Advanced Materials Research Vols. 734-737

Abstract: According to advantages and disadvantages of the traditional data center network structure ,this paper propose a new data center network structure base on BCube and DCell. The new structure is mainly improved based on the scalability, fault tolerance, the throughput

Abstract: Gesture recognition has many applications in fields such as the intelligent robot, human computer interaction and so on. The classical BP neural network has its advantages in modeling the highly nonlinear mapping from features to gesture meanings, and could avoid hard-coded feature extraction. However, it usually takes a rather long training and testing time, especially in dealing with redundant high dimensional data. To address this drawback, we combine the BP neural network and PCA, and propose an improved algorithm. Experiments demonstrate the feasibility and efficiency of the proposed algorithm by comparing with the classical one.

Abstract: A new piecewise rational re-parameterization of a polynomial curve is presented. The method relies on a parametric polygonal decomposition method. With the proposed piecewise rational re-parameterization method, the optimal parameterization can be reached, and the optimal parameterizations asymptotic convergence to the arc-length parameterization is analyzed. Computing instances demonstrates the efficiency of the proposed method.

Abstract: Due to noises and instrument defects, frequency-or time-domain measuring curves of a certain signal are usually different. It is then of great importance to recognize which signal a measuring curve belongs to, resulting in a classification problem. Considering the slow running speed of the commonly used classifier SVM, we propose a novel classification algorithm based on interval estimation. The complexity of our algorithm is linear to the class number. Experiment results demonstrate the feasibility and efficiency of the proposed algorithm.

Abstract: This paper proposes two complementary procedures for assessing the indoor global comfort: the first one, prevalently objective, is based on the acquisition of microclimate measured data and computed subjective values; the second one, that is purely subjective, uses a questionnaire drawn from the ISO/DP 10551 Recommendation. An application to some lecture-halls is here showed

Abstract: Aiming at the phenomenon that the chaff and corner reflector released by surface ship can influence the selection of missile seeker, this paper proposed a multi-target selection method based on the prior information of false targets distribution and Support Vector Machine (SVM). By analyzing the false targets distribution law we obtain two classification principles, which are used to train the SVM studies the true and false target characteristics. The trained SVM is applied to the seeker in the target selection. This method has advantages of simple programming and high classification accuracy, and the simulation experiment in this paper confirms the correctness and effectiveness of this method.

Abstract: The attack from small speedboat and underwater robot is becoming more and more serious. And most powerful countries have installed underwater surveillance systems to protect port, ship, seashore depository and anchorage. The detection technology of underwater target is the most important technology in the process of surveillance. In order to take good advantage of the target’s geometry characteristic and classification function of SVM(Support Vector Machine), an algorithm for imaging sonar target detection based on geometry characteristic and SVM is proposed in the paper. The experiment results are presented and show that this algorithm is in high detection rate under complex underwater circumstance.

Abstract: Aiming at anhydrous bridge automatically identification in aerial images, an anhydrous bridge recognition algorithm based on the geometric characteristics is proposed. Firstly, the original image is do threshold segmentation to get binary image. Secondly, binary image is do morphological processed to get bridge area enhanced image and bridge area corrosion image, and these two bridge area are subtracted to extract suspected bridge area based on bridge rectangle feature. Finally, bridge regional area is positioned according to the straight-line characteristics of the bridge. Experimental results show the proposed algorithm can accurately identify the anhydrous bridge effectively. Key words: aerial image; anhydrous bridges identification; edge detection ; straight line extraction ; geometric features

Abstract: In this paper we propose an automatic cloud service platform for learning from large-scale data. Firstly, we design an event-driven mechanism for controlling data service delivery automatically and intelligently in order to guarantee end-to-end service quality and efficiency. Then a data management platform is provided to collect, process and storage batch data and real-time data. Furthermore, we suggest a method of enhancing algorithm for learning from large-scale data, analyze learning process, and elaborate that algorithm performance can be enhanced constantly along with growth of data set.

Abstract: nformatization construction is a major issue of current social construction, and the technology of multi-source information fusion is an integral part of the information construction. This paper provides an overview of the technology of the multi-source information fusion, gives an introduction of the application of the technology of multi-source information fusion in industrial monitoring and fault diagnosis, and gives the direction of development and trends of the technology in the future according to the main problems in the research of the technology of multi-source information fusion.