多源信息约束下的路径选择模型与算法

针对交通诱导管理措施的制定常缺乏理论支持的问题,提出信息约束机理作用下的时变路径选择行为研究方法。从人的知觉角度出发基于模糊聚类算法深入解析了多源交通信息(MSTI)的约束规律,借助VISSIM软件模拟路网环境并构建交通状态模式识别模型模拟信息约束下出行者的心理活动。采用意向(SP)调查法获取驾驶员在路网中的路径选择决策数据,并利用Biogeme软件对行为数据建模。结果表明,当偏好路径拥挤不严重时,信息很难对行为产生约束,出行者更倾向于坚持偏好路径;但随着偏好路径拥挤加剧,在信息影响下路径变更行为渐趋频繁,相应的信息对行为的约束也逐渐增强。研究结论为信息环境下出行者的不完全理性行为研究提供了思路及借鉴,并可为交通管理部门提供决策支持。     

Application of load balancing based on symmetric balanced incomplete block design to random networks

In a load balancing algorithm [O. Lee, M. Anshel, I. Chung, Design of an efficient load balancing algorithm on distributed networks by employing symmetric balanced incomplete block design, IEE Proceedings - Communications 151 (6) (2004) 535-538] based on the SBIBD (Symmetric Balanced Incomplete Block Design), each node receives global workload information by only two round message exchange with traffic overhead, where v is the number of nodes. It is very efficient and works well only when v=p²+p+1 is used for a prime number p. In this paper, we generated a special incidence structure using the SBIBD and then propose a new load balancing algorithm, which executes well for an arbitrary number of nodes. To accomplish this, we add a number of links to nodes in order for each node to receive more than 80% of the workload information by two round message exchange. For performance of our algorithm, we carried out an experiment for the number of nodes, w, which was up to 5000. Traffic overhead is less than in a round and standard deviation of traffic overhead shows that each node has a mostly well-balanced amount of traffic.     

用于交通图像识别的改进尺度依赖池化模型

针对交通标志在自然场景中所占的比例较小、提取的特征量不足、识别准确率低的问题,提出改进的尺度依赖池化（SDP）模型用于小尺度交通图像的识别。首先,基于神经网络深卷积层具有较好的轮廓信息与类别特征,在SDP模型只提取浅卷积层特征信息的基础上,使用深卷积层特征补足型SDP（SD-SDP）映射输出,丰富特征信息;其次,因SDP算法中的单层空间金字塔池化损失边缘信息,使用多尺度滑窗池化（MSP）将特征池化到固定维度,增强小目标的边缘信息;最后,将改进的尺度依赖池化模型应用于交通标志的识别。实验结果表明,与原SDP算法比较,提取特征量增加,小尺度交通图像的识别准确率较好地提升。     

Traffic information interpolation method based on traffic flow emergence using swarm intelligence

Traffic congestion has become one of the most pressing social problems in today’s society, and research into appropriate traffic signal control is actively underway. At present, most traffic signal control methods define traffic signal parameters on the basis of traffic information such as the number of passing vehicles. Installing sensors at a vast number of intersections is necessary for more precise and real-time adaptive control, but this is unrealistic from the viewpoint of cost. As an alternative, we propose a swarm intelligence-based methodology that creates routes with a similar traffic volume using the traffic information from intersections already equipped with sensors and interpolates this information in the intersections without sensors in real time. Our simulation results show that the proposed methodology can effectively create similar traffic routes for main traffic flows with high traffic volumes. The results also show that it has an excellent interpolation performance for heavy traffic flows and can adapt and interpolate to situations where traffic flow changes suddenly. Moreover, the interpolation results are highly accurate at a road link where traffic flows confluence. We also developed an interpolation algorithm that is adaptable to traffic patterns with confluence traffic flows. Experiments were conducted with a simulation of merging traffic flows and the proposed method showed good results.

     

基于Cortex-A8处理器的车牌识别系统设计

随着车辆数量的日益增多,交通管理的压力日趋增大,越来越多的场合需要实时车牌识别。针对此问题,本文设计一种基于Cortex-A8处理器的实时车牌识别系统。该系统以Coretx-A8嵌入式处理器为核心,通过V4L2接口进行视频流的采集,然后运行基于改进的OpenCV车牌识别算法,最后通过MJPG-streamer和Socket编程进行视频流和车牌数据的传输。测试结果表明,该系统具有较强的稳定性和实时性,具有较强的实用价值。     

基于Kinect骨架信息的交通警察手势识别

针对现有的手势识别算法识别率低、鲁棒性弱的问题,提出一种基于Kinect骨架信息的交通警察手势识别方法。从Kinect深度图像中预测人体骨架节点的坐标位置,将节点的运动轨迹作为训练和测试的特征,结合距离加权动态时间规整算法和K-最近邻分类器进行识别。实验表明,在参数最优的情况下,该方法对八种交通警察手势的平均识别率达到98.5%,可应用于智能交通等领域。     

On the impacts of human interactions in MMORPG traffic

Game traffic depends on two main factors, the game protocol and the gamers’ behavior. Based on a few popular real-time multiplayer games this paper investigates the latter factor showing how a set of typical game phases—e.g., player movement, changes in the environment—impacts traffic on different observation levels. The nature of human behavior has such a high impact on traffic characteristics that it influences the traffic both at a macroscopic—e.g., traffic rate—and at a microscopic—payload content—level. First, by understanding the nature of this impact a user behavior detection algorithm is introduced to grab specific events and states from passive traffic measurements. The algorithms focus on the characteristics of the traffic rate, showing what information can be gathered by observing only packet header information. Second, as an application of our method some results, including a detailed analysis of measurements taken from an operational broadband network, are presented. Third, a novel model and an algorithm are introduced to extend the Deep Packet Inspection traffic classification method with the analysis of non-fix byte signatures, which are not considered in current methods. The model captures the variation of the dynamic byte segments and provides parameters for the algorithm. The introduced algorithm exploits the spatial and temporal correlation by examining and extracting the correlation structure of the traffic and constructing signatures based on the observed correlation. The algorithm is evaluated by examining proprietary gaming traffic and also other known non-gaming protocols.     

改进YOLOv7的交通标志检测算法

自动驾驶技术的快速发展,导致对交通标志检测技术的要求日益提高.为解决YOLOv7算法在识别小目标时误检、漏检等问题,本文提出一种基于注意力机制的交通标志检测模型YOLOv7-PC.首先通过K-means++聚类算法对交通标志数据集进行聚类,获得适用于检测交通标志的锚框;其次在YOLOv7主干特征提取网络中引入坐标注意力机制,将交通标志的横向和纵向信息嵌入到通道中,使生成的特征信息具有交通标志的坐标信息,加强有效特征的提取;最后在加强特征提取网络中引入空洞空间金字塔池化,捕获交通标志多尺度上下文信息,在保证交通标志小目标分辨率的同时,进一步扩大卷积的感受野.在中国交通标志检测数据集(CCTSDB)上的实验表明,本文算法增强了识别小目标的能力,相较于YOLOv7模型,本文算法的m AP、召回率平均分别提高了5.22%、9.01%,是一种有效的交通标志检测算法.     

基于YOLO v3算法改进的交通标志识别算法

针对目前交通标志识别任务在使用深度学习算法时存在模型参数量大、实时性较差和准确率较低的问题,提出了基于YOLO v3改进的交通标志识别算法。该算法首先将深度可分离卷积引入YOLO v3算法的特征提取层,将卷积过程分解为深度卷积、逐点卷积两部分,实现通道内卷积与通道间卷积之间的分离,从而保证了在较高识别准确率的基础上极大地减少了算法模型参数数量以及计算量。其次,在损失函数设计上使用广义交并比（GIoU）损失替换均方误差（MSE）损失,将评测标准量化为损失,解决了MSE损失存在的优化不一致和尺度敏感的问题,同时将Focal损失加入到损失函数以解决正负样本严重不均衡的问题,通过降低大量简单背景类的权重使得算法更专注于检测前景类。将该算法应用于交通标志任务中的结果表明,在TT100K数据集上,该算法的平均精度均值（mAP）指标达到了89%,相较于YOLO v3算法提升了6.6个百分点,且其参数量仅为原始YOLO v3算法的1/5左右,每秒帧数（FPS）亦比YOLO v3算法提升了60%。该算法在极大地减少模型参数量和计算量的同时,提高了检测速度和检测精度。     

Hoeffding bound based evolutionary algorithm for symbolic regression

In symbolic regression area, it is difficult for evolutionary algorithms to construct a regression model when the number of sample points is very large. Much time will be spent in calculating the fitness of the individuals and in selecting the best individuals within the population. Hoeffding bound is a probability bound for sums of independent random variables. As a statistical result, it can be used to exactly decide how many samples are necessary for choosing i individuals from a population in evolutionary algorithms without calculating the fitness completely. This paper presents a Hoeffding bound based evolutionary algorithm (HEA) for regression or approximation problems when the number of the given learning samples is very large. In HEA, the original fitness function is used in every k generations to update the approximate fitness obtained by Hoeffding bound. The parameter 1?δ is the probability of correctly selecting i best individuals from population P, which can be tuned to avoid an unstable evolution process caused by a large discrepancy between the approximate model and the original fitness function. The major advantage of the proposed HEA algorithm is that it can guarantee that the solution discovered has performance matching what would be discovered with a traditional genetic programming (GP) selection operator with a determinate probability and the running time can be reduced largely. We examine the performance of the proposed algorithm with several regression problems and the results indicate that with the similar accuracy, the HEA algorithm can find the solution more efficiently than tradition EA. It is very useful for regression problems with large number of training samples.     

离群点挖掘技术在交通事件检测中的应用

交通事件的检测与确认是交通事件管理中的首要问题。基于线圈和视频数据的检测方法由于成本高,检测效果不明显,在实际应用中受到限制。提出了一种基于离群点挖掘的交通事件检测算法。该算法通过使用浮动车（floatingcardata,FcD）技术得到路况信息,并提取交通事件特征,建立特征向量。算法简单、高效、易于部署。实验结果表明,同模式识别方法相比,该算法具有较高的准确度,能有效区分常规拥堵与交通事件。     

基于流量信息结构的异常检测

由于人们对网络流量规律的认识还不够深入,大型高速网络流量的异常检测仍然是目前测量领域研究的一个难点问题.通过对网络流量结构和流量信息结构的研究发现,在一定范围内,正常网络流量的IP、端口等具有重尾分布和自相似特性等较为稳定的流量结构,这种结构对应的信息熵值较为稳定.异常流量和抽样流量的信息熵值以正常流量信息熵值为中心波动,构成以IP、端口和活跃IP数量为维度的空间信息结构.据此对流量进行建模,提出了基于流量信息结构的支持向量机(support vector machine,简称SVM)的二值分类算法,其核心是将流量异常检测转化为基于SVM的分类决策问题.实验结果表明,该算法具有很高的检测效率,还初步验证了该算法的抽样检测能力.因此,将该算法应用到大型高速骨干网络具有实际意义.     

井下人员定位系统防碰撞算法改进

为解决井下人员定位系统中多个标签向接收器发送信息时产生的数据碰撞问题,提出了一种改进的二进制指数退避算法。该算法采用乘法增加、线性减小的碰撞窗口调整方式,设定了两个阈值,并根据不同网络流量制定了不同的退避发生器值更新规则,同时同步更新优化窗口值,使标签能够自适应快速接入信道。测试表明,改进后的算法最大并发识别数量为150,最大位移速度为10m/s,均优于经典的二进制指数退避算法。该算法提高了数据传输率,减少了漏卡率,有效地解决了井下多目标识别的防碰撞问题。     

一种利用不完整数据检测交通异常的方法

城市化进程的加快带来了严重的交通问题,检测交通异常成为数据挖掘领域的热点之一。传统道路管理主要是应用视频监控,使得处理交通问题的效率受限。鉴于上述原因,提出了一种利用不完整数据检测交通异常的方法(Traffic Anomaly Detection,TAD)。首先,利用相关性聚类从手机数据中获取车辆密度信息,降低处理不完整数据的计算开销;然后,设计一个自适应无参数检测算法,根据手机呼叫量变化率捕捉车辆的分散式动态异常,以解决道路状况不确定性难题;最后,提出异常轨迹算法来追踪异常分布路线并预测影响范围,提高异常检测效率。实验结果表明,TAD方法在不同的实验环境下能够有效地检测交通异常,与现有算法相比,所提算法在有效性和伸缩性上效果更好。     

On the complexity and algorithm of grooming regular traffic in WDM optical networks

In SONET/WDM networks, a high-speed wavelength channel is usually shared by multiple low-rate traffic demands to make efficient use of the wavelength capacity. The multiplexing is known as traffic grooming and performed by SONET Add-Drop Multiplexers (SADM). The maximum number of low-rate traffic demands that can be multiplexed into one wavelength channel is called grooming factor. Since SADMs are expensive, a key optimization goal of traffic grooming is to minimize the total number of SADMs in order to satisfy a given set of traffic demands. As an important communication traffic pattern, all-to-all traffic has been widely studied for the traffic grooming problem. In this paper, we study the regular traffic pattern, which is considered as a generalization of the all-to-all traffic pattern. We focus on the Unidirectional Path-Switched Ring (UPSR) networks. We prove that the traffic grooming problem is NP-hard for the regular traffic pattern in UPSR networks, and show that the problem does not admit a Fully Polynomial Time Approximation Scheme (FPTAS). We further prove that the problem remains NP-hard even if the grooming factor is any fixed value chosen from a subset of integers. We also propose a performance guaranteed algorithm to minimize the total number of required SADMs, and show that the algorithm achieves a better upper bound than previous algorithms. Extensive simulations are conducted, and the empirical results validate that our algorithm outperforms the previous ones in most cases. In addition, our algorithm always uses the minimum number of wavelengths, which are precious resources as well in optical networks.     

Unsupervised learning for human activity recognition using smartphone sensors

To provide more sophisticated healthcare services, it is necessary to collect the precise information on a patient. One impressive area of study to obtain meaningful information is human activity recognition, which has proceeded through the use of supervised learning techniques in recent decades. Previous studies, however, have suffered from generating a training dataset and extending the number of activities to be recognized. In this paper, to find out a new approach that avoids these problems, we propose unsupervised learning methods for human activity recognition, with sensor data collected from smartphone sensors even when the number of activities is unknown. Experiment results show that the mixture of Gaussian exactly distinguishes those activities when the number of activities k is known, while hierarchical clustering or DBSCAN achieve above 90% accuracy by obtaining k based on Caliński–Harabasz index, or by choosing appropriate values for ɛ and MinPts when k is unknown. We believe that the results of our approach provide a way of automatically selecting an appropriate value of k at which the accuracy is maximized for activity recognition, without the generation of training datasets by hand.     

基于模拟退火的流量矩阵估计

OD（Origin-Destination）流量估计用以获得网络流量在各个OD对间的分布情况,在网络优化、管理和网络异常的检测与识别等方面具有重要意义。模拟退火算法是一种全局的最优化技术,运行效率高,将其应用于OD流估计中,有助于降低求解的复杂性,并取得较高精度。提出了一种基于模拟退火的流量矩阵估计方法,首先采用IPF算法（Iterative Proportional Fitting algorithm）校正后的历史均值作为模拟退火初始值;在模拟退火过程中,利用链路流量信息来缩小模拟退火解的搜索空间,以达到提高算法的估计精度及实时性的目的。采用Abilene网络实际数据的仿真结果表明,该文方法能够取得较高的OD流估计精度,且计算效率明显优于现有的广义重力模型方法。     

基于贝叶斯分类算法的木马程序流量识别方法

针对传统计算机杀毒产品对木马程序识别问题上存在的资源消耗和杀毒滞后问题,结合网络流量的分类算法提取各种应用服务流量的特征属性,文章采用朴素贝叶斯分类算法对网络中木马程序流量进行识别。这种方法可以在一定程度上解决现有计算机杀毒产品资源消耗和杀毒滞后的问题。实验结果表明,对于网络中处在待机状态下的木马程序产生的数据流识别效果明显,只需较少量的训练样本即可获得较高的识别率。     

基于进化ResNet的交通标志识别

卷积神经网络具有较优的图像特征提取性能,被广泛应用于交通标志识别领域。然而,现有交通标志识别算法通常基于专家经验设计改进的图像特征提取网络,需经历图像预处理和模型调参过程,导致模型的复杂度增大。提出一种基于进化ResNet的交通标志识别算法。将ResNet的构建参数嵌入到进化算法中,在架构搜索空间中以构建块作为基本单位,并将网络深度、卷积层通道数、池化层类型和模块构建顺序作为搜索空间的可变参数,利用交叉、变异等遗传算子执行自适应优化搜索,以确保进化搜索的有效性,同时设计适用于交通标志识别的轻量化网络。在德国交通标志数据集上的实验结果表明,该算法的识别精度达到99.41%,而参数量仅为2.37×10⁶,相比Multi-column DNN、MFC、MFC+ELM等算法,在保证识别精度的同时减少网络参数量。     

基于遗传算法的排考系统

排考是高校教学管理一项非常重要的工作。随着高校规模的日渐增大, 参与考试的学生数量和课程数量也成倍增加, 由工作人员手工完成排考工作将非常困难。提出了一种使用遗传算法实现排考的方法, 通过对变异算法进行优化, 实现算法的快速收敛。即使对于非常复杂的考试表, 也可以取得很高的成功率和很快的收敛速度。