Applied Mechanics and Materials Vols. 236-237

Abstract: In this paper, a support vector machine (SVM) based land/sea clutter classification algorithm was proposed. For target location error correction based on passive beacon reference source of over-the-horizon radar (OTHR), the signal model of land/sea clutter is established, the three kinds of multi-features of land/sea clutter are analyzed, and the classification algorithm based on SVM using multi-features is detailed. Simulation experiments were carried out for different clutter-noise- ratios, and the results showed that the proposed algorithm has a higher recognition rate of land/sea clutter than algorithms based on single feature of backscatter amplitude or linear discriminant analysis. This paper could provide theoretical guidance for improving target location accuracy.

Abstract: A priority based packet scheduling scheme for video streaming (rtPS) over WiMAX networks, which corporate with a resource allocation algorithm, has been proposed in this paper. After resource allocation algorithm allocates all the resources available among service flows, packet scheduling algorithm schedules packets in each packet queue according to current byte loss rate of video streaming queue. Priorities of the video packets in the queue and delays of these packets until all the resources for this flow are used up. Simulation results show that the proposed algorithm has better performance for video streaming and can protect the packets which have higher priority from being left, so the video quality has some improvement.

Abstract: In image matching research, how to ensure that best match’s accuracy of the premise and a significant reduction in the amount of computing is the focus of concern by researchers. Search strategy to find the best match location of the image matching process to determine the amount of computing of image matching, in the existing image matching method are used to traverse search strategy, it is difficult to reduce the amount of computing. This is a common defect of the existing image matching algorithm. Traditional evolutionary algorithm trapped into the local minimum easily. Therefore, based on a simple evolutionary algorithm and combine the base ideology of orthogonal test then applied it to the population initialization, to prevent local convergence to form a new evolutionary algorithm. Compared the traditional evolutionary algorithm, the new algorithm enlarges the searching space and the complexity is not high. We use this new algorithm in image matching; from the results we reach the conclusion: in the optimization precision and the optimization speed, the new algorithm is efficiency for the image match problem.

Abstract: A gray-image face detection algorithm was proposed, in which feature vectors were Gabor wavelet coefficients at 4 scales and 6 orientations. Firstly, feature vectors of training samples and negative samples were separately clustered. Secondly, these clusters were reduced by discriminate analysis. Finally, distribution model of feature vectors was built and average probability was calculated to determine if the testing image was similar to face samples. The experimental results show the algorithm is effective.

Abstract: By means of self-organizing clustering, a new color-based image retrieval method is proposed in the paper. According to the colors’ distributing information in the image, every pixel is assigned a weighing value and thus the initial number of clustering can be confirmed. Therefore, those weighed pixels are clustered and the dominant colors’ statistical features are acquired. Based on the dominant colors spread in the image, the colors’ moment features are extracted to present their spatial features simultaneously. Therefore, the whole image’s content can be expressed from general statistic to partial distributing by the two kinds of features. The experiments verify the method mentioned above more efficiently than those ways based on color histogram

Abstract: This paper presents a novel optimization technique called embedded micro-particle swarm optimization (EMPSO) to solve high-dimensional problems with continuous variables. The proposed EMPSO adopts a population memory which is divided into two portions as the source of diversity, and an external memory to collect particles performing well in an embedded PSO with a very small population size. However, the fact that the new method doesn’t excel in all of the benchmark functions highlights the necessity of developing improvement. Thus an adaptive mutation operator is introduced into EMPSO to remedy the issue. The experimental results show that the improved EMPSO has good performance for solving large-scale optimization problems.

Abstract: This paper proposed a cooperative coevolving particle swarm optimization base on principal component analysis (PCA-CCPSO) algorithm for large-scale and complex problem. In this algorithm, PCA are used to pick up the available particles which gathered the important information of the initialized particles for CCPSO. The Cauchy and Gaussian distributions are used to update the position of the particles and the coevolving subcomponent size of the particles is determined dynamically. The experimental results demonstrate that the convergence speed of PCA-CCPSO is faster than that of CCPSO in solving the large-scale and complex multimodal optimization problems.

Abstract: The particle swarm optimization (PSO) algorithm is a population-based intelligent stochastic search optimization technique, which has already been widely used to various of fields. In this paper, a simple micro-PSO is proposed for high dimensional optimization problem, which is resulted from being introduced escape boundary and perturbation for global optimum. The advantages of the simple micro-PSO are more simple and easily implemented than the previous micro-PSO. Experiments were conducted using Griewank, Rosenbrock, Ackley, Tablets functions. The experimental results demonstrate that the simple micro-PSO are higher optimization precision and faster convergence rate than PSO and robust for the dimension of the optimization problem.

Abstract: Cam mechanisms are widely used in automated machines. Conjugate cams have become popular for its eminent kinematics and dynamic performance in research and in industry. As a commonly used cam mechanism in industry, especially in automatic pin insertion machines, conjugate cams have the advantages of being highly efficient, highly accurate and relatively cheap. A parametric simulation method was used to create a conjugate cam profile. This paper describes the steps used to create 3D models of the conjugate cam and the basic principles used to simulate the motion of cam mechanisms. The motion simulations were done with the parametric 3D modeling method using Creo Parametric Software.

Abstract: We design a portable measurement device which can simultaneously detect ECG (electrocardiograph) and PPG (photoplethysmograph pulse wave) signal, analyze arrhythmia and calculate SpO₂ (oxygen saturation of blood). It consists of two parts: the main and the sub. Besides of the most important part MSP430 MCU, there are front-end amplifiers, filter circuit, Bluetooth module, data management module, keyboard and LCD display module, etc. The device can detect QRS complex and PPG signals in real time. For the Fantasia database and patients, the monitor can correctly judge the QRS complex of ECG signals and PPG signal.