Understanding the spatial distribution of crime based on its related variables using geospatial discriminative patterns

Crime tends to cluster geographically. This has led to the wide usage of hotspot analysis to identify and visualize crime. Accurately identified crime hotspots can greatly benefit the public by creating accurate threat visualizations, more efficiently allocating police resources, and predicting crime. Yet existing mapping methods usually identify hotspots without considering the underlying correlates of crime. In this study, we introduce a spatial data mining framework to study crime hotspots through their related variables. We use Geospatial Discriminative Patterns (GDPatterns) to capture the significant difference between two classes (hotspots and normal areas) in a geo-spatial dataset. Utilizing GDPatterns, we develop a novel model—Hotspot Optimization Tool (HOT)—to improve the identification of crime hotspots. Finally, based on a similarity measure, we group GDPattern clusters and visualize the distribution and characteristics of crime related variables. We evaluate our approach using a real world dataset collected from a northeast city in the United States.     

Security alert: Generalized deep multi-view representation learning for crime forecasting

Crime is a focal problem in modern society, affecting social stability, public safety, economic development, and life quality of residents. Promptly predicting crime occurrence places in a relatively high accuracy is a very important and meaningful research direction. Via the rapid development of social media (e.g., Twitter), the online information can act as a strong supplement for the offline information (crime records). Additionally, the geographic information and taxi flow between communities can model the spatial relationship between communities, which has already been confirmed effective in previous work. In order to efficiently solve crime prediction problem, we propose a generalized deep multi-view representation learning framework for crime forecasting. Our extensive experiments on a 4-month city-wide dataset that consists of 77 communities and 22 crime types show our model improve the prediction accuracy on most crime types.     

Dynamic road crime risk prediction with urban open data

Crime risk prediction is helpful for urban safety and citizens’life quality.However,existing crime studies focused on coarse-grained prediction,and usually failed to capture the dynamics of urban crimes.The key challenge is data sparsity,since that 1)not all crimes have been recorded,and 2)crimes usually occur with low frequency.In this paper,we propose an effective framework to predict fine-grained and dynamic crime risks in each road using heterogeneous urban data.First,to address the issue of unreported crimes,we propose a cross-aggregation soft-impute(CASI)method to deal with possible unreported crimes.Then,we use a novel crime risk measurement to capture the crime dynamics from the perspective of influence propagation,taking into consideration of both time-varying and location-varying risk propagation.Based on the dynamically calculated crime risks,we design contextual features(i.e.,POI distributions,taxi mobility,demographic features)from various urban data sources,and propose a zero-inflated negative binomial regression(ZINBR)model to predict future crime risks in roads.The experiments using the real-world data from New York City show that our framework can accurately predict road crime risks,and outperform other baseline methods.     

Prediction of urban human mobility using large-scale taxi traces and its applications

This paper investigates human mobility patterns in an urban taxi transportation system. This work focuses on predicting humanmobility fromdiscovering patterns of in the number of passenger pick-ups quantity (PUQ) from urban hotspots. This paper proposes an improved ARIMA based prediction method to forecast the spatial-temporal variation of passengers in a hotspot. Evaluation with a large-scale realworld data set of 4 000 taxis’ GPS traces over one year shows a prediction error of only 5.8%. We also explore the application of the prediction approach to help drivers find their next passengers. The simulation results using historical real-world data demonstrate that, with our guidance, drivers can reduce the time taken and distance travelled, to find their next passenger, by 37.1% and 6.4%, respectively.     

基于兴趣热点的移动社交网络资源发现机制研究

摘 要: 针对移动社交网络中的资源发现问题,提出了一种基于兴趣热点的资源发现机制（IHRD）,IHRD考虑了人类对感兴趣地点的访问偏好,利用移动节点对热点的访问轨迹计算节点之间的社会关系,根据兴趣热点与社会关系之间的关联,设计了基于兴趣热点的资源搜索办法,解决了网络中存在未共享兴趣节点的资源搜索问题。引入马尔科夫预测模型,对兴趣热点的变化进行有效预测,进一步提高了资源搜索效率,降低了系统开销。仿真实验表明,IHRD与同类发现机制相比,具有较高的资源发现效率,较低的平均时延与通信开销。     

An anticrime information support system design: Application of K-means-VMD-BiGRU in the city of Chicago

The sharp rise in urban crime rates is becoming one of the most important issues of public security, affecting many aspects of social sustainability, such as employment, livelihood, health care, and education. Therefore, it is critical to develop a predictive model capable of identifying areas with high crime intensity and detecting trends of crime occurrence in such areas for the allocation of scarce resources and investment in the prevention and reduction of criminal strategies. This study develops a predictive model based on K-means clustering, signal decomposition technique, and neural networks to identify crime distribution in urban areas and accurately forecast the variation tendency of the number of crimes in each area. We find that the time series of the number of crimes in different areas show a correlation in the long term, but this long-term effect cannot be reflected in the short period. Therefore, we argue that short-term joint law enforcement has no theoretical basis because data show that spatial heterogeneity and time lag cannot be timely reflected in short-term prediction. By combining the temporal and spatial effects, a high-precision anticrime information support system is designed, which can help the police to implement more targeted crime prevention strategies at the micro level.     

社交网络用户在在线媒体中点播行为预测

在线媒体快速发展,为用户带来丰富多彩信息的同时,用户的参与也给在线媒体本身带来巨大的经济利益。因此,如何通过精确预测用户的偏好以增加在线媒体点击,成为一个学术界和工业界均关注的问题。现有的预测方法主要是借助用户个人信息和历史行为来预测用户行为,然而此类方法没有考虑媒体本身缺乏用户信息造成无法预测的问题。随着社交网络的发展,在线媒体与服务运营商间的兼并或合作的增多,支持用户通过单一账户使用多个媒体网络服务的情况越来越常见,这就为基于用户在社交网络中的资料预测用户在其他媒体中的喜好提供海量可信的基础数据。该文基于社交网络Google+和视频媒体YouTube的数据,首先证明用户在YouTube偏好具有高度的集聚性,并提出用户在社交网络中偏好与其在线媒体点击行为具有关联性,基于这种关联性,该文使用社交网络用户信息预测用户在在线媒体中的点播行为。实验结果显示,使用社交网络用户信息可以有效预测用户偏好,预测准确率比仅使用媒体本身信息提高了17%,而且能满足用户个性化需求。     

Crime hotspot mapping using the crime related factors—a spatial data mining approach

The technique of Hotspot Mapping is widely used in analysing the spatial characteristics of crimes. The spatial distribution of crime is considered to be related with a variety of socio-economic and crime opportunity factors. But existing methods usually focus on the target crime density as input without utilizing these related factors. In this study, we introduce a new crime hotspot mapping tool—Hotspot Optimization Tool (HOT). HOT is an application of spatial data miming to the field of hotspot mapping. The key component of HOT is the Geospatial Discriminative Patterns (GDPatterns) concept, which can capture the differences between two classes in a spatial dataset. Experiments are done using a real world dataset from a northeastern city in the United States and the pros and cons of utilizing related factors in hotspot mapping are discussed. Comparison studies with the Hot Spot Analysis tool implemented by Esri ArcMap 10.1 validate that HOT is capable of accurately mapping crime hotspots.     

食源性疾病事件智能探测与预警平台

食源性疾病由来已久,每年都会造成巨大的社会经济损失.人工智能技术给食源性疾病事件的探测和预警带来了新的方法.该文基于互联网大数据开发了食源性疾病事件智能探测与预警平台,该平台面向食源性疾病事件的数据获取、数据分析以及可视化展示的全过程,通过D-M-V分层模型以及模块化开发集成了多种模块.该平台主要解决了食源性疾病事件的数据获取、数据融合、事件探测、风险预测和可视化等问题,该平台能够自动从互联网中采集社交媒体、社会经济等数据;根据数据的时空坐标对多源异构数据进行高效融合;从社交媒体数据中探测出食源性疾病事件并推断其关键信息;利用多源数据对食源性疾病风险进行预测;提供高效的可视化方法和交互手段.该文通过2018年北京市食源性疾病数据作为示例验证平台功能.     

Inferring urban air quality based on social media

Outdoor air pollution is a serious environmental problem in many developing countries; obtaining timely and accurate information about urban air quality is a first step toward air pollution control. Many developing countries however, do not have any monitoring stations and therefore the means to measure air quality. We address this problem by using social media to collect urban air quality information and propose a method for inferring urban air quality in Chinese cities based on China's largest social media platform, Sina Weibo combined with other meteorological data. Our method includes a data crawler to locate and acquire air-quality associated historical Weibo data, a procedure for extracting indicators from these Weibo and factors from meteorological data, a model to infer air quality index (AQI) of a city based on the extracted Weibo indicators supported by meteorological factors. We implemented the proposed method in case studies at Beijing, Shanghai, and Wuhan, China. The results show that based the Weibo indicators and meteorological factors we extracted, this method can infer the air quality conditions of a city within narrow margins of error. The method presented in this article can aid air quality assessment in cities with few or even no air quality monitoring stations.     

犯罪热点分布与驱动因子分析

盗窃和抢劫作为最普遍的犯罪形态,是各级公共安全部门的工作重点.而发现犯罪热点的时空分布和掌握驱动因子对于犯罪宏观规律的把握非常重要.一方面,基于特定时间尺度的连续的犯罪空间热点分析,有助于帮助公安部门发现特定犯罪类型的犯罪热点的分布形态和变化规律;另一方面,基于主成分分析法,通过对案件发生的诸多驱动因子进行选择,可以发现犯罪热点的主要影响因素;采用Getis-Ord Gi＊热点分析和主成分分析方法,对某市2009年盗窃、抢劫犯罪的月度数据进行了深入分析,得出了相应的结论,为警力在特定时间和空间上的合理分配以及主要的管理方向提供了建议.     

A data-driven agent-based simulation to predict crime patterns in an urban environment

Spatial crime simulations contribute to our understanding of the mechanisms that drive crime and can support decision-makers in developing effective crime reduction strategies. Agent-based models that integrate geographical environments to generate crime patterns have emerged in recent years, although data-driven crime simulations are scarce. This article (1) identifies numerous important drivers of crime patterns, (2) collects relevant, openly available data sources to build a GIS-layer with static and dynamic geographical, as well as temporal features relevant to crime, (3) builds a virtual urban environment with these layers, in which individual offender agents navigate, (4) proposes a data-driven decision-making process using machine-learning for the agents to decide whether to engage in criminal activity based on their perception of the environment and, finally, (5) generates fine-grained crime patterns in a simulated urban environment. The novelty of this work lies in the various large-scale data layers, the integration of machine learning at individual agent level to process the data layers, and the high resolution of the resulting predictions. The results show that the spatial, temporal, and interaction layers are all required to predict the top street segments with the highest number of crimes. In addition, the spatial layer is the most informative, which means that spatial data contributes most to predictive performance. Thus, these findings highlight the importance of the inclusion of various open data sources and the potential of theory-informed, data-driven simulations for the purpose of crime prediction. The resulting model is applicable as a predictive tool and as a test platform to support crime reduction.     

A network-based scan statistic for detecting the exact location and extent of hotspots along urban streets

Socio-economic activities and incidents such as crimes and traffic accidents have a negative impact on our society, and their reduction has been a priority in our social-science endeavour. These events are not uniform in their occurrences but, rather, manifest a distinct set of concentrations, commonly known as hotspots. Detecting the exact extent, shape and changes in these hotspots can lead to deeper understanding of their cause and help reduce the volume of incidents, yet accuracy of the analytical outcomes using existing methods are often hampered by their reliance on Euclidean distance. This paper proposes a new type of cluster detection method for identifying significant concentration of urban and social-science activities recorded at the individual street-address level. It extends Scan Statistic—a regular hotspot detection method originally developed in the field of epidemiology—by introducing flexible search windows that adapt to and sweep across a street network. Using a set of synthetic data of crime incidents as an example, performance of the proposed method is measured against that of its conventional counterparts. Results from the performance tests confirm that the proposed method is more accurate in detecting the exact locations of hotspots without over- or under-representing them, thus offering an effective means to identify problem places at the individual street-address level. The simulation also demonstrates how well the proposed method captures changes in the intensity of hotspots, which is also something existing methods have struggled with. An empirical analysis is carried out with data on drug, burglary, robbery, as well as thefts from vehicles in Chicago. The study demonstrates the capacity of the proposed method to extract the detailed profile of the concentration of each crime type, which offers interesting insights into their micro-scale patterns which were previously not available at such a fine spatial granularity.     

Spatio-temporal crime predictions in smart cities: A data-driven approach and experiments

Steadily increasing urbanization is causing significant economic and social transformations in urban areas, posing several challenges related to city management and services. In particular, in cities with higher crime rates, effectively providing for public safety is an increasingly complex undertaking. To handle this complexity, new technologies are enabling police departments to access growing volumes of crime-related data that can be analyzed to understand patterns and trends. These technologies have potentially to increase the efficient deployment of police resources within a given territory and ultimately support more effective crime prevention. This paper presents a predictive approach based on spatial analysis and auto-regressive models to automatically detect high-risk crime regions in urban areas and to reliably forecast crime trends in each region. The algorithm result is a spatio-temporal crime forecasting model, composed of a set of crime-dense regions with associated crime predictors, each one representing a predictive model for estimating the number of crimes likely to occur in its associated region. The experimental evaluation was performed on two real-world datasets collected in the cities of Chicago and New York City. This evaluation shows that the proposed approach achieves good accuracy in spatial and temporal crime forecasting over rolling time horizons.     

基于社会网络的犯罪组织关系挖掘

在对犯罪组织进行图形化构建的基础上,利用社会网络方法对犯罪组织关系进行挖掘。犯罪组织关系挖掘包含根据社会网络的中心性指标提出一种犯罪组织重点人员判定方法和挖掘犯罪组织成员间的关系。实验结果显示,犯罪组织关系挖掘方法具有较好的性能和挖掘效果。     

Making recommendations by integrating information from multiple social networks

It is becoming a common practice to use recommendation systems to serve users of web-based platforms such as social networking platforms, review web-sites, and e-commerce web-sites. Each platform produces recommendations by capturing, maintaining and analyzing data related to its users and their behavior. However, people generally use different web-based platforms for different purposes. Thus, each platform captures its own data which may reflect certain aspects related to its users. Integrating data from multiple platforms may widen the perspective of the analysis and may help in modeling users more effectively. Motivated by this, we developed a recommendation framework which integrates data collected from multiple platforms. For this purpose, we collected and anonymized datasets which contain information from several social networking and social media platforms, namely BlogCatalog, Twitter, Flickr, Facebook, YouTube and LastFm. The collected and integrated data forms a consolidated repository that may become a valuable source for researchers and practitioners. We implemented a number of recommendation methodologies to observe their performance for various cases which involve using single versus multiple features from a single source versus multiple sources. The conducted experiments have shown that using multiple features from multiple sources is expected to produce a more concrete and wider perspective of user’s behavior and preferences. This leads to improved recommendation outcome.     

安徽气象为农服务大数据平台设计与应用

从安徽省气象为农信息服务的个性化、精准化、智能化需求出发,采用Hadoop架构、自然语言处理、相关度分析、大数据可视化等大数据和人工智能相关技术,研发安徽省气象为农服务大数据平台。汇集安徽省多部门涉农数据资源,通过建立用户行为画像、网络服务热点的预测,开展精准化的服务产品相关性推荐服务,并跟踪评估信息服务产品的网络传播服务效果,指导后续关键农时农事建议和决策服务产品的研发与制作,同时建立气象为农服务大数据展示系统,探索实现气象为农信息服务从“人找信息”到“信息找人”的转变。该平台已在安徽气象为农业务服务中应用,提升了服务能力,具有较好的行业知名度和社会影响力。     

大数据下的基于主题模型的社交网络链接预测

计算机技术和网络的发展使得数据呈爆炸式的涌现,社交媒体不断融入到人们的生活中,社会网络分析已成为研究的热点。随着大数据时代的到来,对社交网络链接算法研究产生巨大影响,原有的基于网络结构的预测方法已经渐渐不适应现状。因此,提出了一种基于主题模型的社交网络链接预测方法。首先以微博社交网络为数据源,将实验网络分为测试集和训练集;其次利用主题模型得到用户的主题特征,结合命名实体集和用户联系特征集合得到用户的兴趣特征相似性度量,加上网络结构相似性从而得到用户节点相似度,进而对社交网络链接进行预测;最终使用链接预测最常用的评价体系AUC来评价链接预测方法的效果。通过实验验证,该方法的预测准确率更高。     

基于词向量语义聚类的微博热点挖掘方法

随着社交媒体的迅速发展,信息过载问题越发严重,因此如何从海量、短小而充满噪声的社交媒体数据中发现和挖掘出热点话题或者热点事件成为一个重要的问题。结合社交媒体数据实时性、地理性、包含较多元数据等特点,提出了用户行为分析与文本内容分析相结合的热点挖掘方法。在内容分析过程中,提出了从更细的词语粒度进行聚类,以代替传统的在消息粒度进行聚类的经典方法。为了提高话题关键词提取的效果,引入了基于词向量技术,并通过语义聚类的方法进行热点挖掘。在真实数据集上的实验结果表明,该方法提取的关键词语义关联性强、话题划分效果好,在主要指标上优于传统的热点挖掘方法。     

基于线上线下关联推理的边缘节点热点预测

随着城市规模的实时数据处理和增强现实等一系列应用的广泛普及,亟待有效预测边缘计算机构下边缘节点的热点,从而为解决因分布、带宽、服务器性能带来的访问延迟问题提供解决方案.针对该问题,进行了一种边缘节点热点预测方法的研究,旨在根据用户活动相关的线上线下信息预测城市区域的边缘节点服务热点:根据城市各主要区域的线下人口流动量以及线上访问流量,采用卷积神经网络和长短期记忆网络提取相关特征,并由基于注意力机制进行线上特征和线下特征的关联推理,综合城市主要区域边缘节点的图嵌入表达预测各区域边缘节点的热点程度,从而为调配边缘节点资源提供依据.采用某南方城市移动用户数据集进行性能评估,与相关热点分析方法相比,该方法在预测准确性方面具有明显的优越性.