Advanced Materials Research Vols. 225-226

Abstract: Analyze the ways to get fault information for heavy equipment fault diagnosis system, which are the control system of the device, layout sensors to get the key performance parameters, and human-computer interaction. In order to improve accuracy and efficiency of the diagnostic system, the methods of fault location tree retrieval and similar case retrieval are applied respectively according to the difference of fault information content in the diagnosis information database. The diagnosis system introduced in the paper gets effective initial application in the heavy equipment fault diagnosis system.

Abstract: Human Skin Color(HSC) features have been widely used in video moving human positioning. However, in complex background video sequences, due to illumination changes or other moving objects which have similar HSC regions, the effect of moving human positioning is not satisfactory. A new method of moving human positioning applied on complex background video sequences is presented in this paper. Firstly, brightness information of the video sequence images is detected and analyzed based on HSV color model. Secondly, adopt the multi frame subtraction method to extract the moving object regions from motionless background. Then, the regions with distinctive HSC features are separated from other moving objects using the data fusion model of HSC and brightness information. Finally, identify human object among regions with HSC features according to the prior knowledge of human. The experimental results show that the method provided in this paper is effective in moving human positioning of complex background video, and has the strong illumination change adaptability and anti-jamming ability.

Abstract: An unascertained measure-entropy evaluation model for the program selection of shaft construction under complex conditions is established so that a scientific and effective decision making method is provided in this paper, the evaluation model of shaft construction is established based on unascertained measure and entropy weight theory, then, the model proposed in this paper is applied to evaluate three shaft construction program comprehensively, and the evaluation results show validity and applicability of the model.

Abstract: With the rapid development and integration of Mobile communications, Internet and GIS technology, as well as the diversity of market demand, the commercialization of wireless location business process was accelerated. With the development of logistics information system, the combination of wireless location technology and logistics are increasingly closed. In this paper we introduced several kinds of popular wireless positioning technology, analyzed many factors which the operator selection of these technologies need to considered, and then discussed the necessity of combing the wireless location technology with GIS technology, and provided the architecture of system integration. Finally, the paper summarized the integration system in logistics of some typical application.

Abstract: The graph isomorphism problem is to study the relationship between two graphs which seem to be different, but essentially identically. A novel algorithm based on the degree tree is proposed, where each node of the tree describes a given vertex and its neighboring information of a graph. Two vertexes in different graphs are regarded as mapping if the corresponding nodes and all their junior nodes are similar. Hence by comparing their degree trees, two graphs can be determined whether matching or not, and the mapping vertexes can be found. Experimental results show the approach’s performance.

Abstract: At present, the existed incremental mining algorithms can not make full use of the results of the previous mining. When the support is changed, the algorithms need to mine the database once again. In this paper, we propose an incremental mining algorithm of sequential patterns based on frequent sequence tree, called IMFST. When the database is updated and the support is changed, IMFST is divided into four kinds of situations to update the frequent sequence tree, and finally gets all sequential patterns. IMFST uses two kinds of pruning strategies to reduece the size of the projected databases. When the support is changed and the support is no less than the frequent sequence tree support threshold, IMFST can find all the sequential patterns without mining the database once again. Experiments show that IMFST outperforms PrefixSpan and IncSpan in time cost.

Abstract: This paper deals with finite-time control problem of a class of fuzzy discrete-time system with time-varying norm-bounded disturbance. Applying the Lyapunov function theory and matrix inequalities, a sufficient condition is obtained for robust finite-time stability and the fuzzy system satisfies a prescribed level for the effect of the disturbance input on the controlled output.

Abstract: Based on principles of human heart auscultation and the associated signal processing technology, we designed and manufactured "a double-header two-way voice auscultation detection device". The paper introduced a special human feature extraction method which is based on improved circle convolution (ICC) slicing algorithm combined with independent sub-band function (ISF). Follow we adopt a fire-new classification technology namely s1 and s2 model which is through two recognition steps to get different human’s heart sound features to assure validity, and then use similarity distance to carry out human heart sound pattern matching. The method was verified using 10 recorded heart sounds. The results show that identification accuracy is 85.7% in the two-step mode, and the error acceptance rate is less than 7%，and refusing error rate is less than 10% for normal people.

Abstract: Nowadays, face detection and recognition have gained importance in security and information access. In this paper, an efficient method of face detection based on skin color segmentation and Support Vector Machine(SVM) is proposed. Firstly, segmenting image using color model to filter candidate faces roughly; And then Eye-analogue segments at a given scale are discovered by finding regions which are darker than their neighborhoods to filter candidate faces farther; at the end, SVM classifier is used to detect face feature in the test image, SVM has great performance in classification task. Our tests in this paper are based on MIT face database. The experimental results demonstrate that the proposed method is encouraging with a successful detection rate.

Abstract: We propose an evolutionary model for weighted network according to characteristics of real-life network, and the weighted model integrates the triad formation and the preferential mechanism. The two mechanisms provide a wide variety of scale-free behaviors depending on the parameter that govern the new nodes and new links growth. The model gives power-law distributions of degree, weight, and strength. In particular, the average strength displays scale-free property , , as confirmed in many real networks. While in BBV weighted model, the scaling exponent . This implies that the strength of nodes grows faster than their degree. This denotes a strong correlation between the weight and the topological properties in the model, which can be considered as a meaningful development of weighted network model.