Applied Mechanics and Materials Vols. 427-429

Abstract: Parsing Chinese is a key issue in NLP. Many controversies arise from Chinese special sentence patterns. This paper puts forward a novel model Feature Structure theory to resolve the semantic labeling of Chinese special sentence patterns. We analyze the difficulties in annotating these sentences, and compare Feature Structure with dependency structure. Feature Structure represents more semantic information and more semantic relations. Feature Graph is a recursive undirected graph, allows nesting and multiple correlations.

Abstract: In allusion to the problem of launching precision, it carried on the research of the effect of shipborne missile launch position based on the spectrum analysis technology. A rigid-flexible coupling integrative model of ship movement and missile launch was built by use of virtual prototype technology. Simulation analyses on a variety of conditions were automatic conducted by launch time parameterized scripting language, and missile muzzle attitude parameters of different launch position were gained. By using of spectrum analysis which is based on FFT, the missile dynamic responsive was analyzed, and the relationship between launch position and accuracy was established. Then the position of the weapon system can be designed according to the specific motion characteristics of ship. The research result is also constructive to the selecting of suitable launch position.

Abstract: Depending on image processing system, a major sub-system in foreign object debris (FOD) detecting system on the runway, FOD image will be observed efficiently and rapidly with few economy costs and highly accuracy and reliability so as to ensure the passengers safety. The thesis analyses the characteristics and principles of wavelet transformation and applies the theory in image processing under poor visual background for identifying the FODs shape and mark characteristic point on the runway by programming in MATLAB. Besides that, it brings about profound significance for realizing the real-time detecting on the FOD and testing the feasibility and efficiency.

Abstract: Battlefield situation assessment has a positive significance on improving the efficiency of commanding decision-making; moreover, battlefield situation assessment cannot be made successfully without the support of some integrated and exact intelligence data. In this paper, basing on the demand of identifying the battlefield situation, the corresponding knowledge context database was first discussed; on this basic, construction of the intelligence data warehouses framework was explored. Then, the study of data mining based on the intelligence data warehouse was made from the view of a holistic conception, and a detailed arithmetic was presented by making use of the tactic from data mining driven fishbone.

Abstract: Extreme learning machine (ELM) as a neural network algorithm has shown its good performance in regression or classification applications, but it has a weak robustness. In this paper, a new approach called The Adaptive Ensemble Of OP-ELM using Forward-Backward Selection (AEOP-ELM) is presented, it consists of two significant steps, firstly, we use forward-Backward selection algorithm to select the inputs which will ensure the robustness of the output, then, we train several independent OP-ELM models, and we test them iteratively to find the adaptive weights which will improve the accuracy of the output. The experiments indicate the AEOP-ELM achieves a better robustness than the original ELM as well as a better accuracy.

Abstract: Sparse extended information filter-based simultaneous localization and mapping (SEIF-based SLAM) algorithm can reflect significant advantages in terms of computation time and storage memories. However, SEIF-SLAM is easily prone to overconfidence due to sparsification strategy. In this paper we will consider the time consumption and information loss of sparse operation, and get the optimal sparse time. In order to verify the feasibility of sparsification, a sea trial for autonomous underwater vehicle (AUV) C-Ranger was conducted in Tuandao Bay. The experimental results will show the improved algorithm is much more effective and accurate comparedwithothermethods.

Abstract: The directional warhead of ATBM missile requires accurate initiation delay time and the initiating direction to obey effective damage for TBM, which needs to estimate the relative motion parameters to improve the accuracy. A debiased converted measurement Kalman Filter is presented and used for the estimation of TBMs position in body coordinate system of ATBM missile and the relative velocity. Results of simulation shows that this algorithm has high estimation precision for the parameters and satisfies the need of building initiating control algorithm for The directional warhead of ATBM missile.

Abstract: With the mass production of Electric Vehicles, end of line test of Electric Vehiles has become an important research topic.In this paper, a scheme of the system with a portable computer is establish for thepractical application to the end of line test based on CAN bus, and then design and research of the testing system software are followed. To develop establish the system scheme, we study in depth and explore test methods and management, and design two test modes in view of the practicality and re-usability of the test system. In the process of system software development, we program in LabVIEW, manage the test items in NI TestStand, make a research and optimization of Microsoft Office Access database connection for both software, and design user interface program of database maintenance and management finally. Commissioning not only verifies practical performance of the test system in the aspects of testing, data processing and others, but also feedbacks the reference information to enhance and improve the stability and re-usability of the system based on CAN bus.

Abstract: With the rapid development of embedded technology, mobile devices have been widely used than before. Face recognition has also been taken as a key application with PCA as the basic algorithm. Though PCA can provide basic information processing, it still has some problems to be used for mobile devices. The movement of the faces increases the difficulty of the recognition and the limited resources of mobile devices propose more constraints to traditional PCA algorithm. A novel approach is presented to optimize PCA based face recognition for better performance and faster recognition speed. The experiments show that the new approach can achieve its target though the optimization.

Abstract: In this paper, a Multi-Classification SVMs classifier in terms of the theory of SVM is presented and which can tell the various properties of panel surface. The sample data is obtained by preprocessing the data which is measured through the flatness detector in the cold-rolled operation. Using the supervised method of one-class-against-the-rest to train Multi-Classification SVMs classifier. Finally, testing the performance of classifier by test data. The simulation results show that the proposed method performs high recognition rate in processing little sample data and has good ability of generalization. To the flatness recognition, this is a new research method.