Applied Mechanics and Materials Vols. 241-244

Abstract: The present status of speech emotion recognition was introduced in the paper. The emotional databases of Chinese speech and facial expressions were established with the noise stimulus and movies evoking subjects' emtion. For different emotional states, we analyzed the single-mode speech emotion recognitions based the prosodic features and the geometric features of facial expression. Then, we discussed the bimodal emotion recognition by the use of Gaussian Mixture Model. The experimental results show that, the bimodal emotion recognition rate combined with facial expression is about 6% higher than the single model recognition rate merely using prosodic features.

Abstract: For the path planning problem of search and rescue robot in unknown environment, a bionic learning algorithm was proposed. The GSOM (Growing Self-organizing Map) algorithm was used to build the environment cognitive map. The heuristic search A* algorithm was used to find the global optimal path from initial state to target state. When the local environment was changed, reinforcement learning algorithm based on sensor information was used to guide the search and rescue robot behavior of local path planning. Simulation results show the method effectiveness.

Abstract: It is one of key elements, which makes network high service and stability, to improve intelligent degree and automatic disaster recovery capability of access gateway system .Working state remote monitoring of access gateway, management and control technology are studied, including remote collection and analysis of gateway working state, realizing integration with management and control technology of power, solving working state real time monitoring of access gateway and automatic disaster recovery. Therefore, intelligent auto-control of access gateway system is realized. With system test, the intelligent redundancy gateway system model can improve access gateway early warning and disaster recovery ability obviously.

Abstract: Intelligent tourism is a new field of the research for Chinese tourism industry. Seeing from the appearance to the essence, we can find it is the integration between the tourism and the information industry on the basis of making full use of the modern information technology development. This paper will describe the modern information technology and its application in tourism industry by analyzing the connotation of the intelligent tourism as well as discuss the basic structure and system of it. Besides this, the author will also put forward corresponding constructive advice and measures in the light of the reality of China’s national conditions.

Abstract: The relationship was analyzed among dependability of core attribute and other mono-attributes in terms of mono-attribute dependability and the definition of core attribute based on the method of discernibility matrix to find the core, and the correction was made that the mono-attribute for maximum dependability is not always the core attribute through theory and practice, the value of mono-attribute dependability is independent of its classification capacity on the basis of previous study on the summary of the two extreme properties of mono-attribute dependability.

Abstract: In this paper, a robust and efficient face recognition system based on luminance distribution by using maximum likelihood estimation is proposed. The distribution of luminance components of the face region is acquired and applied to maximum likelihood test for face matching. The experimental results showed that the proposed method has a high recognition rate and requires less computation time.

Abstract: This paper proposes an improved evolutionary computing method called an improved real quantum evolutionary algorithm (IRQEA) based on analysing the traditional quantum evolutionary algorithm. Quantum chromosomes are divided into real components andprobability amplitude components in IRQEA. One real component shows one candidate real solution obtained the optimal solution by gauss variation. Probability amplitude components maintain the population diversity through trigonometric function changes and realize more candidate solutions by less chromosomes, so as to achieve the algorithm’s better optimization abilities. Through the simulation experiments of seven common functions obtaining the optimal values ,it shows that IRQEA have many good characteristics,such as fast convergence rate and best performance.

Abstract: This paper proposes a novel algorithm for image feature extraction, namely, the two-directional two-dimensional locality preserving projection, ((2D)2LPP), which can find an embedding from two directions that not only preserves local information and detect the intrinsic image manifold structure, but also combines the both information between rows and those between columns simultaneously. We also combine the advantages of (2D)2LPP and LDA, and propose a new framework for feature extraction as two-stage: “(2D)2LPP+LDA.” The LDA step is performed to further reduce the dimension of feature matrix in the (2D)2LPP subspace. Experimental results on ORL face databases demonstrate the effectiveness of the proposed methods.

Abstract: A simplified structure of the least square support vector machine (LS-SVM) model is proposed in this paper. Under the premise that the accuracy of LS-SVM model is unchanged, a small amount of training samples are chosen, which further fit this model by LS-SVM modeling. Finally, a typical nonlinear problem is taken as example to test the performance of this simplified model and the simulation results show that this simplified method proposed in this paper is effective.

Abstract: In this paper, we design and implement a system of QR Barcode Recognition based on the mobile phone. This system is based on image processing, consists of image capture model, image pre-processing model and decode model. We propose a new adaptive local threshold method for non-illumination of QR image. The experiment result shows this system is very effective on iphone mobile.