Identifying Anomaly Aircraft Trajectories in Terminal Areas Based on Deep Autoencoder and Its Application in Trajectory Clustering

Anomalous trajectory detection and traffic flow classification for complicated airspace are of vital importance to safety and efficiency analysis.Some researchers employed density-based unsupervised machine learning method to exploit these trajectories related to air traffic control(ATC)actions.However,the quality of position data and the tiny density difference between traffic flows in the terminal area make it particularly challenging.To alleviate these two challenges,this paper proposes a novel framework which combines robust deep auto-encoder(RDAE)model and density peak(DP)clustering algorithm.Specifically,the RDAE model is utilized to reconstruct denoising trajectory and identify anomaly trajectories in the terminal area by two different regularizations.Then,the nonlinear components captured by the encoder of RDAE are input in the DP algorithm to classify the global traffic flows.An experiment on a terminal airspace at Guangzhou Baiyun Airport(ZGGG)with anomaly label shows that the proposed combination can automatically capture non-conventional spatiotemporal traffic patterns in the aircraft movement.The superiority of RDAE and combination are also demonstrated by visualizing and quantitatively evaluating the experimental results.

Improved insensitive to input parameters trajectory clustering algorithm

The existing trajectory clustering （TRACLUS） is sensitive to the input parameters c and MinLns. The parameter value is changed a little, but cluster results are entirely different. Aiming at this vulnerability, a shielding parameters sensitivity trajectory cluster （SPSTC） algorithm is proposed which is insensitive to the input parameters. Firstly, some definitions about the core distance and reachable distance of line segment are presented, and then the algorithm generates cluster sorting according to the core dis- tance and reachable distance. Secondly, the reachable plots of line segment sets are constructed according to the cluster sorting and reachable distance. Thirdly, a parameterized sequence is extracted according to the reachable plot, and then the final trajectory cluster based on the parameterized sequence is acquired. The parameterized sequence represents the inner cluster structure of trajectory data. Experiments on real data sets and test data sets show that the SPSTC algorithm effectively reduces the sensitivity to the input parameters, meanwhile it can obtain the better quality of the trajectory cluster.

Trajectory clustering for arrival aircraft via new trajectory representation

Trajectory clustering can identify the flight patterns of the air traffic,which in turn contributes to the airspace planning,air traffic flow management,and flight time estimation.This paper presents a semantic-based trajectory clustering method for arrival aircraft via new proposed trajectory representation.The proposed method consists of four significant steps:representing the trajectories,grouping the trajectories based on the new representation,measuring the similarities between different trajectories through dynamic time warping(DTW)in each group,and clustering the trajectories based on k-means and densitybased spatial clustering of applications with noise(DBSCAN).We take the inbound trajectories toward Shanghai Pudong International Airport(ZSPD)to carry out the case studies.The corresponding results indicate that the proposed method could not only distinguish the particular flight patterns,but also improve the performance of flight time estimation.

Continuous Clustering Trajectory Stream of Moving Objects

The clustering of trajectories over huge volumes of streaming data has been rec- ognized as critical for many modem applica- tions. In this work, we propose a continuous clustering of trajectories of moving objects over high speed data streams, which updates online trajectory clusters on basis of incremental line- segment clustering. The proposed clustering algorithm obtains trajectory clusters efficiently and stores all closed trajectory clusters in a bi- tree index with efficient search capability. Next, we present two query processing methods by utilising three proposed pruning strategies to fast handle two continuous spatio-temporal queries, threshold-based trajectory clustering queries and threshold-based trajectory outlier detections. Finally, the comprehensive experi- mental studies demonstrate that our algorithm achieves excellent effectiveness and high effi- ciency for continuous clustering on both syn- thetic and real streaming data, and the propo- sed query processing methods utilise average 90% less time than the naive query methods.

A Fuzzy Clustering Algorithm Based on Multipath Component Trajectory for Millimeter Wave Radio Channels

Time-varying channel modeling plays an important role for many applications in time-variant scenarios,while most clustering algorithms focus on static channels and cannot accurately model the channel time-evolution properties.In this paper,a fuzzy clustering algorithm based on multipath component(MPC)trajectory is proposed.Firstly,both the distance and velocity similarities of the MPCs in different snapshots are taken into account to track the MPC trajectory,in which the fuzzy scheme and a kernel function are used to calculate the distance and velocity similarities,respectively.Secondly,a fuzzy MPC trajectory clustering algorithm is proposed to cluster the MPCs in multiple snapshots.The MPCs in a snapshot are clustered according to the membership,which is defined as the probability that a MPC belongs to different clusters.Finally,time-varying channels at 28 GHz are simulated to validate the performance of our proposed algorithm.The results show that our proposed algorithm is able to accurately identify the clusters in time-varying channels compared with the existing clustering algorithms.

Spatio-temporal clustering analysis of COVID-19 cases in Johor

At the end of the year 2019,a virus named SARS-CoV-2 induced the coronavirus disease,which is very contagious and quickly spread around the world.This new infectious disease is called COVID-19.Numerous areas,such as the economy,social services,education,and healthcare system,have suffered grave consequences from the invasion of this deadly virus.Thus,a thorough understanding of the spread of COVID-19 is required in order to deal with this outbreak before it becomes an infectious disaster.In this research,the daily reported COVID-19 cases in 92 sub-districts in Johor state,Malaysia,as well as the population size associated to each sub-district,are used to study the propagation of COVID-19 disease across space and time in Johor.The time frame of this research is about 190 days,which started from August 5,2021,until February 10,2022.The clustering technique known as spatio-temporal clustering,which considers the spatio-temporal metric was adapted to determine the hot-spot areas of the COVID-19 disease in Johor at the sub-district level.The results indicated that COVID-19 disease does spike in the dynamic populated sub-districts such as the state's economic centre(Bandar Johor Bahru),and during the festive season.These findings empirically prove that the transmission rate of COVID-19 is directly proportional to human mobility and the presence of holidays.On the other hand,the result of this study will help the authority in charge in stopping and preventing COVID-19 from spreading and become worsen at the national level.

Gonorrhea cluster detection in Manitoba,Canada:Spatial,temporal,and spatio-temporal analysis

In Canada,Gonorrhea infection ranks as the second most prevalent sexually transmitted infection.In 2018,Manitoba reported an incidence rate three times greater than the national average.This study aims to investigate the spatial,temporal,and spatio-temporal patterns of Gonorrhea infection in Manitoba,using individual-level laboratory-confirmed administrative data provided by Manitoba Health from 2000 to 2016.Age and sex patterns indicate that females are affected by infections at younger ages compared to males.Moreover,there is an increase in repeated infections in 2016,accounting for 16%of the total infections.Spatial analysis at the 96 Manitoba regional health authority districts highlights significant positive spatial autocorrelation,demonstrating a clustered distribution of the infection.Northern districts of Manitoba and central Winnipeg were identified as significant clusters.Temporal analysis shows seasonal patterns,with higher infections in late summer and fall.Additionally,spatio-temporal analysis reveals clusters during high-risk periods,with the most likely cluster in the northern districts of Manitoba from January 2006 to June 2014,and a secondary cluster in central Winnipeg from June 2004 to November 2012.This study identifies that Gonorrhea infection transmission in Manitoba has temporal,spatial,and spatio-temporal variations.The findings provide vital insights for public health and Manitoba Health by revealing high-risk clusters and emphasizing the need for focused and localized prevention,control measures,and resource allocation.

A privacy-preserving vehicle trajectory clustering framework

As one of the essential tools for spatio‒temporal traffic data mining,vehicle trajectory clustering is widely used to mine the behavior patterns of vehicles.However,uploading original vehicle trajectory data to the server and clustering carry the risk of privacy leakage.Therefore,one of the current challenges is determining how to perform vehicle trajectory clustering while protecting user privacy.We propose a privacy-preserving vehicle trajectory clustering framework and construct a vehicle trajectory clustering model(IKV)based on the variational autoencoder(VAE)and an improved K-means algorithm.In the framework,the client calculates the hidden variables of the vehicle trajectory and uploads the variables to the server;the server uses the hidden variables for clustering analysis and delivers the analysis results to the client.The IKV’workflow is as follows:first,we train the VAE with historical vehicle trajectory data(when VAE’s decoder can approximate the original data,the encoder is deployed to the edge computing device);second,the edge device transmits the hidden variables to the server;finally,clustering is performed using improved K-means,which prevents the leakage of the vehicle trajectory.IKV is compared to numerous clustering methods on three datasets.In the nine performance comparison experiments,IKV achieves optimal or sub-optimal performance in six of the experiments.Furthermore,in the nine sensitivity analysis experiments,IKV not only demonstrates significant stability in seven experiments but also shows good robustness to hyperparameter variations.These results validate that the framework proposed in this paper is not only suitable for privacy-conscious production environments,such as carpooling tasks,but also adapts to clustering tasks of different magnitudes due to the low sensitivity to the number of cluster centers.

Optimal midcourse trajectory cluster generation and trajectory modification for hypersonic interceptions

The hypersonic interception in near space is a great challenge because of the target’s unpredictable trajectory, which demands the interceptors of trajectory cluster coverage of the predicted area and optimal trajectory modification capability aiming at the consistently updating predicted impact point(PIP) in the midcourse phase. A novel midcourse optimal trajectory cluster generation and trajectory modification algorithm is proposed based on the neighboring optimal control theory. Firstly, the midcourse trajectory optimization problem is introduced; the necessary conditions for the optimal control and the transversality constraints are given.Secondly, with the description of the neighboring optimal trajectory existence theory(NOTET), the neighboring optimal control(NOC)algorithm is derived by taking the second order partial derivations with the necessary conditions and transversality conditions. The revised terminal constraints are reversely integrated to the initial time and the perturbations of the co-states are further expressed with the states deviations and terminal constraints modifications.Thirdly, the simulations of two different scenarios are carried out and the results prove the effectiveness and optimality of the proposed method.

Relationship Between Urban Road Traffic Characteristics and Road Grade Based on a Time Series Clustering Model： A Case Study in Nanjing, China

With the increasing number of vehicles in large-and medium-sized cities challenges in urban traffic management, control, and road planning are being faced. Taxi GPS trajectory data is a novel data source that can be used to study the potential dynamic traffic characteristics of urban roads, and thus identify locations that show a notable lack of road planning. Considering that road traffic characteristics on their own are insufficient for a comprehensive understanding of urban traffic, we develop a road traffic characteristic time series clustering model to analyze the relationship between urban road traffic characteristics and road grade based on existing taxi trajectory data. We select the main urban area of Nanjing as our study area and use the taxi trajectory data of a single month for evaluating our method. The experiments show that the clustering model exhibit good performance and can be successfully used for road traffic characteristic classification. Moreover, we analyze the correlation between traffic characteristics and road grade to identify road segments with planning designs that do not match the actual traffic demands.

Outlier Behavior Detection for Indoor Environment Based on t-SNE Clustering

In this study,we propose a low-cost system that can detect the space outlier utilization of residents in an indoor environment.We focus on the users’app usage to analyze unusual behavior,especially in indoor spaces.This is reflected in the behavioral analysis in that the frequency of using smartphones in personal spaces has recently increased.Our system facilitates autonomous data collection from mobile app logs and Google app servers and generates a high-dimensional dataset that can detect outlier behaviors.The density-based spatial clustering of applications with noise(DBSCAN)algorithm was applied for effective singular movement analysis.To analyze high-level mobile phone usage,the t-distributed stochastic neighbor embedding(t-SNE)algorithm was employed.These two clustering algorithms can effectively detect outlier behaviors in terms of movement and app usage in indoor spaces.The experimental results showed that our system enables effective spatial behavioral analysis at a low cost when applied to logs collected in actual living spaces.Moreover,large volumes of data required for outlier detection can be easily acquired.The system can automatically detect the unusual behavior of a user in an indoor space.In particular,this study aims to reflect the recent trend of the increasing use of smartphones in indoor spaces to the behavioral analysis.

Spatio-temporal analysis of the incidence of colorectal cancer in Guangzhou,2010-2014

Introduction: Colorectal cancer(CRC) is a common type of neoplasm. This study examined the spatio?temporal distribution of the CRC incidence in Guangzhou during 2010–2014.Methods: Colorectal cancer incidence data were obtained from the Guangzhou Cancer Registry System. Spatial autocorrelation analysis and a retrospective spatio?temporal scan were used to assess the spatio?temporal cluster distribution of CRC cases.Results: A total of 14,618 CRC cases were registered in Guangzhou during 2010–2014, with a crude incidence of 35.56/100,000 and an age?standardized rate of incidence by the world standard population(ASRIW) of 23.58/100,000. The crude incidence increased by 19.70% from 2010(32.88/100,000) to 2014(39.36/100,000) with an average annual percentage change(AAPC) of 4.33%. The AAPC of ASRIW was not statistically significant. The spatial autocorrelation analysis revealed a CRC incidence hot spot in central urban areas in Guangzhou City, which included 25 streets in southwestern Baiyun District, northwestern Haizhu District, and the border region between Liwan and Yuexiu Dis?tricts. Three high? and five low?incidence clusters were identified according to spatio?temporal scan of CRC incidence clusters. The high?incidence clusters were located in central urban areas including the border regions between Bai?yun, Haizhu, Liwan, and Yuexiu Districts.Conclusions: This study revealed the spatio?temporal cluster pattern of the incidence of CRC in Guangzhou. This information can inform allocation of health resources for CRC screening.

An Algorithm for Mining Gradual Moving Object Clusters Pattern From Trajectory Streams

The discovery of gradual moving object clusters pattern from trajectory streams allows characterizing movement behavior in real time environment,which leverages new applications and services.Since the trajectory streams is rapidly evolving,continuously created and cannot be stored indefinitely in memory,the existing approaches designed on static trajectory datasets are not suitable for discovering gradual moving object clusters pattern from trajectory streams.This paper proposes a novel algorithm of gradual moving object clusters pattern discovery from trajectory streams using sliding window models.By processing the trajectory data in current window,the mining algorithm can capture the trend and evolution of moving object clusters pattern.Firstly,the density peaks clustering algorithm is exploited to identify clusters of different snapshots.The stable relationship between relatively few moving objects is used to improve the clustering efficiency.Then,by intersecting clusters from different snapshots,the gradual moving object clusters pattern is updated.The relationship of clusters between adjacent snapshots and the gradual property are utilized to accelerate updating process.Finally,experiment results on two real datasets demonstrate that our algorithm is effective and efficient.

Spatio-temporal epidemic type aftershock sequence model for Tangshan aftershock sequence

Shallow earthquakes usually show obvious spatio-temporal clustering patterns. In this study, several spatio-temporal point process models are applied to investigate the clustering characteristics of the well-known Tangshan sequence based on classical empirical laws and a few assumptions. The relative fit of competing models is compared by Akalke Information Criterion. The spatial clustering pattern is well characterized by the model which gives the best fit to the data. A simulated aftershock sequence is generated by thinning algorithm and compared with the real seismicity.

Clustered trajectories anonymity in wireless sensor networks

This paper proposes a clustered trajectories anonymity scheme （CTA） that enhances the kano nymity scheme to provide the intended level of source location privacy in mobile event monitoring when a global attacker is assumed. CTA applies isomorphic property of rotation to create traces of the fake sources distributions which are similar to those of the real sources. Thus anonymity of each trajectory and that of the clustered is achieved. In addition, location kdiversity is achieved by dis tributing fake sources around the base station. To reduce the time delay, tree rooted at the base sta tion is constructed to overlap part of the beacon interval of the nodes in the hierarchy. Both the ana lytical analysis and the simulation results prove that proved energy overhead and time delay. our scheme provides perfect anonymity with improved energy overhead and time delay.

基于聚类和深度学习的车联网轨迹隐私保护机制

针对车联网轨迹发布中用户面临的隐私泄露问题,提出基于聚类和深度学习的轨迹隐私保护机制(PPCDL).考虑轨迹中的时间因素,通过时间戳将轨迹空间划分为多个区域,获取区域中的轨迹分布点.对每个区域进行改进稳定隶属度多峰值聚类,根据区域轨迹密度进行隐私预算矩阵的预分配.利用时间图卷积网络模型提取轨迹数据的时空特征,对隐私预算预分配矩阵进行训练和预测.根据预测结果添加相应的拉普拉斯噪声,在轨迹数据发布前进行扰动.理论分析和实验结果表明,PPCDL相较于对比机制,时间开销更少,能够更精确地预测隐私预算.利用PPCDL可以合理地在轨迹数据中添加拉普拉斯噪声,有效地提高了轨迹数据的可用性.

基于船舶轨迹数据的几何航路网络建模方法

文中提出了一种基于船舶轨迹数据几何航路网络构建方法,通过选取符合条件的船舶轨迹特征点提取航路点区域,结合轨迹聚类与边界提取构建航路点区域的连接方法,建立几何航路网络.结果表明:该方法能够构建航行水域的几何航路网络.

基于多特征融合的高机动多目标低截获概率跟踪技术

在多目标跟踪过程中,目标的高机动特性使得传统采用固定运动模型或交互式多模型的目标跟踪算法很难实时精确匹配目标运动模型,从而引起高机动目标的低跟踪精度问题。针对这一问题,本文提出一种基于目标运动状态模型自适应更新的高机动多目标跟踪算法。在多目标跟踪过程中,该算法采用多特征聚类融合算法进行目标运动模型估计,并根据各目标跟踪波动参数进行状态转移矩阵决策更新,同时利用联合概率数据关联实现多机动目标状态转移矩阵自适应更新的关联跟踪,从而解决了传统多目标跟踪算法因目标运动模型失配引起的低跟踪精度问题。在目标跟踪算法的传感器选择上,无源传感器不对外辐射能量,具有较好的低截获概率性能,但其跟踪精度有限,常不能满足多目标高跟踪精度的要求。雷达作为有源传感器,具有较高的跟踪精度。但由于雷达对外辐射信号,容易被防御方截获。针对这一问题,本文提出了一种无源传感器目标跟踪为主,有源雷达间歇跟踪为辅的多传感器协同管理目标跟踪算法。该算法通过对目标跟踪本征堆积误差的判断进行传感器的最优分配,并根据波动参数的大小进行状态转移矩阵决策更新。仿真结果验证了本文所提出的多传感器协同的高机动目标跟踪算法在满足高机动目标跟踪精度的条件下可以有效的提升雷达低截获概率性能。

基于起点-终点数据的成山角船舶交通流特征分析

文中提出了一种基于起点-终点(origin-destination,OD)数据的船舶AIS(automatic identification system)轨迹聚类模型.该模型通过对船舶AIS轨迹的OD数据聚类,得到起点标签和终点标签的OD类别组合,从而将行为相似的船舶轨迹划分到同一个簇中,实现船舶AIS轨迹的有效聚类,并识别噪声轨迹.在此基础上,分析了成山角定线制水域船舶航行偏好、OD位置特点和船舶的群体性活动规律等交通流特征.

基于GPS轨迹数据的电动出租车充电站选址规划

针对电动汽车保有量持续增长、充电设施匮乏难以满足用户需求的问题,提出一种基于GPS轨迹数据的电动出租车充电站选址规划方案。首先利用出租车GPS数据分析用户潜在充电需求并提取需求分布;其次提出一种基于网格密度分区的DBSCAN聚类方法,与传统算法相比DB指数由0.34降为0.30,对需求进行聚类和划分需求密集区,设置预选站址;最后,构建集合覆盖模型实现站址优化。利用此方案对北京大兴区出租车轨迹数据进行仿真,得出了合理的选址结果,即该方案可为电动出租车充电站规划提供参考。