Applied Mechanics and Materials Vols. 303-306

Abstract: The romote intelligent home system design based on WAVECOM Q2406B Module and ARM7 S3C44B0X was elaborated, GPRS technology was used to realize remote control, RS485 bus technique was used to net the home system, and embedded system was used to establish the developing platform of Home Intelligent controller which can realize intelligent management and control of home applications. Partial hardware electric diagram and software flowchart were provided. Field using indicates that this system is economical and flexible.

Abstract: The wide use of GUI (Graphic User Interface - graphical User Interface) is one of the great achievements in today's computer development. μC/GUI, as one of the mature GUI technology, becomes more and more common in embedded products. It has a small kernel, occupying less resources, high performance and high reliability etc, and can be designed as powerful and complex man-machine interface for embedded system. it uses the STM32 development board as the carrier. Software system is composed of hardware drivers, μC/OS-Ⅱ real-time operating system, FATFS file system, μC/GUI graphical interface system and so on. Analyzing the process and steps of μC/GUI transplantation, through the design of interface we can realizes simple human-computer interaction function. After tested, it works well.

Abstract: It’s a new idea to make computers be able to obtain “sensations” from a color image through some unsupervised ways. To let the idea come into true, a granule-based model, based on granular computing(GrC) which is a new way to simulate human thinking to help solve complicated problems in the field of computational intelligence, is proposed for color image processing. First, this paper deems data a hypercube, defines two new concepts, attribute granules(AtG) and connected granules(CoG), and presents the definitions of the granule-based model. Then, in order to fulfill the granule-based model, this paper designs a single attribute analyser(SAA), defines some theorems and lemmas related to decomposition, and describes the processing of extracting all attibute granules. Experimental results on over 300 color images show that the proposed analyser is accurate, robust, high-speed, and able to provide computers with “sensations”.

Abstract: Aiming at effectively overcoming the disadvantages of traditional evolutionary algorithm which converge slowly and easily run into local extremism, an improved adaptive evolutionary algorithms is proposed. Firstly, in order to choose the optimal objective fitness value from the population in every generation, the absolute and relative fitness are defined. Secondly, fuzzy technique is adopted to adjust the weights of objective functions, crossover probability, mutation probability, crossover positions and mutation positions during the iterative process. Finally, three classical test functions are given to illustrate the validity of improved adaptive evolutionary algorithm, simulation results show that the diversity and practicability of the optimal solution set are better by using the proposed method than other multi-objective optimization methods.

Abstract: Most existing methods of active support vector machine (ASVM) focus on the samples nearby the current separating hyperplane, which ignore some support vector (SV) samples which are far form the separating hyperplane, also pay not attention on whether the current separating hyperplane is close to the optimal one. In this paper a new classification method of ASVM based on improved probability-calculation method is presented. It not only presents a new method of calculating probability, but also measures the degree of closeness of the current separating hyperplane to the actual separating hyperplane by a confidence factor. Experimental results show the superiority of our proposed method both in classification accuracy and computing cost.

Abstract: When data mining involves document processing, extracting abstract information from the content of documents has become an essential procedure. The core idea of the algorithms of abstract extraction represented by Luhn is extracting the abstract merely from the sentences which contain frequent words in the essay. However, these algorithms fail to extract from the full text in a deeper semantic level. Therefore, the accuracy of the traditional abstract extraction algorithm needs to be enhanced. In order to improve the accuracy, we propose a method which can improve the performance of the algorithm of candidate key words extraction by using the substitute words and considering the semantic meanings of the candidate key words.

Abstract: This text describes the research work in machine learning framework for the assessment of teaching quality , mainly focused on the analysis of data on information technology in the teaching process , and the use of artificial neural network method, the experiment , the experimental results reflect the level of teaching quality analysis . Experimental results show that the use of machine learning methods can indeed make a positive contribution to the teaching quality assessment .

Abstract: The human sensory test is often used to obtain the sensory quantities of odors, however, the fluctuation of results due to the experts condition can cause discrepancies among panelists. We have developed an artificial odor recognition system using a quartz resonator sensor and backpropagation neural networks as the pattern recognition system in order to eliminate the disadvantage of human panelist system. The backpropagation neural networks shows high recognition rate for single component odor, however, become very low when it is used to discriminate mixture fragrances odor. In this paper we have proposed an ensemble of backpropagation neural networks as the pattern recognition system, and by using the ensemble learning mechanisms, the recognition rate is significantly increased, especially when using ensemble neural networks with five components.

Abstract: To solve constrained optimization problems, an Oracle penalty method-based comprehensive learning particle swarm optimization (OBCLPSO) algorithm was proposed. First, original Oracle penalty was modified. Secondly, the modified Oracle penalty method was combine with comprehensive learning particle swarm optimization algorithm. Finally, experimental results and comparisons were given to demonstrate the optimization performances of OBCLPSO. The results show that the proposed algorithm is a very competitive approach for constrained optimization problems.

Abstract: According to the nature of 16 - the intersection model and the constraints of the broad boundary region, get 67 topological relations that can be realized between a concave region and a simple broad boundary region. We realize the reasoning of topological relations between a concave region and a simple broad boundary region, and establish topology model of typhoon rainfall warning, and provide reference for expand of the related topology model applications.