an illustrative example. It is provided to show the effectiveness of the proposed model and method.