Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-28 Cooperative journals: 《计算机应用研究》
Abstract： In view of the imprecision problem for PAD(Pleasure、Arousal、Dominance) prediction, this paper proposed clustering PSO-LSSVM model combineing Least Squares Support Vector Machine(LSSVM) optimized by Particle Swarm Optimization(PSO) and affective clustering analysis. Firstly, selecting three emotion speeches of TYUT2.0 emotional speech database and Berlin voice library, and extracting emotion features. Establishing Single emotional dimension PSO-LSSVM models for three single emotion and the mixed emotion dimension PSO-LSSVM model for three emotions based on emotion features and P, A and D values. The mothod used mixed emotion dimension PSO-LSSVM model to predict the P, A and D values of the test set, and calculated the distance between the predictive PAD and the PAD of the basic emotion. Finally clustering the emotion whose distance is greater than the threshold into mixed emotion, and clustering the emotion whose distance is less than the threshold into the nearest emotions, then using the corresponding emotional dimension regression model to predict its P, A and D. The research showed that the predictive error of clustering PSO-LSSVM regression model to P, A and D was smaller than that of LSSVM and PSO-LSSVM model, and the correlation between the predicted value and the tagged value was stronger. So the clustering PSO-LSSVM regression model is more reliable and accurate in predicting P, A and D values.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-12-13 Cooperative journals: 《计算机应用研究》
Abstract： To solve the problem that iterative closest point (ICP) algorithm has a single feature for searching and low accuracy for registration, this paper proposed a point cloud registration algorithm that based on multiple-feature matching. It chose the improved adaptive octree algorithm to segment the point cloud. Then calculated the multiple features of the points after performed moving least squares (MLS) algorithm to fit the leaf nodes. Next, this algorithm introduced the point pairs similarity that based on multiple features to establish the matching points. Lastly, computed the rotation matrix and translation matrix to achieve registration. Experiments show that this algorithm can effectively improve the accuracy of registration on the basis of keeping the point cloud registration speed high. And with the number of point sets increasing, the trend of accuracy for this method is increasing.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-12-13 Cooperative journals: 《计算机应用研究》
Abstract： In the wireless sensor network based on mobile beacon nodes, the path planning problem of mobile beacon nodes has important influence on positioning performance. However , the existing path planning method does not take full account of the distribution of unknown nodes in the networks, the positioning efficiency is low and the cost is large. Therefore, this paper designed a path planning method of mobile beacon node: Firstly, determined the position of the virtual beacon nodes, and the number by making full use of sensor nodes distribution; then proposed the grey wolf optimization algorithm of nonlinear dynamic change convergence factor based on Gaussian decreasing strategy . This algorithm is used in the TSP algorithm to solve the path planning problem, and can obtain the shortest moving path of the mobile beacon node. Simulation results show that the proposed method can effectively improve the locatization coverage and save the localization cost.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-08-13 Cooperative journals: 《计算机应用研究》
Abstract： Currently the visual SLAM system can only output the camera's motion trajectory, but it cannot generate maps for path planning and navigation. In order to solve this problem, this paper proposes a real-time grid map algorithm based on ORB-SLAM2. Firstly, 爐he爌aper establishes an inverse sensor model (ISM) for visual SLAM. 燬econdly, 爐he paper rearranges the construction mechanism of the grid map algorithm for ISM model and then derives it in detail. Finally, the paper introduces the specific implementation scheme of ORB-SLAM2 grid map construction. Through experiments, the algorithm shows its feasibility based on the analysis of the ISM model and the grid map model. Furthermore, the real-time experiments using monocular camera and RGB-D camera can realize爐he real-time construction of the grid map and clearly show the positions of obstacles, which verifies the effectiveness of the algorithm.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-24 Cooperative journals: 《计算机应用研究》
Abstract： Clinical studies have shown that J wave can be used as a high risk early warning index of some heart diseases. In view of the shortcomings of J wave diagnosis only by the clinicians’ experiences, which can easily lead to misdiagnosis. From the perspective of signal processing, this paper proposed a J wave automatic identification method. This method extracted the energy features of electrocardiogram data after the extreme-point symmetric mode decomposition and higher order statistics, combined linear and nonlinear features, and adopted the principal component analysis to reduce the dimension of the features. Finally, it used support vector machine optimized by artificial bee colony algorithm to realize automatic identification of J wave. The experimental results show that the average accuracy rate of identifying J wave is 97.3%, which can effectively identify the J wave.
Hits
Hits
Downloads
Comment