Applied Mechanics and Materials Vols. 241-244

Abstract: Character image clustering can find similar characters which have much reference value to ancient character identification. But the classical clustering method depends much on the threshold. To alter the threshold dynamically and get result in real time, a improved clustering method is proposed. The classical BIRCH CF tree was amended to chain hierarchical structure, and the new tree was built from bottom to top with KNN clustering method. Based on this structure, relative similarity degree was transformed to character number in clustering result. By converting the dynamic threshold clustering problem to finding the different cluster range, this method could get the clustering result in real time.

Abstract: No matter in civil remote sensing or in military investigation, infrared images have an extensive application value. According to the characteristics of the infrared images, in this paper, we build comprehensive feature vectors of airplane identification based on comprehensive consideration of the characteristics of infrared images, including boundary invariant moments , normalized moment of inertia and geometric features. Identifying an air plane by calculating the comparability of feature vector between template image and the image to be identified, the algorithm has been proved by experiments to have a better stability and robustness.

Abstract: The immune genetic algorithm is a kind of heuristic algorithm which simulates the biological immune system and introduces the genetic operator to its immune operator. Conquering the inherent defects of genetic algorithm that the convergence direction can not be easily controlled so as to result in the prematureness；it is characterized by a better global search and memory ability. The basic principles and solving steps of the immune genetic algorithm are briefly introduced in this paper. The immune genetic algorithm is applied to the survey data processing and experimental results show that this method can be practicably and effectively applied to the survey data processing.

Abstract: A face recognition method based on discrete cosine transform and Gabor transform is proposed. A FPGA-based platform on DE2-115 board is designed by SOPC. We compared our methods with the method based on PC. In the experiments, the nearest neighbor classifier is used to recognize different faces from the Yale face database. Experimental results show that the proposed

Abstract: This paper mainly concentrated on the method of improving the dispatching trucks working at a container terminal and built the multi-agent model for the dispatching job. The contract net protocol was taken as the communication ones among agents, and the analytic hierarchy process was also applied for the decision support for container trucks dispatching.

Abstract: Auto-search is one of the key steps in digital signal processing for Loran-C receivers, however, for digital sampling Loran-C signal, the principle search algorithm is unable to realize signal search veraciously because of the asynchronism between sampling clock and transmitting station clock. For this question, an auto-search algorithm based on subsection correlation for Loran-C is presented after analyzing the principle search algorithm. The experiment results show that for the received digital Loran-C signal, there are several correlation and accumulation values of master and secondary stations to exceed the search thresholds; the maximum correlation and accumulation value of the presented algorithm is far higher than that of the principle algorithm. That is to say, the presented algorithm can search the arrival time of master and secondary station successfully, solve the problem of clock asynchronism effectively, and enhance the search sensitivity of the receiver, which have great significance for digital processing of Loran-C signal and the engineering realization of Loran-C digital receiver.

Abstract: To reduce power usage and meet user satisfaction for indoor environmental condition, an intelligent light control system was analyzed. It designed sensor node and light control module to judge open the light or not and adjust the light levels according to indoor light intensity. The results show the advantage of the system based on wireless sensor network.

Abstract: To overcome the problem of lower training speed and difficulty parameter selection in traditional support vector machine (SVM), a method based on extreme learning machine (ELM) for lithofacies recognition is presented in this paper. ELM is a new learning algorithm with single-hidden layer feedforward neural networks (SLFNN). Not only it can simplify the parameter selection process, but also improve the training speed of the network learning. By determining the optimal parameters, the lithofacies classification model is established, and the classification result of ELM is also compared to traditional SVM. The experimental results show that, ELM with less number of neurons has similar classification accuracy compared to SVM, and it is easier to select the parameters which significantly reduce the training speed. The feasibility of ELM for lithofacies recognition and the availability of the algorithm are verified and validated

Abstract: Fuzzy theory is one of the newly adduced self-adaptive strategies,which is applied to dynamically adjust the parameters of genetic algorithms for the purpose of enhancing the performance.In this paper, the financial time series analysis and forecasting as the main case study to the theory of soft computing technology framework that focuses on the fuzzy logic genetic algorithms(FGA) as a method of integration. the financial time series forecasting model based on fuzzy theory and genetic algorithms was built. the ShangZheng index cards as an example. The experimental results show that FGA perform s much better than BP neural network，not only in the precision.but also in the searching speed.The hybrid algorithm has a strong feasibility and superiority.

Abstract: The paper proposes an automatic modulation recognition scheme based on instantaneous features of intercepted signals. The modulation classifier can discriminate modulations such as Amplitude Modulation (AM), Double Side Band (DSB), Single Side Band (SSB), Frequency Modulation (FM), M-ary Amplitude Shift Keying (M-ASK), M-ary Frequency Shift Keying (M-FSK), M-ary Phase Shift Keying (M-PSK) and M-ary Quadrature Amplitude Modulation (M-QAM) without any prior information. The scheme is with simple structure, computationally simpler, and suitable for real-time processing. And the recognition parameters are anti-noise, and insensitive to frequency offset, phase offset and timing error. To evaluate the performance of the scheme, several experiments with signals in Additive White Gaussian Noise (AWGN) channel were carried out in the MATLAB by varying the values of both the main modulation parameters and the signal-to-noise ratios (SNRs). The results show that the approach can achieve high recognition accuracy even at low SNR.