异质信息网络高阶层次化嵌入学习与推荐预测

异质信息网络是一种异质数据表示形式,如何融合异质数据复杂语义信息,是推荐系统面临的挑战之一.利用弱关系具有的丰富语义和信息传递能力,构建一种面向推荐系统的异质信息网络高阶嵌入学习框架,主要包括:初始化信息嵌入、高阶信息嵌入聚合与推荐预测3个模块.初始化信息嵌入模块首先采用基于弱关系的异质信息网络最佳信任路径筛选算法,有效地避免在全关系异质信息网络中,采样固定数量邻居造成的信息损失,其次利用新定义的基于多头图注意力的多任务共享特征重要性度量因子,筛选出节点的语义信息,并结合交互结构,有效地表征网络节点;高阶信息嵌入聚合模块通过融入弱关系及网络嵌入对知识良好的表征能力,实现高阶信息表达,并利用异质信息网络的层级传播机制,将被采样节点的特征聚合到待预测节点;推荐预测模块利用高阶信息的影响力推荐方法,实现了推荐任务.该框架具有嵌入节点类型丰富、融合共享属性和隐式交互信息等特点.最后,实验验证UI-HEHo学习框架可有效地改善评级预测的准确性,以及推荐生成的针对性、新颖性和多样性,尤其是在数据稀疏的应用场景中,具有良好的推荐效果.     

LoRa物理层同步及解调性能研究

针对现有的基于FFT的同步算法误差较大的问题,提出了一种优化的LoRa物理层前导码同步方法。首先,根据Chirp信号的时频转换特性,分别采用差分算法和插值算法对前导信号的归一化的小数频偏和小数时延进行估计,在此基础上采用基于FFT同步的联合估计算法对整数频偏和整数时延进行估计;之后,从理论上分析残余的同步误差对LoRa信号解调性能的影响。仿真结果表明,所提出的同步方案可以在相应信噪比极限下满足解调性能要求。     

多馈入直流受端电网换相失败风险区域快速识别方法

针对多馈入直流受端电网换相失败风险区域准确识别难题,计及直流控制系统影响,提出基于广义节点电压交互作用因子的风险区域快速识别方法。将交流母线和故障点视为广义节点,构建考虑直流控制影响的广义节点电压交互作用因子指标,并给出其计算方法;建立换流母线电压跌落期间的换流站暂态电路模型,计算临界换相失败风险电压,进而获取指标临界值,依据指标值与临界值的大小进行换相失败风险的判断;结合指标值的故障位置分布特性,提出换相失败风险区域的快速识别方法;在CIGRE HVDC测试系统和含三馈入直流的39节点测试系统中,验证所提计算方法和识别方法的有效性,与传统方法相比,临界换相失败风险电压的计算误差由7.7%降低到2.4%,提高了换相失败风险区域识别的准确性。     

利用斜井接地体降低输电杆塔周围触电风险研究

为提高输电杆塔的安全性,提出了采用斜井接地体降低杆塔周围接触跨步电压的方法。首先,对接地装置的接触跨步电压分布情况进行分析,得到斜井接地体的最优倾角,研究斜井接地体数量、长度等因素对最优倾角的影响;然后,对接地装置的安全性进行分析,得到入地电流限值曲线;最后,提出人身安全防护措施。研究表明:利用最优倾角布置的斜井接地体,能够显著降低杆塔周围的接触跨步电压。采用划定安全距离、在地表铺设高电阻率介质的措施,能够大大降低人身触电风险。     

Adaptive relay co-ordination using a busbar splitting approach for a system integrity protection scheme

Power system faults can often result in excessively high currents. If sustained for a long time, such high currents can damage system equipment. Thus, it is desirable to operate the relays in the minimum possible time. In this paper, a busbar splitting approach is used for adaptive relay setting and co-ordination purposes for a system integrity protection scheme (SIPS). Whenever a fault occurs, the busbar splitting scheme splits a bus to convert a loop into a radial structure. The splitting schemes are chosen such that the net fault current is also reduced. Busbar splitting eliminates the dependency upon minimum breakpoints set (MBPS) and reduces the relay operating time, thus making it adaptive. The proposed methodology is incorporated into the IEEE 14-bus and IEEE 30-bus systems with single and multiple fault conditions. The modeling and simulation carried out in ETAP, and the results of the proposed busbar splitting-based relay co-ordination are compared with the MBPS splitting-based relay co-ordination.     

5G时代,有线接入网基础资源布局思路探讨

双千兆时代,网络规模空前巨大,有线接入网更是因覆盖范围广,建设规模大,投入人力多,投资占比高等因素,成为研究重点。文章根据有线接入网架构演进,从“点(各类业务及分纤点)、线(各级管线)、面(业务汇聚区)”三个层面对基站、家客、集客等业务接入、分纤点规划及业务汇聚机房等基础资源规划进行研究。     

车联网信息对驾驶员视觉注意与行为的影响

目的探讨不同驾驶情景下车联网信息呈现形式及复杂度对驾驶过程和绩效的影响。方法采用3(信息复杂度:无、简单、复杂)*2(信息通道:视、听)*3(驾驶场景:纵向、横向、转角)多因素混合设计,以驾驶员视觉注意指标、驾驶行为指标为因变量,共招募60名驾驶员,分两组。结果 (1)车联网信息以听觉通道呈现会增加行车稳定性及方向盘控制稳定性,且不会损害驾驶员的视觉注意行为,视觉则相反;(2)信息简单也会增加行车稳定性及方向盘控制稳定性。结论横向与纵向路径以听觉呈现简单信息有利于促进安全驾驶行为,转角路径中应避免车联网信息。     

Multidecadal Trends in Large-Scale Annual Mean SATa Based on CMIP5 Historical Simulations and Future Projections

Based on observations and Coupled Model Intercomparison Project Phase 5 (CMIP5) results, multidecadal variations and trends in annual mean surface air temperature anomalies (SATa) at global, hemispheric, and hemispheric land and ocean scales in the past and under the future scenarios of two representative concentration pathways (RCPs) are analyzed. Fifteen models are selected based on their performances in capturing the temporal variability, long-term trend, multidecadal variations, and trends in global annual mean SATa. Observational data analysis shows that the multidecadal variations in annual mean SATa of the land and ocean in the northern hemisphere (NH) and of the ocean in the southern hemisphere (SH) are similar to those of the global mean, showing an increase during the 1900–1944 and 1971–2000 periods, and flattening or even cooling during the 1945–1970 and 2001–2013 periods. These observed characteristics are basically reproduced by the models. However, SATa over SH land show an increase during the 1945–1970 period, which differs from the other hemispheric scales, and this feature is not captured well by the models. For the recent hiatus period (2001–2013), the projected trends of BCC-CSM1-1-m, CMCC-CM, GFDL-ESM2M, and NorESM1-ME at the global and hemispheric scales are closest to the observations based on RCP4.5 and RCP8.5 scenarios, suggesting that these four models have better projection capability in SATa. Because these four models are better at simulating and projecting the multidecadal trends of SATa, they are selected to analyze future SATa variations at the global and hemispheric scales during the 2006–2099 period. The selected multi-model ensemble (MME) projected trends in annual mean SATa for the globe, NH, and SH under RCP4.5 (RCP8.5) are 0.17 (0.29) °C, 0.22 (0.36) °C, and 0.11 (0.23) °C·decade⁻¹ in the 21st century, respectively. These values are significantly lower than the projections of CMIP5 MME without model selection.     

A distortion measure to validate and generate curved high‐order meshes on CAD surfaces with independence of parameterization

A framework to validate and generate curved nodal high‐order meshes on Computer‐Aided Design (CAD) surfaces is presented. The proposed framework is of major interest to generate meshes suitable for thin‐shell and 3D finite element analysis with unstructured high‐order methods. First, we define a distortion (quality) measure for high‐order meshes on parameterized surfaces that we prove to be independent of the surface parameterization. Second, we derive a smoothing and untangling procedure based on the minimization of a regularization of the proposed distortion measure. The minimization is performed in terms of the parametric coordinates of the nodes to enforce that the nodes slide on the surfaces. Moreover, the proposed algorithm repairs invalid curved meshes (untangling), deals with arbitrary polynomial degrees (high‐order), and handles with low‐quality CAD parameterizations (independence of parameterization). Third, we use the optimization procedure to generate curved nodal high‐order surface meshes by means of an a posteriori approach. Given a linear mesh, we increase the polynomial degree of the elements, curve them to match the geometry, and optimize the location of the nodes to ensure mesh validity. Finally, we present several examples to demonstrate the features of the optimization procedure, and to illustrate the surface mesh generation process. Copyright © 2015 John Wiley & Sons, Ltd.     

Classification of focal and nonfocal EEG signals using ANFIS classifier for epilepsy detection

The electroencephalogram (EEG) is the frequently used signal to detect epileptic seizures in the brain. For a successful epilepsy surgery, it is very essential to localize epileptogenic area in the brain. The signals from the epileptogenic area are focal signals and signals from other area of the brain region nonfocal signals. Hence, the classification of focal and nonfocal signals is important for locating the epileptogenic area for epilepsy surgery. In this article, we present a computer aided automatic detection and classification method for focal and nonfocal EEG signal. The EEG signal is decomposed by Dual Tree Complex Wavelet Transform (DT‐CWT) and the features are computed from the decomposed coefficients. These features are trained and classified using Adaptive Neuro Fuzzy Inference System (ANFIS) classifier. The proposed system achieves 98% sensitivity, 100% specificity, and 99% accuracy for EEG signal classification. The experimental results are presented to show the effectiveness of the proposed classification method to classify the focal and nonfocal EEG signals. © 2016 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 26, 277–283, 2016