Applied Mechanics and Materials Vols. 519-520

Abstract: The video capture and preprocessing is the basis of video process system. This paper analyzes the timing of video capture by Camera Link interface based on FPGA, and proposed an automatic error detection approach to avoid error accumulation during the video data capture. Furthermore, by adopting the optimized LUT and pipeline addition, an optimized method for RGB to YCbCr color space conversion (CSC) is presented specifically for the video format preprocessing. Experimental results demonstrate that the strategy we proposed is of high reliability, and it could obtain maximum operation frequency of 334MHz, 3.16 times faster than the direct method.

Abstract: Based on synthesizing octonions and the R, G, B components of color image , a color image edge detection algorithm is proposed ,combining octonions with Echo State Networks(ESN) . The judged pixel and its eight-neighbourhood mean is used to calculate vector product as the feature vectors of image edge. Then the ESN is trained with training samples and the trained ESN is directly used for edge detection. Experiments show that this method has good effect of fabric edge detection with a stronger ability to keep the details.

Abstract: A data parallel implementation of geometric operations is proposed and conclusions are proved. It shows that the computation complexity of data parallel implementation scheme presented in this paper is Ο(M+N). It can be used to improve the efficiency of geometric operations and can easily meet the real time requirements of the digital image processing.

Abstract: Color space conversion (CSC) is an important kernel in the area of image and video processing applications including video compression. As a matrix math, this operation consumes up to 40% of processing time of a highly optimized decoder. Therefore, techniques which efficiently implement this conversion are desired. Multicore processors provide an opportunity to increase the performance of CSC by exploiting data parallelism. In this paper, we present three novel approaches for efficient implementation of color space conversion suitable for homogeneous and heterogeneous multicore. We compare the performance of color space conversion on a variety of platforms including OpenMP running on homogeneous multicore CPUs, CUDA with NVIDIA GPUs and OpenCL running on both NVIDIA and ATI GPUs. Our experimental results show that the speedup of 3×, 17× and 15× can been obtained, respectively.

Abstract: For the clustering problem of wide difference that cannot be solved by K-means, an improvement clustering algorithm (CBG, clustering based on gravitation) is proposed in this paper. The clustering algorithm simulates the law of universal gravitation, which is that stars with heavy mass tend to show a stronger attraction to floating objects than those with less mass. Some experiments have done in this paper for this problem, and the results show that this algorithm can obtain better clustering result for this case.

Abstract: During the early stage of product design, it is important for design engineers to decide the most appropriate functions for various customers. To facilitate this time consuming task, sequential pattern mining is applied to uncover the useful patterns in historical database. The mined sequential patterns can reflect the dynamic change of product functions, which can help design engineers find the most suitable product functions for customers. Based on the historical sales transactions of computer, a case study is conducted to illustrate the proposed method.

Abstract: Traditional optimization algorithms can only optimize parameters in control laws. Machine learning method can optimize parameters and evolve satellite attitude control law automatically under certain criterion. Single axis satellite attitude simulation system with noise was built up, which included satellite attitude dynamic model, sensors and actuators model. The control laws inputs were attitude error, attitude errors integral and angular velocity error, and outputs were actuators control instructions. Control laws fitness function was an attitude errors statistical function. With suitable function set selected for genetic programming (GP) and parse tree used to represent a control law expression, GP was used to evolve control law expression automatically. Simulation result shows that this method can evolve control law with uncertainties noise better. The evolved control law response and control precision are better than PID, and it can be used in satellite attitude control.

Abstract: This paper develops a novel distributed jointly sparse optimization algorithm to recover the sparse signal, in which the joint sparse structure is used to improve the quality of recovery. In distributed networked multi-agent system, each agent collects measurement vectors and aims to recover its own sparse signal collaboratively in a distributed manner. We propose to use the factored gradient approach to calculate the solution iteratively, and introduce a energy vector of the current estimates as the consensus constrain which is updated by inexact consensus optimization for its distributed implementation. This algorithm does not require excessive data transmissions from distributed agents to fusion center, which reduces communication overhead and the computational complexity of the agents. Simulation results demonstrate that the proposed distributed algorithm has strong recovery performance and can reach global convergence as well as fast convergence rate.

Abstract: The traditional tourism services tend to use tourism resources as the center. They ignore individual characteristics and contextual information of the user side. The provided service is static, and doesnt meet the real needs of the users. A service mechanism based on context awareness is presented which consists of data, platform and services. It sets up data center based on users and gets context data according to rules .It uses the cloud computing technology to provide distributed processing, storage and retrieval capability for big data. It also establishes tourism service confirming to requirements of the users and dynamic adjusts service mode according to the user context information. Simulation results show that the mechanism can realize the demand for tourism services in conjunction with the individual characteristics of user.

Abstract: In this paper a novel quantum genetic algorithm (NQGA) introducing the crossover and mutation operations is proposed, and the algorithm is used to solve the TSP in MATLAB. Compared with the traditional Quantum genetic algorithm(QGA),NQGA is better in the global searching ability.