Applied Mechanics and Materials Vols. 239-240

Abstract: The Tsumego problem in Go is a basic and essential problem to be overcome in implementing a computer Go program. This paper proposed a reality of Monte-Carlo tree search in Tsumego of computer Go which using Monte-Carlo evaluation as an alternative for a positional evaluation function. The advantage of this technique is that it requires few domain knowledge or expert input.

Abstract: For the realtime updating and strong randomness of the information, large RFID-based warehousing picking path optimization job requires to make decision continuously. It is different from the traditional picking path Problem. This paper proposed an Improved Ant Colony algorithm in order to solve the optimization of the large storage picking path based on RFID. Distributed Strategy, Dynamic Response Strategy and Time Waiting Strategy are adopted to improve the candidate set, meanwhile, adjust operator and parameter selection. Experimental results show that the convergence speed of this algorithm with high precision, a better solution to the optimization of picking operation based on RFID.

Abstract: The position estimation of optical feature points of visual system is the focus factor of the precision of system. For this problem , to present the Total Least Squares Algorithm . Firstly , set up the measurement coordinate system and 3D model between optical feature points, image points and the position of camera according to the position relation ; Second , build the matrix equations between optical feature points and image points ; Then apply in the total least squares to have an optimization calculation ; Finally apply in the coordinate measuring machining to have a simulation comparison experiment , the results indicate that the standard tolerance of attitude coordinate calculated by total least squares is 0.043mm, it validates the effectiveness; Compare with the traditional method based on three points perspective theory, measure the standard gauge of 500mm; the standard tolerance of traditional measurement system is 0.0641mm, the standard tolerance of Total Least Squares Algorithm is 0.0593mm; The experiment proves the Total Least Squares Algorithm is effective and has high precision.

Abstract: With the development of wireless application, radio spectrum management and monitoring become a hot spot. In this paper, a spectrum measurement method based on Labview is proposed and implemented. Based on this experimental network, radio spectrum of 20-3000MHz frequency band is measured with horizontal and vertical polarizations. This network possesses the characteristics of good compatibility, openness, and ease of implementation. It has a potential application for next generation of radio monitoring network.

Abstract: Contention-Based Forward (CBF) has proven to achieve a very good performance in mobile ad-hoc networks. Compare with other greedy forward algorithm, CBF is much more robust and have low maintenance network overheads. On the other hand, the main issue of CBF is to avoid packet duplication. Duplication is very easy to occur due to the hidden nodes problem. In this paper we introduce an area partition-based suppression algorithm for CBF in mobile ad-hoc networks. This algorithm sets the transmission area of a node into two areas: suppression area and none-suppression area. In the none-suppression area, the algorithm still use the SS-CBF (Sender Suppression-CBF) algorithm, in the suppression area, this paper will use a new equation to avoid packet duplication. The result shows that the new protocol could reduce the network overheads and do not cost extra transmission time.

Abstract: An improved particle filter algorithm is proposed to track a randomly moving target in video. In particle filter framework, a particle swarm optimization improved by niche technique which implemented by restricted competition selection is integrated. It can move particles into high likelihood area of target and form multi-population distribution, so that the searching capability of particles is enhanced and then the adaptation to the change of dynamic target state is improved. The particles of niching particle swarm optimization and the particles of particle filter are integrated for new particle weight calculation and finally realize a new particle filter for target tracking in video sequence.

Abstract: This paper proposes a cardinality estimation-based adaptive multi-tree splitting (CEAMS) algorithm. Tag number is estimated by using the depth information obtained from the first tag identification and adaptively assigns the splitting strategy according to the splitting subset rule table. Simulation results show that the average total number of timeslots can be reduced by 65% compared with DBS and the system throughput is about 0.52 when the number of tags ranged from 5 ~ 1000.

Abstract: Aiming at the shortages of traditional PID controller, and problems of hardly setting the controller parameters, and the setting time is long, this paragraph gives a design of ACA-BP arithmetic based controller of PID Neural Network. First, uses the Ant Colony algorithm to thickly select the PID neuron network weight parameter. Then adjust parameters online by PID Neural Network and BP algorithm. Finally, we can obtain optimal parameters. The simulation result shows, compared with traditional PID controller, this controller has greatly improved its control performances. This would have some theoretical and practical significance.

Abstract: The amount of methane emission is crucial to the safety of coal mine. The paper proposes the Levenberg Marquardt (LM) algorithm (in the nonlinear least squares algorithms) that can reduce the training time of BP network. Genetic Algorithm (GA) is used to optimize weights in global search to prevent the inherent defects that neural network is liable to get stuck in local minimal points. Furthermore, neural network can prevent the defect of weak GA local search. Finally, BP-GA modal was trained and the sample data were precisely analyzed, which proves that this model features broad adaptability and precision.

Abstract: All-k-Nearest-Neighbor (AkNN) operation is common in several applications, such as geographical information systems, data analysis, computer architecture, and so forth. However, in some real applications, users may consider AkNN search constrained to a specified region. Motivated by this, we introduce the Constrained All-k-Nearest-Neighbor (CAkNN) query that for every data in query data set A, retrieves its k NNs in data set B and located in the restricted region. In addition, we develop two efficient algorithms to answer CAkNN search, which utilize a conventional data-partitioning indexing structure (e.g., R-tree) on datasets and employ techniques includes group and plane-sweep to improve the efficiency of the search. Extensive experiments using both real and synthetic datasets demonstrate the efficiency and scalability of the proposed algorithms.