Applied Mechanics and Materials Vols. 20-23

Abstract: The importance of case-retrieving method selection in the CBR system is analyzed, and the defaults of traditional retrieving methods which make use of fuzzy distance to describe the distance in the similar cases are pointed out. A model for case- retrieving based on AHP is presented after the introduction of the basic principle and process of CBR and AHP. With the development environment of CGI, a prototype system is developed, and the running interface is shown.

Abstract: In this paper, we propose a cross-layer protocol that is based on a form of cooperative transmission called Virtual Multi-Input Single-Output (VMISO). Specifically, we discuss the influence of rate, cluster size, and transmission range of the VMISO link on the whole performance improvements, where the key physical layer property that we focus on is an enlarged transmission range due to cooperative diversity. Further, the new protocol, termed the Joint Cross-layer Cooperative Transmission Protocol (JCCTP) including the VMISO routing protocol and the novel MAC protocol, presents the distributed approach of using VMISO links with a fixed cluster size, a given rate, and a certain transmission range, where we leverage the translation of physical layer advantages into higher layer better performances. Finally, we evaluate JCCTP with a flat Rayleigh fading channel model that accurately captures the nature of VMISO transmissions. As compared to using only SISO links and other VMISO links, our work achieves a great increase in the end-to-end throughput and a sharp decline in the end-to-end delay.

Abstract: This paper introduces a robust method for automatically matching features in images corresponding to the same physical point on an object captured from two arbitrary viewpoints. Starting from detected line segments in two or more images using phase congruency, the pairs of line segments are characterized by indices that encode the relative positions and orientations of those segments. The encoding indices are invariant with respect to viewpoint changes and the corresponding line segments between the images can be found by them. The feature matching is optimized for image warping where we wish to ignore unreliable matches at the expense of reducing the number of feature matches. This approach can be applied to the image warping to realize its automatism. Results are presented on real images.

Abstract: Assistant driving systems have attracted more and more attention during recent years. Among them fatigue detection plays a key role because of its close relationship with accidents. In this paper, we propose a novel method which uses eye locating and tracking technique to detect driver fatigue. The present method consists of four steps. First, we employ Adaboost and Haar-like features to construct a robust classifier which can detect eye corner points. Second, we use extended parabolic Hough transformation to construct the parabola curves of upper and lower eyelid. Then, particle filter algorithm is used to track eye corner points in video sequences. Finally, the driver fatigue state is estimated through computing the frequency of eye opening and closing intervals. Experimental results from real environment datasets are given in our discussion as well.

Abstract: Structural damage detection and health monitoring is very important in many applications, and a key related issue is the method of damage detection. In this paper, Fuzzy Least Square Support Vector Machine (FLS-SVM) is constructed by combining Fuzzy Logic with LS-SVM, and a real-coded Quantum Genetic Algorithm (QGA) is applied to optimize parameters of FLS-SVM. Then, the method of FLS-SVM integrated QGA is used to detect damages for fiber smart structures. The testing results show FLS-SVM possesses the higher detecting accuracy and the bitter dissemination ability than LS-SVM under the same conditions, and the parameters of FLS-SVM can be effectively optimized by the real-coded QGA. The proposed method of FLS-SVM integrated QGA is effective and efficient for structural damage detection.

Abstract: With the rapid development of computer network, multimedia technology for e-education is widely applied in everywhere. With increasing availability of spatial data, there is an urgent need to develop way and means for providing easy accessibility and promote spatial data sharing. In this paper, we analyze the multimedia technology, discuss the multimedia technology in video and audio. Multimedia technology has promoted a large amount of research in the area of image and video processing. With the support of optical network, multimedia system can offer a lot of applications in e-learning.

Abstract: Neural network (NN) employed to settle network anomaly has become prevalent. However, traditional training algorithm for NN is not optimum, that is, often suboptimum, and encountering complicated network anomaly, an adaptive yet efficient NN or hybrid NN model should be better considered. Therefore, this paper proposes a novel network anomaly detection method employing wavelet fuzzy neural network (WFNN) to use modified Quantum-Behaved Particle Swarm Optimization (QPSO). In this paper, wavelet transform is applied to extract fault characteristics from the anomaly state. Fuzzy theory and neural network are employed to fuzzify the extracted information. Wavelet is then integrated with fuzzy neural network to form the wavelet fuzzy neural network (WFNN). The Quantum-Behaved Particle Swarm Optimization, which outperforms other optimization algorithm considerably on its simple architecture and fast convergence, has previously applied to solve optimum problem. However, the QPSO also has its own shortcomings. So, there exists a modified QPSO which is used to train WFNN in this paper. Experimental result on KDD99 intrusion detection datasets shows that this WFNN using the novel training algorithm has high detection rate while maintaining a low false positive rate.

Abstract: To develop a good quality of hypoid gear drive, the authors test the vibration and noise of two kinds of hypoid gear drives under different working conditions. The test object is a pair of hypoid gear drive used in the back axle of one minivan and a designed hypoid gear drive with high teeth based on the former. The results indicate that the hypoid gear drive with high teeth has lower vibration and noise.

Abstract: Modularization is an important design method cope with complicated and diversified products.Firstly, idea of quantitative calculation about modules matching base on attribute matching functions is proposed. Secondly, matching problems between two modules and among multi-modules are studied deeply by using graph theory. Then, a simple example is given to show the process of quantitative calculation and prove its feasibility. Finally, conclusions and future studies are presented.

Abstract: Much progress has achieved in forging technology, and it has become a popular process for preparation of intricate parts. As a case, a finite element model of the square block forging process was established by DEFORM software. The deformation, distribution and development trend of velocity, mean stress, equivalent strain and equivalent strain rate were predicted. The load-time variation curves in X, Y and Z direction were obtained too. Based on the numerical simulation result, we had a better understanding of the forging process.