Online sequential extreme learning machine based multilayer perception with output self feedback for time series prediction

This study presents a time series prediction model with output self feedback which is implemented based on online sequential extreme learning machine. The output variables derived from multilayer perception can feedback to the network input layer to create a temporal relation between the current node inputs and the lagged node outputs while overcoming the limitation of memory which is a vital part for any time-series prediction application. The model can overcome the static prediction problem with most time series prediction models and can effectively cope with the dynamic properties of time series data. A linear and a nonlinear forecasting algorithms based on online extreme learning machine are proposed to implement the output feedback forecasting model. They are both recursive estimator and have two distinct phases: Predict and Update. The proposed model was tested against different kinds of time series data and the results indicate that the model outperforms the original static model without feedback.     

面向自组织平衡的共享电动汽车调度优化方法

针对共享电动汽车运营中出现的站点车辆供需不平衡及人工调度成本过高等问题，提出面向自组织平衡的共享电动汽车调度优化方法.利用共享电动汽车站点选择行为数据，构建用户取车站点选择MNL(Multinominal Logit)模型，分析用户的站点选择行为；构建面向各站点车辆供需自组织平衡的站点间车辆调度优化方法，即通过车辆动态折扣策略引导用户改变默认的最近取还车站点，在运营结束后以运营企业的调度总成本最小为目标，建立人工调度优化模型并应用禁忌搜索算法求解；最后，选取北京市海淀区部分共享电动汽车站点进行算例分析.结果表明：本文提出的优化方法与无动态折扣策略相比，调度总成本降低了 4.5%，人工调度成本降低了21.1%，人工调度任务数减少了8.3%.     

面向自组织平衡的共享电动汽车调度优化方法

针对共享电动汽车运营中出现的站点车辆供需不平衡及人工调度成本过高等问题，提出面向自组织平衡的共享电动汽车调度优化方法.利用共享电动汽车站点选择行为数据，构建用户取车站点选择MNL(Multinominal Logit)模型，分析用户的站点选择行为；构建面向各站点车辆供需自组织平衡的站点间车辆调度优化方法，即通过车辆动态折扣策略引导用户改变默认的最近取还车站点，在运营结束后以运营企业的调度总成本最小为目标，建立人工调度优化模型并应用禁忌搜索算法求解；最后，选取北京市海淀区部分共享电动汽车站点进行算例分析.结果表明：本文提出的优化方法与无动态折扣策略相比，调度总成本降低了 4.5%，人工调度成本降低了21.1%，人工调度任务数减少了8.3%.     

单面坡沙堆模型自组织临界性实验研究

沙堆模型是自组织临界状态理论的范例,介绍一种倾斜平面下半无限松散边坡坍塌沙堆模型实验研究,实验结果表明：沙堆的自组织临界性与颗粒的非均匀性有关,从而首次用实难方法证明了自组织临界状态受系统组织原则影响的猜测。     

Research of order allocation model based on cloud and hybrid genetic algorithm under ecommerce environment

For massive order allocation problem of the third party logistics (TPL) in ecommerce, this paper proposes a general order allocation model based on cloud architecture and hybrid genetic algorithm (GA), implementing cloud deployable MapReduce (MR) code to parallelize allocation process, using heuristic rule to fix illegal chromosome during encoding process and adopting mixed integer programming (MIP) as fitness function to guarantee rationality of chromosome fitness. The simulation experiment shows that in mass processing of orders, the model performance in a multi-server cluster environment is remarkable superior to that in stand-alone environment. This model can be directly applied to cloud based logistics information platform (LIP) in near future, implementing fast auto-allocation for massive concurrent orders, with great application value.     

AN OPTIMIZED SCHEME FOR FAST HANDOFF IN IP-BASED CDMA WIRELESS COMMUNICATION NETWORKS

IntroductionMobility as an essential characteristic of wire-less network has received considerable attention inrecent years.A number of system- specific solu-tions have been developed for2 G( such as GSM)and 3G( such as UMTS) wireles networks.Fromthe Internetpointofview these solutions can be re-garded as layer- 2 solutions for wireless access net-works working transparently to the layer- 3 ( IPlayer) [1] .The evolution of wireless network is be-ing strongly influenced by mainly two compo…     

基于网约车数据的城市区域出行时空特征识别与预测研究

针对交通需求特征识别和需求预测问题,构建改进的LDA(Latent Dirichlet Allocation)城市区域内出行需求识别与预测组合模型,快速识别城市区域内出行需求特征并对需求做出预测. 构建城市交通小区尺度内的空间和时间维度下的主要出行需求特征分布挖掘辨识方法,以及数据集在不同时间尺度下时间维度出行特征构建及预测方法. 利用北京市三环内网约车出行订单数据,验证模型的有效性和准确性. 结果表明,模型能够对不同时间窗口下的区域出行需求特征进行辨识和预测,取得较好的结果.     

大跨径桥梁自振特性试验的环境随机激振法

采用快速可靠的环境随机振动激振法,基于结构止各测点的脉动时域应信号,应用ＩＴＤ时域模态参数识别理论,分析大路径桥梁实桥的结构固有模态并列举了工程应用实例。     

厦门(新)站综合交通枢纽换乘客流组织评价研究

交通枢纽的核心功能在于换乘,枢纽的首要任务是构建高效、快捷、便利的换乘条件,而对枢纽换乘效率产生巨大影响的因素主要是枢纽交通设施的布局及客流组织方式。利用传统四阶段法建立枢纽换乘量的预测模型,对厦门(新)站枢纽的换乘量进行预测,并在厦门(新)站枢纽现有规划设施布局的基础上,制定合理的换乘组织方案,同时建立评价指标对枢纽的客流组织进行评价,得到厦门(新)站枢纽交通设施布局的不足,提出改善措施。     

基于神经网络的高温下（后）预应力损失分析

提出了基于神经网络的高温下(后)预应力损失的评价方法.针对影响高温下(后)预应力损失的复杂多变性和相当强的不确定性,建立了基于神经网络的高温下(后)预应力损失模型.运用神经网络强大的自适应、自组织、自学习的能力以及高度的非线性映射性、泛化性和容错性的特点,通过对训练样本的神经网络学习,建立了预应力损失与温度、初始有效预应力以及高温条件的网络关系,最终实现了对测试样本的预应力损失预报.     

基于遗传算法(GA)优化BP神经网络的船舶交通流量预测

为了提高船舶交通流量的预测精度,在BP神经网络的基础上,结合遗传算法(GA)建立一个新的预测模型.该模型利用GA自适应搜索能力和较快的收敛速度,进而确定BP神经网络中的最优权值和阈值.以青岛港2011—2019年船舶交通流量统计数据为例,进行仿真实例验证.结果表明,与传统的BP神经网络相比,该模型能显著地提高船舶交通流量的预测精度,用于预测船舶交通流量具有一定可行性.     

基于球面Delaunay三角网的GPS网络构造算法

根据球面Delaunay三角网的最大二面角性质，提出了一种GPS网络快速生长算法．采用国际大地坐标系的离散GPS站点，构造了全球球面Delaunay三角网，以验证该算法的可靠性．最后，对球面Delaunay三角网快速生长算法和球面Delaunay三角网直接搜索算法的效率进行了比较．结果表明，所提出的基于球面Delaunay三角网的GPS网络快速生长算法是有效的．     

Dynamic Analysis of Micro-machined Diamagnetic Stable Permanent Magnet Levitation System

A novel micro-machined diamagnetic stable levitation system (MDSLS) which is composed of a free permanent magnetic rotor, a ring lifting permanent magnet and two diamagnetic stabilizers was presented. The static and dynamic stable characters of MDSLS were analyzed. The coupled non-linear differential equations were used to describe six-degree-of-freedom motion of the levitated rotor, and the equivalent surface current and combined diamagnetic image current method were utilized to model the interaction forces and torques between the lifting permanent magnet and rotor permanent magnet and also between the rotor permanent magnet and diamagnetic substrates. Because of difficulty to get analytical solution, the numerical calculation based on Runge-Kutta method was used to solve the dynamic model. The vibration frequencies were identified by fast Fourier transform (FFT) analysis. According to their resonance characteristics and parameters, the translational and angular dynamic stiffness were also calculated. The results show that the levitation of the rotor in MDSLS is stable, and the MDSLS is potential for the application in levitation inertial sensor.     

基于改进核密度估计的电动出租车快速充电行为研究

电动汽车充电行为研究是充电负荷时空分布预测、充电基础设施规划和有序充电管理的 基础。本文基于上海市电动出租车的实测数据，划分充电片段并提取快速充电行为特征变量，开 展相关性分析以揭示变量之间的内在相关性，从工作日和休息日两个时间维度揭示快速充电行 为规律，提出一种基于扩散方程的自适应扩散核密度估计模型应用于快速充电行为特征变量的 概率建模并使用拟合优度检验指标验证该模型的有效性。研究结果表明：电动出租车的快速充 电行为在工作日和休息日具有明显的差异性，自适应扩散核密度估计模型可使电动汽车充电行 为特征变量的概率建模更加准确，且具有更高的拟合精度。     

Thread labeling for news event

Automatic thread labeling for news events can help people know different aspects of a news event. In this paper, we present a method to label threads of a news event. We use latent Dirichlet allocation (LDA) topic model to extract news threads from news corpus. Our method first selects the thread words subset then extracts phrases based on co-occurrence calculation. The extracted phrase is then used as a label of a news thread. Experimental results show that about 60% of generated labels visualize the meaningful aspects of a news event. These labels can help people fast to capture many different aspects of a news event.     

��̬ʱ϶�ٷ���ķֲ�ʽЭͬ����ģ���о���

协同时隙再分配是以利益为中心的自私理性个体间的分布式协作问题,具有高度的动态性和不确定性,再分配的目标是在追求个体自身利益最大化的基础上,实现群体目标.本文分析了DCCEA（分布式协同多目标进化算法）的特性及原理,确定了其在时隙再分配问题中的可用性,并在此基础上构建了基于时隙再分配的分布式协同多目标进化算法模型.仿真实验结果表明,模型在提高总交换效用的同时,增强了航空公司外部交换的自主性,同时分配效率也得到了进一步提高,增强了分配时效性,由此更为有效地解决了分布式动态环境下的CDM GDP（地面延误程序）时隙再次分配问题.     

A Combined Speaker Adaptation Method for Mandarin Speech Recognition

A speaker adaptation method that combines transformation matrix linear interpolation with maximum a posteriori (MAP) was proposed. Firstly this method can keep the asymptotical characteristic of MAP. Secondly,as the method uses linear interpolation with several speaker-dependent (SD) transformation matrixes, it can fully use the prior knowledge and keep fast adaptation. The experimental results show that the combined method achieves an 8.24% word error rate reduction with only one adaptation utterance, and keeps asymptotic to the performance of SD model for large amounts of adaotation data.     

STRUCTURAL MODELING OF WAN TRAFFIC

ＩｎｔｒｏｄｕｃｔｉｏｎＲｅｃｅｎｔｅｍｐｉｒｉｃａｌｓｔｕｄｉｅｓ［１～４］ｏｆｈｉｇｈ－ｒｅｓｏｌｕｔｉｏｎｔｒａｆｆｉｃｍｅａｓｕｒｅｍｅｎｔｓｆｒｏｍａｖａｒｉｅｔｙｏｆｄｉｆｆｅｒｅｎｔｗｏｒｋｉｎｇｃｏｍｍｕｎｉｃａｔｉｏｎｎｅｔｗｏｒｋｓｈａｖｅｐｒｏｖｉｄｅｄａｍｐｌｅｅｖｉｄｅｎｃｅｔｈａｔａｃｔｕａｌｎｅｔｗｏｒｋｔｒａｆｆｉｃｉｓｓｅｌｆ－ｓｉｍｉｌａｒ，ｏｒｆｒａｃｔａｌ，ｉｎｎａｔｕｒｅ，ｉ．ｅ．，ｂｕｒｓｔｙｏｖｅｒａｗｉｄｅｒａｎｇｅｏｆｔｉｍｅｓｃａｌｅｓ．Ｔｈｉ…     

A Solution Model to Protect Mobile Agents Against Malicious Host Attack

Within an agent server, the model introduces a trusted third party entity called Secure Service Station(SSS). The SSS is a non-hardware component and is intended to prevent most attacks performed by malicioushosts, by providing mechanisms that ensure attack detection and provide integrity to mobile agents. This noble technique involves encapsulating partial results obtained on each intermediate host and binding these results together using a hash function, thus forming a strong bonded chain that cannot be compromised. An analytical model to explore the system performance was also developed.     

构建反思性学习模式,培养综合职业能力

近年来,综合职业能力的培养已成为高职院校关注的重要领域。公共英语教学涉及的学生多,影响大,是高职生综合职业能力培养的重要平台。本文旨在具体研究在公共英语听说自主学习课程中培养学生的反思性学习能力,并从自我计划、自我监控、自我评价和自我调整四个方面提出了英语自主学习课程中的反思性学习模式,从而更好的从自我管理能力、沟通能力、团队合作能力、组织协调能力、口头与书面表达能力、判断思维能力等方面培养高职生的综合职业能力。