Advanced Materials Research Vols. 255-260

Abstract: To solve the problem of Deep Web data sources topic classification, this paper proposed a quantum self-organization feature mapping network model(DR-QSOFM)with a classification algorithm. DR-QSOFM combines quantum computation and traditional SOFM, and relies the feature vectors and target vectors incoordinately in different phases of training, making a more centralized distribution of winner neurons in competitive layer and more obvious boundaries among clusters. Some experiments are designed and done on the expanded TEL-8 dataset to test the validity of DR-QSOFM.

Abstract: Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we present a new approach using structural similarity index for assessing quality in image fusion. The advantages of our measures are that they do not require a reference image and can be easily computed. Numerous simulations demonstrate that our measures are conform to subjective evaluations and can be able to assess different image fusion methods.

Abstract: This study investigates the effects of temperature on micro-electro mechanical system (MEMS) gyroscope null drift and methods and efficiency of temperature compensation. First, this study uses in-house-designed inertial measurement units (IMUs) to perform temperature effect testing. The inertial measurement unit is placed into the temperature control chamber. Then, the temperature is gradually increased from 25 °C to 80 °C at approximately 0.8 degrees per minute. After that, the temperature is decreased to -40 °C and then returning to 25 °C. During these temperature variations, the temperature and static gyroscope output observes the gyroscope null drift phenomenon. The results clearly demonstrate the effects of temperature on gyroscope null voltage. A temperature calibration mechanism is established by using a neural network model. With the temperature calibration, the attitude computation problem due to gyro drifts can be improved significantly.

Abstract: The use of least squares support vector machine (LSSVM), a novel machine learning method, for classification and function approximation has increased over the past few years especially due to its high generalization performance. However, LSSVM is plagued by the drawback that the hyper-parameters, which largely determine the quality of LSSVM models, have to be defined by the user, and this increases the difficulty of applying LSSVM and limits its use on academic and industrial platforms. In this paper we present a novel method of automatically tuning the hyper-parameters of LSSVM based on colonial competitive algorithm (CCA), a newly developed evolutionary algorithm inspired by imperialistic competition mechanism. To show the efficacy of the CCA assisted LSSVM methodology, we have tested it on several benchmark examples. The study suggests that proposed paradigm can be a competitive and powerful tool for classification and function approximation.

Abstract: Nowadays P2P is the premier data distribution technology which tops Internet traffic flow chart. It becomes more and more important to optimize the data flow of P2P traffic. However, there is no general standard for measuring which data distribution scheme is better. A network expense model is proposed for this purpose. By observing the data flows which are produced by P2P, we can calculate the network expense of any data distribution scheme. Now there is a unified standard for evaluating the influence of different data distribution schemes to the network. According to this model, the network expense of a few typical P2P data distributions scheme over the Internet is calculated. Judging from the results, a topology-aware P2P can generate more balanced flows to save the bandwidth of backbone network. Network expense model provide a fundamental tool for optimizing the P2P data distribution.

Abstract: A gait control system is designed for walking a slope movement according to the features of biped robot, Two BP networks are introduced into train the walking trajectory of robot and the optimal trajectory is generated by the new evolutionary approach based on particle swarm optimization. Additionally, online environmental information is collected as neural network input, and necessary joint trajectory is output for the movement. Simulations with Matlab and experiments on NAO humanoid robot testify the efficiency of the method.

Abstract: The robot vision system is the critical component of the soccer robot, in football competition, robot perceive the most of the information from the vision system. Because of the variable illumination conditions, the traditional image segmentation method based on color information is not satisfactory. Based on the color information and shape information of the object, this paper proposes a object recognition algorithm that combine color image segmentation with edge detection. This algorithm implement image segmentation use color information in the HSV color space obtain the pixel of the object, then use this pixel implement edge detection to recognize the object. Experiments show that this algorithm can recognize the object exactly in the different illumination conditions, satisfy the requirement of the competition.

Abstract: Removed due to plagiarism. Original paper is published at: http://ieeexplore.ieee.org/stamp/stamp.jsptp=&arnumber=5256313&isnumber=5446457

Abstract: Aimed at the defects of security monitoring system in intelligent building with complicated design, higher production cost, uneasy to installation, and not suitable for ordinary family, this paper combined with the development needs of intelligent building, and designed a remote network security monitoring system based on Internet, used AT91SAM9260 as the main controller and used embedded technology, Internet technology, video compression/decompression technology and so on. So that users can detect the illegal intrusion and fire hazards at home in real-time, through computers or mobile phones. Then the validity and efficiency of the system was validated via test-experiment. The results show that this system has several merits such as good safety, good generality, simple operation, easy maintenance, low cost and so on. It can meet the needs of security monitoring for an ordinary home.

Abstract: During the last two decades, many approaches to corporate and industrial environmental management as well as tools and sustainability programmes have been created and implemented. Sustainable business is business that is rewarding in economic, social and ecological approach people creating these new ways of doing business [1].