基于Camshift的改进人脸跟踪算法

文中利用目标加速度运动位移方程,预测下一时刻目标可能移动的位置,使用预测位置误差方程,估测运动目标搜索范围,并且通过启动多个Camshift跟踪器的方法,改进Camshift算法。仿真实验表明,该方法有效地克服了Camshift算法自身的缺陷,即使是加速运动的目标,也可准确地预测运动目标的位置,并且有效提高了对遮挡目标跟踪和多个人脸目标跟踪的鲁棒性。     

移动无线传感器网络定位算法研究

为了解决移动无线传感器网络中节点的自身定位问题,提出了一种基于运动预测的定位算法。该算法利用节点运动的连续性和接收信号强度测距方式,保存其最近两组历史位置信息,并结合节点当前的状态来估计自身位置。它不需要额外的硬件支持与较高的信标节点密度,满足复杂传输环境的应用要求。仿真结果表明,该算法具有较好的鲁棒性和较高的定位精度,节点随机运动时的定位误差约为15%,而直线运动时只有12%。     

结合帧差法与Mean Shift的抗遮挡跟踪算法

针对目标严重遮挡后,运动状态发生改变时,传统的基于运动预测的算法无法有效跟踪的问题,提出一种基于帧差法的改进算法。引入巴氏系数(Bhattacharyya)作为目标是否发生遮挡的判据;当发生遮挡时,帧差法检测目标,再次检测到目标时将此位置作为Mean Shift迭代的起始位置;最后正常跟踪时采用卡尔曼滤波预测目标位置,减少迭代次数。实验结果表明,当目标在严重遮挡后,运动状态改变时,基于运动预测的算法将无法跟踪目标,改进算法能够重新跟踪目标。     

基于蒙特卡罗的无线传感器网络中的移动节点定位算法

针对信标节点固定、待定位节点移动的应用场景,在传统MCB算法的基础上,文章提出一种改进的蒙特卡罗盒子定位算法。该算法利用节点的历史估算位置,构建节点运动模型,采用灰色预测理论预测待定位节点可能到达的区域;并利用待定位节点与邻居信标节点以及非邻居信标节点的相对位置信息定义扩展锚箱,增加过滤条件,提高样本有效性,从而提高定位精度。仿真结果表明,改进方案在不同的信标节点密度、不同的节点运动速度等情况下,均表现出良好的性能。     

基于Kalman滤波和Meanshift算法的目标跟踪

如何实现移动目标被其他物体遮挡后,预测其所处位置,并能够实现遮挡结束后恢复目标的跟踪是视频目标检测与跟踪研究方面的一个热点问题。文章将Kalman滤波器对目标位置估计能力与Meanshift跟踪算法相互结合实现视频序列中移动目标检测与跟踪。利用遮挡因子对目标进行遮挡判断,如果没有发生遮挡则使用Meanshift算法进行直接目标跟踪,一旦检测出遮挡则利用Kalman的预测值进行目标新位置的确定,最终实现对运动目标进行跟踪,并通过MATLAB编写程序实现对运动目标的检测与跟踪。     

基于Stacking的集成算法在证券趋势预测中的应用

股票价格的趋势预测一直是金融领域的重要问题,也是一个难题。但即使是对预测性能的微小改进,也可以为金融工程的技术手段带来非常可观的收益。现有研究大多为单一预测算法,旨在通过对比寻求预测效果更优的算法。文中结合指数移动平均值、相对强弱指数等10个有效技术指标,构建基于Stacking集成学习的股票趋势涨跌预测方法,以预测性能较好且存在差异的异质机器学习算法作为Stacking集成的初级学习器,以逻辑回归方法作为元学习器,进行集成预测。选取上证指数和深圳成指作为研究对象,以ROC曲线下方面积AUC值作为性能评估指标。研究结果表明,Stacking集成学习方法的预测性能优于单一预测模型,并通过Friedman检验证明,Stacking集成算法和单一算法之间存在显著差别。     

基于云模型移动对象行为识别算法评价

为了研究视频监控中异常行为识别算法鲁棒性、准确度和速度的评价方法,将采集图像序列移动对象运动类型等参数作为样本输入逆向云发生器,得到移动对象定性概念的定量表示:期望值Ex、熵En和超熵He。以这些参数作为基础模拟出移动对象行为参数表征。Ex,En和He输入正向云发生器,将每个移动对象设计成一个智能体,个体通过感知环境和自激励调整行为参数,产生多种行为表征参数,并用这些参数来评价行为识别算法。通过实验实现了多种行为表征参数的模拟,用这些参数评价了几种典型算法,实验结果表明评价方法切实可行。     

基于时间加权数据挖掘的FMIPv6切换算法

预测式快速移动IPv6协议（Proactive FMIPv6）需要依靠链路层（L2）触发来进行预切换从而实现平滑切换,然而虚报L2触发以及移动节点（MN）乒乓运动的存在将严重影响Proactive FMIPv6的切换性能。考虑到在每天重复的日常生活中MN往往具有运动轨迹明确、运动时间相对固定等特点,提出一种基于时间加权的数据挖掘算法的FMIPv6切换方案（TWP-FMIPv6）,通过时空数据挖掘机制对时间加权的MN移动历史记录进行移动规则挖掘并预测MN的下一个移动位置,代替Proactive FMIPv6协议中的L2预测触发从而避免虚报L2触发现象。仿真实验结果表明,TWP-FMIPv6能充分利用MN的移动特点进行高准确度的切换预测,减少切换延时和分组丢失率,提高切换效率。     

基于卡尔曼滤波的动态轨迹预测算法

基于拟合的传统轨迹预测算法已无法满足高精度和实时性预测要求.提出基于卡尔曼滤波的动态轨迹预测算法,对移动对象动态行为进行状态估计,利用前一时刻的估计值和当前时刻的观测值更新对状态变量的估计,进而对下一时刻的轨迹位置预测.大量真实移动对象数据集上的实验结果表明：GeoLife数据集上基于卡尔曼滤波的轨迹预测算法的平均预测误差（预测轨迹点与实际轨迹点的均方根误差）为12.5米;与基于轨迹拟合的轨迹预测算法相比,T-Drive数据集预测误差平均下降了555.4米,预测准确率提升了7.1%.在保证预测时效性前提下,基于卡尔曼滤波的动态轨迹预测算法解决了轨迹预测精度较低的问题.     

结合扩展卡尔曼滤波的CamShift移动目标跟踪算法

CamShift算法是一种利用颜色信息对移动目标进行跟踪的算法,当目标快速运动或者受到干扰时容易导致跟踪失败.因此提出了一种结合CamShift与扩展卡尔曼滤波的移动目标跟踪算法,使用扩展卡尔曼滤波对目标运动速度和空间位置进行预测,同时采用目标加权直方图改进CamShift算法.所研究的算法能有效地克服目标背景干扰,存...     

Spatiotemporal Pattern Mining Technique for Location‐Based Service System

In this paper, we offer a new technique to discover frequent spatiotemporal patterns from a moving object database. Though the search space for spatiotemporal knowledge is extremely challenging, imposing spatial and timing constraints on moving sequences makes the computation feasible. The proposed technique includes two algorithms, AllMOP and MaxMOP, to find all frequent patterns and maximal patterns, respectively. In addition, to support the service provider in sending information to a user in a push‐driven manner, we propose a rule‐based location prediction technique to predict the future location of the user. The idea is to employ the algorithm AllMOP to discover the frequent movement patterns in the user's historical movements, from which frequent movement rules are generated. These rules are then used to estimate the future location of the user. The performance is assessed with respect to precision and recall. The proposed techniques could be quite efficiently applied in a location‐based service (LBS) system in which diverse types of data are integrated to support a variety of LBSs.     

Location prediction algorithm for a nonlinear vehicular movement in VANET using extended Kalman filter

Vehicular ad-hoc network (VANET) is an essential component of the intelligent transportation system, that facilitates the road transportation by giving a prior alert on traffic condition, collision detection warning, automatic parking and cruise control using vehicle to vehicle (V2V) and vehicle to roadside unit (V2R) communication. The accuracy of location prediction of the vehicle is a prime concern in VANET which enhances the application performance such as automatic parking, cooperative driving, routing etc. to give some examples. Generally, in a developed country, vehicle speed varies between 0 and 60 km/h in a city due to traffic rules, driving skills and traffic density. Likewise, the movement of the vehicle with steady speed is highly impractical. Subsequently, the relationship between time and speed to reach the destination is nonlinear. With reference to the previous work on location prediction in VANET, nonlinear movement of the vehicle was not considered. Thus, a location prediction algorithm should be designed by considering nonlinear movement. This paper proposes a location prediction algorithm for a nonlinear vehicular movement using extended Kalman filter (EKF). EKF is more appropriate contrasted with the Kalman filter (KF), as it is designed to work with the nonlinear system. The proposed prediction algorithm performance is measured with the real and model based mobility traces for the city and highway scenarios. Also, EKF based prediction performance is compared with KF based prediction on average Euclidean distance error (AEDE), distance error (DE), root mean square error (RMSE) and velocity error (VE).     

基于类别转移加权张量分解模型的兴趣点分区推荐

基于位置社交网络的兴趣点(POI)推荐是人们发现有趣位置的重要途径,然而,现实中用户在不同区域的地点偏好侧重的差异,加之高维度的历史签到信息,使得精准而又个性化的POI推荐极富挑战性.对此,该文提出一种新型的基于类别转移加权张量分解模型的兴趣点分区推荐算法(WTD-PR).通过结合用户连续行为和时间特征,来充分利用用户...     

Vehicle trajectory prediction algorithm in vehicular network

Vehicular ad hoc network has become an important component of the intelligent transportation system, what’s more, the vehicle trajectory prediction has gradually become one of the hotter issues in this research. Vehicle trajectory prediction cannot only provide accurate location services, but also can monitor traffic conditions in advance, and then recommend the best route for the vehicle. For this purpose, this research established a new method for vehicle trajectory prediction (TPVN), which is mainly applied to predict the vehicle trajectory in the short term. Based on the regularity of vehicle movement, the algorithm is helpful to predict the vehicle trajectory so as to estimate the position of the vehicle motion probability. To improve the prediction accuracy, the motion patterns are divided into two types: simple pattern and complex pattern. The advantage of the TPVN algorithm is that the calculation result not only predicts the movement behavior of vehicles in different motion patterns but also the probability distribution of all possible trajectories of the vehicle in the future. Simulation on a large number of true trajectory datasets shows that the performance of TPVN outperforms than other classical algorithms.

     

一种基于历史信息的干扰信号预测算法

基于历史数据的预测方法使用较为广泛,但对数据的类型与特征依赖很大.低轨卫星通信系统获得的频谱感知数据中有时间信息与位置信息.结合这一特性,文中提出了一种基于位置相关和时间相关的干扰预测方法,并采用星上实测数据进行验证,结果表明,该算法具有较好的预测性能.     

Predictive distance-based mobility management for multidimensional PCS networks

This paper presents a mobile tracking scheme that exploits the predictability of user mobility patterns in wireless PCS networks. In this scheme, a mobile's future location is predicted by the network, based on the information gathered from the mobile's recent report of location and velocity. When a call is made, the network pages the destination mobile around the predicted location. A mobile makes the same location prediction as the network does; it inspects its own location periodically and reports the new location when the distance between the predicted and the actual locations exceeds a threshold. To more realistically represent the various degrees of velocity correlation in time, a Gauss-Markov mobility model is used. For practical systems where the mobility pattern varies over time, we propose a dynamic Gauss-Markov parameter estimator that provides the mobility parameters to the prediction algorithm. Based on the Gauss-Markov model, we describe an analytical framework to evaluate the cost of mobility management for the proposed scheme. We also present an approximation method that reduces the computational complexity of the cost evaluation for multidimensional systems. We then compare the cost of predictive mobility management against that of the regular, nonpredictive distance-based scheme, for both the case with ideal Gauss-Markov mobility pattern and the case with time-varying mobility pattern.     

Multi-hop Mobility Prediction

With the occurrence of large-scale human trajectories, which imply spatial and temporal patterns, the subject of mobility prediction has been widely studied. A number of approaches are proposed to predict the next location of a user. In this paper, we expect to lengthen the temporal dimension of prediction results beyond one hop. To predict the future locations of a user at every time unit within a specified time, we propose a Markov-based multi-hop mobility prediction (Markov–MHMP) algorithm. It is a hybrid approach that considers multiple factors including personal habit, weekday similarity, and collective behavior. On a GPS dataset, our approach performs prediction better than baseline and state-of-the-art approaches under several evaluation criteria.     

移动无线传感器网络节点的定位

文中在MCB（Monte—Carlo Localization Boxed）定位算法的基础上提出了一种新的移动无线传感器网络（Mobile Wireless Sensor Networks）节点的定位算法——权重MCB算法。MCB算法在定位过程中,在采样和滤波阶段用到了一阶锚节点和二阶锚节点的位置信息,而没有应用到邻居节点的位置信息。权重MCB在定位过程中不仅用到了一阶锚节点和二阶锚节点的位置信息,还应用到了一阶邻居节点的采样集合里的采样点（即一阶邻居节点的估计位置）,从而改进了定位精度。对比MCB算法,权重MCB算法对定位精度的改进为13％～18％。