基于支持向量机的多因素话务量预测研究

提高移动通信话务量的预测精度对提高网络性能、增进用户体验具有重要意义。由于多种因素会影响到移动通信话务量的准确预测,故选择多因素灰色话务量预测模型来预测话务量。先对数据进行预处理,用关联分析法找到影响话务量预测的主要因素。但此模型对波动较大的数据预测精度较低,用支持向量机的模型来改善预测结果,选取拥有较强的敛散性和全局寻优能力的复高斯小波核函数优化向量机。从仿真结果可以看出该模型有更好的收敛作用和较为理想的预测效果。     

On universal algorithms for adaptive forecasting

In the last decade, new methods of forecasting were developed different from traditional statistical methods. In particular, it is possible to “efficiently” predict any sequence of outcomes without using any hypothesis on the nature of a source generating it. In the present paper, a modified version of the universal forecasting algorithm is considered. The main part of the paper is devoted to algorithmic analysis of universal forecasting methods and to exploring limits of their performance.     

Swarm intelligence for traffic light scheduling: Application to real urban areas

Congestion, pollution, security, parking, noise, and many other problems derived from vehicular traffic are present every day in most cities around the world. The growing number of traffic lights that control the vehicular flow requires a complex scheduling, and hence, automatic systems are indispensable nowadays for optimally tackling this task. In this work, we propose a Swarm Intelligence approach to find successful cycle programs of traffic lights. Using a microscopic traffic simulator, the solutions obtained by our algorithm are evaluated in the context of two large and heterogeneous metropolitan areas located in the cities of Málaga and Sevilla (in Spain). In comparison with cycle programs predefined by experts (close to real ones), our proposal obtains significant profits in terms of two main indicators: the number of vehicles that reach their destinations on time and the global trip time.     

组合粗糙集和支持向量回归的船舶交通流预测

影响交通流变化的因素众多,为改进传统的船舶交通流预测精度不高,一种结合粗糙集和支持向量回归智能算法的交通流预测模型提出,通过ROSETTA软件进行属性约简预处理,筛选出影响交通流变化的关键影响因素,剔除冗余信息。筛选结果显示外轮进出艘次、对外贸易总额、港口GDP、集装箱标准箱、港口货物吞吐量为输入变量,运用Libsvm软件构建基于遗传算法参数寻优的支持向量回归模型预测2008年和2009年的交通流。算例结果表明,与BP神经网络和SVM模型相比,组合预测模型是有效和实用的预测工具。     

Artificial neural network model for ground vibration amplitudes prediction due to light railway traffic in urban areas

The growth of density and circulation speed of railway transportation systems in urban areas increases the importance of the research issues of the produced environmental impacts. This study presents a field data analysis, obtained during monitoring campaigns of ground vibration, due to light railway traffic in urban areas, based on the artificial neural network (ANN) approach, using quantitative and qualitative predictors. Different ANN-based models, using those predictors, were evaluated/trained and validated. Using several criteria, including those that measures the possibility of ANN overfitting (RR²) and complexity (AIC), the best ANN model was successfully obtained for Lisbon area. This model, with 16 input elements (quantitative and qualitative predictors), 2 neurons on the hidden layer with a hyperbolic tangent sigmoid transfer function, and 1 neuron on the output layer considering a linear transfer function, has 0.9720 for the coefficient of determination and 0.5293 for the sum squared error.

     

基于异常值识别卡尔曼滤波器的短期交通流预测

针对智慧交通的需求提出了一种新颖有效的短时交通流预测方法,通过异常值识别扩展了卡尔曼滤波,使其能对噪声进行识别和过滤——异常值识别卡尔曼滤波器。利用卡尔曼滤波能有效地过滤导致系统不确定性的交通流波动,但这可能会使指示交通流突变的细微线索丢失,为了提升预测精度,应用离散小波变换对原始信号进行识别处理,在去掉异常值的同时保留原有对预测有效的信号源信息,此外还使用了历史参考值对预测值进行修正。在四个基准数据集上的大量实验表明,与常用及最新的预测模型相比,其结果MAPE平均降低了2.919%,RMSE平均降低了79.582。     

一种城市交通瓶颈的计算方法

城市交通瓶颈指的是常发性拥堵路段或位置。以往基于交警的巡查经验来确定交通瓶颈,虽可以部分地反映实际情况,但成本太高且无法做到动态跟踪。运用交通传感数据提出了一个简单的交通瓶颈计算方法,通过计算统计周期内的路段拥堵概率来反映交通瓶颈的严重程度。实验表明该方法是有效的。     

Intelligent control for urban traffic systems

This paper proposes a hierarchically intelligent control procedure to resolve certain aspects of the urban traffic management problem. Three levels of the hierarchical system: the linguistic organization, the coordinator, and the on-line controller are responsible, respectively, for the management of traffic in city, neighborhood, and single intersection. Traffic situations are partitioned into five different categories, ranging from sparse to immobile traffic. For each category (except the immobile traffic which is not probed in this paper) a suitable control scheme is introduced. The control at the lowest level, single intersection, will be exerted by optimizing an assigned subgoal. Each coordination level will manage the interaction among the single intersections within its jurisdiction. A learning algorithm is incorporated at this level in order to reduce considerably the need for extensive a priori numerical computations.     

城市小时级需水量的改进型引力搜索算法--最小二乘支持向量机模型预测

本文研究利用最小二乘支持向量机(least squares support vector machine,LS-SVM)算法建立城市小时级需水量预测模型.采取精英策略,自适应的速度更新权重系数,同时引入粒子历史最优信息对引力搜索算法(gravitational search algorithm,GSA)进行了改进.最后采用改进型引力搜索算法(ameliorated gravitational search algorithm,AGSA)优化LS-SVM水量预测模型的正规化参数和核参数来提高模型的预测精度及预测速度.理论测试与实例分析表明,基于AGSA比基于GSA,遗传算法(genetic algorithms,GA)和粒子群优化算法(particle swarm optimization,PSO)的LS-SVM水量预测模型具有更好的预测精度,从而验证了基于AGSA的LS-SVM算法适用于小时级需水量预测问题,AGSA适用于多领域的模型参数的优化过程.     

RQEA-SVR在交通流预测中的应用

建立在统计学习理论和结构风险最小化准则基础上的支持向量回归（SVR）是处理小样本数据回归问题的有利工具,SVR的参数选取直接影响其学习性能和泛化能力。文中将SVR参数选取看作是参数的组合优化问题,确定组合优化问题的目标函数,采用实数量子进化算法（RQEA）求解组合优化问题进而优选SVR参数,形成RQEA-SVR,并应用RQEA-SVR求解交通流预测问题。仿真试验表明RQEA是优选SVR参数的有效方法,解决交通流预测问题具有优良的性能。     

基于粗集理论和支持向量机的道路网短时交通流量预测*

为了解决城市交通流量预测问题,研究道路网中多断面同时作用的情况,先将各断面交通流时间序列在相空间中重构,以充分提取交通流中的相关信息,然后应用粗集理论的强定性分析能力对输入信息进行约简,消除了样本中的噪声和冗余。在此基础上,再利用支持向量机对约简信息进行预测。为了获得最优的预测精度,该方法还利用遗传算法对预测进行了优化。实例研究表明,该方法的预测效果令人满意,在交通控制领域具有较大的应用潜力。     

面向交通流量预测的时空超关系图卷积网络

交通流量预测是智能交通系统中的重要研究课题,然而,交通对象（如站点、传感器）之间存在的复杂局部时空关系使得这项研究颇具挑战。尽管以往的一些研究将流量预测问题转化为一个时空图预测问题从而取得了较大的进展,但是它们忽略了交通对象们跨时空维度的直接关联性。目前仍缺乏一种全面建模局部时空关系的方法。针对这一问题,首先提出一种新颖的时空超图建模方案,通过构造一种时空超关系来全面地建模复杂的局部时空关系;然后提出一种时空超关系图卷积网络（STHGCN）预测模型来捕获这些关系用于交通流量预测。在四个公开交通数据集上进行了大量对比实验,结果表明,相比ASTGCN、时空同步图卷积网络（STSGCN）等时空预测模型,STHGCN在均方根误差（RMSE）、平均绝对误差（MAE）、平均绝对百分比误差（MAPE）这三个评价指标上均取得了更优的结果,不同模型运行时间的对比结果也表明,STHGCN有着更高的推理速度。     

Scheduling models for air traffic control in terminal areas

We propose a job-shop scheduling model with sequence dependent set-up times and release dates to coordinate both inbound and outbound traffic flows on all the prefixed routes of an airport terminal area and all aircraft operations at the runway complex. The proposed model is suitable for representing several operational constraints (e.g., longitudinal and diagonal separations in specific airspace regions), and different runway configurations (e.g., crossing, parallel, with or without dependent approaches) in a uniform framework. The complexity and the highly dynamic nature of the problem call for heuristic approaches. We propose a fast dynamic local search heuristic algorithm for the job-shop model suitable for considering one of the different performance criteria and embedding aircraft position shifting control technique to limit the controllers/pilots’ workload. Finally, we describe in detail the experimental analysis of the proposed model and algorithm applied to two real case studies of Milan-Malpensa and Rome-Fiumicino airport terminal areas. This work has been partially supported by grant CNR FPCCR021074 from the Italian National Research Council.     

A universal sample-based background subtraction method for traffic surveillance videos

Multimedia Tools and Applications - Background subtraction in traffic surveillance videos plays a crucial role in many high-level analytics and applications. Although great progress has been made...     

基于小波分解的网络流量时间序列建模与预测

提出一种基于小波分解的网络流量时间序列的分析和预测方法。将非平稳的网络流量时间序列通过小波分解成为多个平稳分量,采用自回归滑动平均方法分别对各平稳分量进行建模,将所有分量的模型进行组合,得到原始非平稳网络流量时间序列的预测模型。在仿真实验中,利用网络流量文库的时间序列数据建立了预测模型,并对其进行独立测试检验。仿真结果表明,本预测方法提高了网络流量时间序列的预测准确率,是一种有效、稳健的网络流量预测方法。     

Dynamic bandwidth provisioning using ARIMA-based traffic forecasting for Mobile WiMAX

With fast proliferation of QoS-enabled wireless packet networks, need for effective QoS control is increasing. In this paper, we focus on QoS provisioning in Mobile WiMAX access service network (ASN). We investigate a dynamic bandwidth provisioning method that can help to increase resource utilization. Our approach consists of two stages: traffic forecasting, followed by bandwidth provisioning. For the first stage, we use auto-regressive integrated moving average (ARIMA) model to forecast traffic based on online measurement. For the second stage, we use a bandwidth provisioning scheme that allocates bandwidths depending on the traffic forecasting. We modeled our problem as a Fractional Knapsack Problem for which we used a greedy algorithm in order to find an approximate solution. Through simulation studies with real-world data sets, we found that our approach could increase the bandwidth for the real-time traffic class and guarantee adequate service quality for the nonreal-time traffic class as well, while maximizing resource utilization.     

Video traffic analytics for large scale surveillance

The video traffic analysis is the most important issue for large scale surveillance. In the large scale surveillance system, huge amount of live digital video data is submitted to the storage servers through the number of externally connected scalable components. The system also contains huge amount of popular and unpopular old videos in the archived storage servers. The video data is delivered to the viewers, partly or completely on demand through a compact system. In real time, huge amount of video data is imported to the viewer’s node for various analysis purposes. The viewers use a number of interactive operations during the real time tracking suspect. The compact video on demand system is used in peer to peer mesh type hybrid architecture. The chunk of video objects move fast through the real time generated compact topological space. Video traffic analytics is required to transfer compressed multimedia data efficiently. In this work, we present a dynamically developed topological space, using mixed strategy by game approach to move the video traffic faster. The simulation results are well addressed in real life scenario.     

Data-driven approaches for emissions-minimized paths in urban areas

Concerns about air quality and global warming have led to numerous initiatives to reduce emissions. In general, emissions are proportional to the amount of fuel consumed, and the amount of fuel consumed is a function of speed, distance, acceleration, and weight of the vehicle. In urban areas, vehicles must often travel at the speed of traffic, and congestion can impact this speed particularly at certain times of day. Further, for any given time of day, the observations of speeds on an arc can exhibit significant variability. Because of the nonlinearity of emissions curves, optimizing emissions in an urban area requires explicit consideration of the variability in the speed of traffic on arcs in the network. We introduce a shortest path algorithm that incorporates sampling to both account for variability in travel speeds and to estimate arrival time distributions at nodes on a path. We also suggest a method for transforming speed data into time-dependent emissions values thus converting the problem into a time-dependent, but deterministic shortest path problem. Our results demonstrate the effectiveness of the proposed approaches in reducing emissions relative to the use of minimum distance and time-dependent paths. In this paper, we also identify some of the challenges associated with using large data sets.     

A privacy mechanism for mobile-based urban traffic monitoring

In mobile-based traffic monitoring applications, each user provides real-time updates on their location and speed while driving. This data is collected by a centralized server and aggregated to provide participants with current traffic conditions. Successful participation in traffic monitoring applications utilizing participatory sensing depends on two factors: the information utility of the estimated traffic condition, and the amount of private information (position and speed) each participant reveals to the server. We assume each user prefers to reveal as little private information as possible, but if everyone withholds information, the quality of traffic estimation will deteriorate. In this paper, we model these opposing requirements by considering each user to have a utility function that combines the benefit of high quality traffic estimates and the cost of privacy loss. Using a novel Markovian model, we mathematically derive a policy that takes into account the mean, variance and correlation of traffic on a given stretch of road and yields the optimal granularity of information revelation to maximize user utility. We validate the effectiveness of this policy through real-world empirical traces collected during the Mobile Century experiment in Northern California. The validation shows that the derived policy yields utilities that are very close to what could be obtained by an oracle scheme with full knowledge of the ground truth.     

A video streaming application for urban traffic management

Urban traffic control systems have based their technological infrastructure both on advanced analog close-circuit television systems (CCTV) and point-to-point links, providing difficult-to-scale and very expensive systems. The main goal of an urban traffic monitoring system is to capture, send, play and distribute video information from the streets of a certain city to a management centre where it is processed by different services. Current digitalization process of video networks, and the research carried out in the field of streaming media, has led vendors to present proprietary hardware and software solutions resulting in a strong dependency by their customers. This work presents an open urban traffic control system based in commercial off-the-shelf (COTS) philosophy for hardware and software components, as well as open source and standardized protocols. The existence of open standards for video encoding and protocols for streaming media transmission over IP networks has led to the proposal of such a system. The proposed system is a suitable solution in terms of scalability, cost, interoperability and performance for traffic control systems. Furthermore, its architecture can be easily adapted to other video applications and tools like command and control, surveillance or security systems for military and civilian applications.