A spatial entropy reflecting distribution of spatial objects

Decision trees are mainly used to classify data and predict data classes. A spatial decision tree has been designed using Euclidean distance between objects for reflecting spatial data characteristic. Even though this method explains the distance of objects in spatial dimension, it fails to represent distributions of spatial data and their relationships. But distributions of spatial data and relationships with their neighborhoods are very important in real world. This paper proposes decision tree based on spatial entropy that represents distributions of spatial data with dispersion and dissimilarity. The rate of dispersion by dissimilarity presents how related distribution of spatial data and nonspatial attributes. The experiment evaluates the accuracy and building time of decision tree as compared to previous methods and it shows that the proposed method makes efficient and scalable classification for spatial decision support.     

A buffer insertion and simultaneous sizing timing optimization algorithm

A path-based timing optimization algorithm for buffer insertion and simultaneous sizing is proposed. Firstly, candidate buffer insertion location and buffer size for each branch in a given routing path were obtained via localized timing optimization. Then, through evaluating each potential insertion against design objectives, potential optimal buffer insertion locations and sizes for the whole routing tree were determined. At last, by removing redundant buffer insertion operations which do not maximize S （ so ）, given timing requirements are finally fulfilled through minimum number of buffers.     

Nearest neighbor search algorithm forGBD tree spatial data structure

： This paper describes the nearest neighbor （NN） search algorithm on the GBD（generalized BD） tree. The GBD tree is a spatial data structure suitable for two- or three-dimensional data and has good performance characteristics with respect to the dynamic data environment. On GIS and CAD systems, the R-tree and its-successors have been used. In addition, the NN search algorithm is also proposed in an attempt to obtain good performance from the R-tree. On the other hand, the GBD tree is superior to the R-tree with respect to exact match retrieval, because the GBD tree has auxiliary data that uniquely determines the position of the object in the structure. The proposed NN search algorithm depends on the property of the GBD tree described above. The NN search algorithm on the GBD tree was studied and the performance thereof was evaluated through experiments.     

A method of combining SE-tree to compute all minimal hitting sets

In model-based diagnosis, the candidate diagnostic results are generally characterized by all minimal hitting sets for the collection of all conflict sets. In this paper, a new method is proposed to judge a hitting set by the number of conflict sets corresponding to components, and the computing procedure is formalized by combining revised SE-tree (set enumeration tree) with closed nodes to generate all minimal hitting sets. Results show that because closed nodes are added into SE-tree, the search efficiency is highly improved. Furthermore, the proposed method is easy to be understood and implemented. Compared with other effective algorithms with completeness in some experimental tests, the diagnosis efficiency of our proposed method is higher, particularly for single- and double-fault diagnosis.     

A modularity analysis method for forum situation prediction

A forum is a social network that consists of posters and the following comments made by netizens. Generally speaking, forum topics are evolving over time dynamically. In this paper, based on time series analysis and matrix modularity analysis, a novel prediction method is proposed through investigating the correlating influence of three key measurements: relationship strength, pillars, and change frequency of a forum topic. The method demonstrates that there exist some macroscopic and potential laws for forum situation prediction. Extensive experiments over large many datasets show the efficiency and effectiveness of the algorithms.     

Design of a 3 tier smart middleware system for ubiquitous sensor networks

The multiagent negotiation testbed proposed by Collins was modified. It utilizes publish/subscribe system, timerelease cryptography and anonymous communication. The proposed protocol reduces DOS attack and avoids replay data attack by providing ticket token and deal sequence number to the supplier. And it is proved that generating random number to the supplier by market is better than the supplier doing it by him in guaranteeing anonymity. Market publishes an interpolating polynomial for sharing the determination process data. It avoids collusion between a customer and a certain supplier. According to the comparison and analysis with other protocols, the proposed protocol shows good security and better efficiency.     

An efficient electronic marketplace bidding auction protocol with bid privacy

The multiagent negotiation testbed proposed by Collins was modified. It utilizes publish/subscribe system, timerelease cryptography and anonymous communication. The proposed protocol reduces DOS attack and avoids replay data attack by providing ticket token and deal sequence number to the supplier. And it is proved that generating random number to the supplier by market is better than the supplier doing it by him in guaranteeing anonymity. Market publishes an interpolating polynomial for sharing the determination process data. It avoids collusion between a customer and a certain supplier. According to the comparison and analysis with other protocols, the proposed protocol shows good security and better efficiency.      

Small unmanned helicopters attitude controller by an on line adaptive fuzzy control system

Since small unmanned helicopter flight attitude control process has strong timevarying characteristics and there are random disturbances, the conventional control methods with unchanged parameters are often unworkable. An online adaptive fuzzy control system (AFCS) was designed, in a way that does not depend on a process model of the plant or its approximation in the form of a Jacobian matrix. Neither is it necessary to know the desired response at each instant of time. AFCS implement a simultaneous online tuning of fuzzy rules and output scale of fuzzy control system. The two cascade controller design with an inner (attitude controller) and outer controller (navigation controller) of the small unmanned helicopter was proposed. At last, an attitude controller based on AFCS was implemented. The flight experiment showed that the proposed fuzzy logic controller provides quicker response, smaller overshoot, higher precision, robustness and adaptive ability. It satisfies the needs of autonomous flight.     

A Service Ratio-Based Dynamic Fair Queueing Algorithm for Packet Switching Networks

A new weighted fair queueing algorithm is proposed, which uses the novel flow-based service ratio parameters to schedule flows. This solves the main drawback of traditional weighted fair queneing algorithms- the packet-based calculation of the weight parameters. In addition, this paper proposes a novel service ratio calculation method and a queue mangement technology. The former adjusts the service ratio parameters adaptively based on the dynamics of the packet lengths and thee solves the unfairness problem induced by the variable packet length. The latter improves the utilization of the server＇s queue buffer and reduces the delay jitter through restricting the buffer length for each flow.     

Method of So.Sensor Modeling for Fermentation Process Based on Geometric Support Vector Regression

The soft-sensor modeling for fermentation process based on standard support vector regression(SVR) needs to solve the quadratic programming problem(QPP) which will often lead to large computational burdens, slow convergence rate, low solving efficiency, and etc. In order to overcome these problems, a method of soft-sensor modeling for fermentation process based on geometric SVR is presented. In the method, the problem of solving the SVR soft-sensor model is converted into the problem of finding the nearest points between two convex hulls (CHs) or reduced convex hulls (RCHs) in geometry. Then a geometric algorithm is adopted to generate soft-sensor models of fermentation process efficiently. Furthermore, a swarm energy conservation particle swarm optimization (SEC-PSO) algorithm is proposed to seek the optimal parameters of the augmented training sample sets, the RCH size, and the kernel function which are involved in geometric SVR modeling. The method is applied to the soft-sensor modeling for a penicillin fermentation process. The experimental results show that, compared with the method based on the standard SVR, the proposed method of soft-sensor modeling based on geometric SVR for fermentation process can generate accurate soft-sensor models and has much less amount of computation, faster convergence rate, and higher efficiency.     

A fast construction method for spatial index GBD-tree

This paper proposes a fast initial construction method of the GBD-tree. The GDB tree has proper characteristics for management of large amount of 2 or 3 dimensional data. However, the GBD-tree needs long initial construction time by originally proposed one-by-one insertion method. A fast insertion method has been proposed, but it needs large size of buffer capable to hold index information of all entries. The paper proposes another fast initial construction method. The method requires only limited size of work space (buffer). The experimental results show the initial construction time reduces into a third or a quarter of the one-by-one insertion method. The memory efficiency and retrieval efficiency are also improved than the one-by-one insertion method.     

Fast wire segmenting algorithm considering layout density and signal integrity

A k-shortest path based algorithm considering layout density and signal integrity for good buffer candidate locations is proposed in this paper. Theoretical results for computing the maximal distance between buffers are derived under the timing, noise and slew rate constraints. By modifying the traditional uniform wire segmenting strategy and considering the impact of tile size on density penalty function, this work proposes k-shortest path algorithm to find the buffer insertion candidate locations. The experiments show that the buffers inserted can significantly optimize the design density, alleviate signal degradation, save the number of buffers inserted and the overall run time.     

遗传模糊系统的分类器融合

将遗传模糊系统引入分类器融合，并且提出了一种快速的遗传模糊系统设计方法，在该方法中对传统的产生初始群体的方法和交叉操作进行了改进．本文方法在从ELENA数据集和UCI数据集中选择的3个大样本数据集上进行了测试，与当前有代表性的分类器融合方法进行了比较实验．实验结果表明，该方法在缩短训练时间以后仍然能够得到模糊规则数少，分类精度高的分类器融合系统．     

ATM网络中基于门限的漏桶令牌产生算法

提出了一种离散时间情况下基于门限的ＡＴＭ漏桶算法．令牌产生池中令牌的产生速率随缓存中信元的数量而变化，信元的到达过程符合ＭＭＢＰ分布．数值分析的结果表明，影响信元丢失率的关键因素是信元缓存的体积，使用本文提出的算法，以较小的缓冲区及令牌产生池便能满足服务质量的要求     

基于最小类内方差的快速阈值分割算法

最小类内方差法分割图像时需要计算二次统计量,运算量大,效率不高。以减小运算量为目标,对最小类内方差的方法进行改进,提出一种基于最小类内方差的快速闪值分割算法。从图像的灰度直方图出发,推导出简单的迭代公式,然后利用基于最小类内方差的快速阈值分割算法求出阈值。该算法获取阈值速度快,实时性强,用所获取的阈值分割图像有较好的分割效果。理论分析和实验结果表明,该算法运算速度快,分割效果好,具有较高的实用价值。     

一种基于节点交换的FP-tree构造算法

基于FP树的FP-Growth关联规则挖掘算法,不需要产生候选项集,是当前频繁项集挖掘算法中应用最为广泛的算法之一.针对该算法在对大型的数据库挖掘的时候,存在运行速度慢,占用资源多的问题,文中发现算法中FP树和条件FP树的构建是最占资源的阶段.为此,提出了一种基于改进的FP树的构造算法.该算法一方面通过节点交换的方式压缩树的规模,提高挖掘的效率;另一方面,利用节点支持度计数的差值作为阈值以限定节点交换的条件,避免了由于交换过于频繁,造成不必要的系统开销,并把这种基于节点交换FP树构造算法称为TFP树算法.经过实验验证和性能分析,结果表明新算法有效,执行时间少,效率高.     

近邻相关匹配图象快速分形压缩编码

为缩短分形编码中值域块与定义域块逐一匹配时间．将值域块与定义域块的全局匹配改为近邻匹配。并提出近邻相关匹配分形近似编码的方法,在子块搜索匹配之前将大量显著不相关的子块剔除掉,从而大大缩小搜索空间。通过实验,该方法比全局搜索匹配的分形编码快。     

一种高效的自由曲面求交算法

针对目前常用的Ｂｅｚｉｅｒ曲面分割法求交难同时满足高精度和高速度要求的问题，提出了一种快速跟踪求交的算法。着重论述卫确定跟踪起点的方法，并对所求交线的完备性作了充分的考虑。算法利用一曲面参数曲线和另一面的快速求交算法，找到两曲面交线上的某一点，解决了确定跟踪起点的问题，兼顾了快速和高精度两方面的要求；同时，利用求曲面间的极值距离获取控制网格间小交线上的跟踪起点，再用跟踪法求得小交线，从而保证了小交     

支持大规模流数据处理的在线MapReduce数据传输机制

针对流数据规模参差不齐、 流量动态变化且突发性较强的特点, 提出一种可伸缩的动态MapReduce计算模型, 支持大规模动/静态数据在线处理. 基于Event推送方式, 利用Netty底层异步通信方式等技术, 建立在线MapReduce数据传输机制, 进一步实现其原型程序, 解决了大规模分布式计算程序的快速在线传输和数据分发等问
题, 支持流数据动态分发机制, 为动态MapReduce模型提供支撑. 与HadoopOnline系统的传统Socket管道传送方式相比, 该方法能有效提高作业之间数据的传送效率, 从而提高大规模流数据处理的实时性.