改进的关联分类算法在交叉营销中的应用

提出一种基于频繁闭项集和不精确推理机制的关联分类算法CHC用于分析企业交叉营销过程,指导商业决策。改进了基于H-Struct动态链接结构的频繁闭项集挖掘算法H-C,将类别属性插入H-Struct头表以减小搜索空间,设定局部相对最小支持度阈值和全局最大支持度阈值过滤无用项集,通过最大挖掘长度阈值提高规则的可用性。扩充了EMYCIN系统中的不精确推理算法,使之可以同时处理后件为负项的关联规则。算法克服了传统分类算法只能得到类别标号的不足,通过求得的类别从属可信度,方便企业对多项营销方案做综合评价。与传统关联分类算法的对比实验证明,改进之后的分类算法在运行速度和分类精度上是高效的。     

Dynamic traffic prediction for insufficient data roadways via automatic control theories

This study aims to propose an algorithm for traffic estimation, particularly for urban roadway sections with insufficient data sources. Establishing an advanced traffic management system (ATMS) heavily depends on obtaining complete data. In this regard, traffic detectors play an important role in data acquisition. However, installing traffic detectors extensively over a metropolitan area can be rather expensive. As such, in most cities around the world, vehicle detectors for traffic data collection are relatively insufficient to meet requirements. In light of this, the current research therefore proposes a feasible algorithm of dynamic section flow prediction based on the automatic control theory and observer design for roadway sections with insufficient data sources. According to the numerical evaluation, the method is found to be satisfactory and acceptable in practice.     

Application of extreme learning machine for series compensated transmission line protection

This paper proposes a new approach based on combined Wavelet Transform-Extreme Learning Machine (WT-ELM) technique for fault section identification (whether the fault is before or after the series capacitor as observed from the relay point), classification and location in a series compensated transmission line. This method uses the samples of fault currents for half cycle duration from the inception of fault. The features of fault currents are extracted by first level decomposition of the current samples using discrete wavelet transform (DWT) and the extracted features are applied as inputs to ELMs for fault section identification, classification and location. The feasibility of the proposed method has been tested on a 400 kV, 300 km series compensated transmission line for all the ten types of faults using MATLAB simulink. On testing 28,800 fault cases with varying fault resistance, fault inception angle, fault distance, load angle, percentage compensation level and source impedance, the performance of the proposed method has been found to be quite promising. The results also indicate that the proposed method is robust to wide variation in system and operating conditions.     

基于几何不变量的直线匹配方法

针对目前直线匹配算法大多基于直线段支持区域的几何特性、灰度特性,但这些特性又极易受外界因素干扰造成匹配失败的情况,提出了基于直线几何不变量的匹配方法,该方法在无任何已知条件的情况下,运用叉积符号、点的线束交比不变量进行直线匹配。对于各个视点图像,采用Hough变换提取直线间交点集,再采用Graham扫描法构造一个最小的凸包,并通过匹配凸包顶点的交比序列来建立点与点的对应关系,选取其中一个对应关系完成直线的匹配。实验结果表明,该方法鲁棒性较好,具有广泛的应用性。     

基于OMNeT++的Ad Hoc网络跨层协议栈仿真

针对OMNeT++的MFW组件中物理层和MAC层模块的错误进行修正和功能改进,实现基于RBAB的IEEE 802.11b协议速率自适应数据传输,建立移动Ad Hoc网络跨层协议栈模型的网络仿真框架,实现将Ad Hoc网络MAC层的速率自适应机制与其路由协议联合优化设计的仿真。结果表明,在移动环境下,采用跨层设计的网络协议栈能大幅提高Ad Hoc网络系统的性能。     

多可再生能源冷热电联供微网系统环境经济优化调度

针对含多种可再生能源的冷热电联供微网系统调度优化问题,提出微网系统最小运行费用和二氧化碳排放的多目标调度优化模型,并结合启发式调度规则,采用改进多目标交叉熵算法获取Pareto最优解集.为了提高算法的收敛速度和求解精度,依据重要抽样理论将多目标优化定义为小概率事件,并引入样本分段生成策略和参数更新机制.算例仿真表明,所提出的多目标模型及其优化算法能够使微网系统获取较好的经济和环境效益,满足用户多样性的优化需求.     

基于行为轨迹属性的软件动态可信模型*

针对软件动态可信度量方法中准确性和效率存在的问题,提出以行为区间划分软件的结构并以行为轨迹属性刻画软件行为的基于行为轨迹属性的软件动态可信模型SBMDB(Software Behavior Model for Dynamic Trustworthiness Based on Behavior Path Properties)。通过对软件功能进行分析,划分软件的行为轨迹区间,提取区间的行为轨迹属性。同时,针对区间的包含、嵌套问题提出了区间化简算法,建立软件的行为模型。该模型以行为轨迹区间为度量基本单位,降低了度量时的整体消耗,提高了度量的效率。实验分析表明,该模型能够精确获取软件的行为信息,有效地检测攻击行为。与其它模型相比,SBMDB可以在保证度量结果准确性基础上提高度量效率。     

Cross‐polarization reduction of microstrip antenna using microwave absorbers

In this article, a metamaterial inspired microwave absorber is used to reduce the cross‐polarization (XP) level of the radiated wave in microstrip antenna (MSA). A microwave absorber unit‐cell has been analyzed and implemented to reduce the cross polarization (XP) level in a single element and a 2 × 2 microstrip patch array antennas. The antennas have been designed on a FR‐4 substrate of thickness 0.8 mm at 10.1 GHz center frequency. The 2 × 2 patch array antenna with and without the absorbers have been experimentally verified for the S11 parameter, the radiation pattern, and the XP suppression in H‐plane and a good comparison has been found.     

Tri‐band composite cylindrical dielectric resonator antenna with hybrid mode excitation and cross‐polarization suppression

This communication investigates composite cylindrical dielectric resonator antenna (CDRA) for various wireless applications. Three important features of proposed antenna design are (i) realization of two different hybrid modes, that is, HEM_11δ and HEM_12δ mode in CDRA with the help of modified annular ring printed line (work as both magnetic dipole and electric dipole), both the hybrid modes support broadside radiation characteristics (ii) suppression of HEM_21δ mode, in order to reduce the cross‐polarization level in H‐plane of other hybrid modes (HEM_11δ and HEM_12δ mode) by an amount of 8‐10 dB (iii) creation of triple‐band attribute using the concept of composite antenna. The proposed antenna design has been fabricated and practically tested. Simulated outcomes show good agreement with measured outcomes. It works in three frequency bands, that is, 2.25‐2.79 GHz, 3.1‐4.0 GHz, and 5.05‐5.6 GHz. The designed antenna structure is appropriate for WLAN and WiMAX applications.