基于聚类的数据加权优化在犯罪预测中的应用

近年来，我国传统暴力犯罪与成年人犯罪呈下降态势，但是，犯罪案由层出不穷。为有效提升公安实践工作中犯罪预测能力，打击各类违法犯罪事件,本文针对犯罪数据，提出一种新型犯罪预测模型。利用密度聚类分析方法将犯罪数据分类，然后进行数据降维提取关键属性生成特征数据，继而对特征数据进行加权优化并采用机器学习的方式对特征数据进行学习，从而预测犯罪案由。实验结果表明，与传统方法相比，本文方法具有更好的预测效果，为公安实践工作中类似案件的侦破和预防，提供新的路径支撑。     

CrimeTelescope: crime hotspot prediction based on urban and social media data fusion

Crime is a complex social issue impacting a considerable number of individuals within a society. Preventing and reducing crime is a top priority in many countries. Given limited policing and crime reduction resources, it is often crucial to identify effective strategies to deploy the available resources. Towards this goal, crime hotspot prediction has previously been suggested. Crime hotspot prediction leverages past data in order to identify geographical areas susceptible of hosting crimes in the future. However, most of the existing techniques in crime hotspot prediction solely use historical crime records to identify crime hotspots, while ignoring the predictive power of other data such as urban or social media data. In this paper, we propose CrimeTelescope, a platform that predicts and visualizes crime hotspots based on a fusion of different data types. Our platform continuously collects crime data as well as urban and social media data on the Web. It then extracts key features from the collected data based on both statistical and linguistic analysis. Finally, it identifies crime hotspots by leveraging the extracted features, and offers visualizations of the hotspots on an interactive map. Based on real-world data collected from New York City, we show that combining different types of data can effectively improve the crime hotspot prediction accuracy (by up to 5.2%), compared to classical approaches based on historical crime records only. In addition, we demonstrate the usability of our platform through a System Usability Scale (SUS) survey on a full prototype of CrimeTelescope.     

多尺度视角特征动态融合的盗窃犯罪预测模型

针对盗窃犯罪时空预测特征融合不精、时序动态适应性不足问题,提出自注意力和多尺度多视角特征动态融合的预测模型。首先,以盗窃发案的位置信息为基础,将数据投射到地图栅格内,通过构建一种可将不同时序长度案件数据匹配为自适应长度数据的方法,并组合向量映射后的天气、作案时间、地理位置等属性,构造多维度特征融合的输入向量;其次,采用自注意力机制生成多视角特征动态融合的向量;最后,通过采用多尺度窗口CNN对多视角特征动态融合向量进行编码后送入分类器,预测出每个地图栅格内的发案态势。在某市盗窃数据集上验证,本文方法在3种地理栅格尺度下,预测准确率最高可达到0.899,显著优于其他对比模型。     

Understanding urban structures and crowd dynamics leveraging large-scale vehicle mobility data

A comprehensive understanding of city structures and urban dynamics can greatly improve the efficiency and quality of urban planning and management, while the traditional approaches of which, such as manual surveys, usually incur substantial labor and time. In this paper, we propose a data-driven framework to sense urban structures and dynamics from large-scale vehicle mobility data. First, we divide the city into fine-grained grids, and cluster the grids with similar mobility features into structured urban areas with a proposed distance-constrained clustering algorithm (DCCA). Second, we detect irregular mobility traffic patterns in each area leveraging an ARIMA-based anomaly detection algorithm (ADAM), and correlate them to the urban social and emergency events. Finally, we build a visualization system to demonstrate the urban structures and crowd dynamics.We evaluate our framework using real-world datasets collected from Xiamen city, China, and the results show that the proposed framework can sense urban structures and crowd comprehensively and effectively.     

Exploring traffic congestion correlation from multiple data sources

Traffic congestion is a major concern in many cities around the world. Previous work mainly focuses on the prediction of congestion and analysis of traffic flows, while the congestion correlation between road segments has not been studied yet. In this paper, we propose a three-phase framework to explore the congestion correlation between road segments from multiple real world data. In the first phase, we extract congestion information on each road segment from GPS trajectories of over 10,000 taxis, define congestion correlation and propose a corresponding mining algorithm to find out all the existing correlations. In the second phase, we extract various features on each pair of road segments from road network and POI data. In the last phase, the results of the first two phases are input into several classifiers to predict congestion correlation. We further analyze the important features and evaluate the results of the trained classifiers through experiments. We found some important patterns that lead to a high/low congestion correlation, and they can facilitate building various transportation applications. In addition, we found that traffic congestion correlation has obvious directionality and transmissibility. The proposed techniques in our framework are general, and can be applied to other pairwise correlation analysis.     

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.     

Urban navigation beyond shortest route: The case of safe paths

Advancements in mobile technology and computing have fostered the collection of a large number of civic datasets that capture the pulse of urban life. Furthermore, the open government and data initiative has led many local authorities to make these datasets publicly available, hoping to drive innovation that will further improve the quality of life for the city-dwellers. In this paper, we develop a novel application that utilizes crime data to provide safe urban navigation. Specifically, using crime data from Chicago and Philadelphia we develop a risk model for their street urban network, which allows us to estimate the relative probability of a crime on any road segment. Given such model we define two variants of the SafePaths problem where the goal is to find a short and low-risk path between a source and a destination location. Since both the length and the risk of the path are equally important but cannot be combined into a single objective, we approach the urban-navigation problem as a biobjective shortest path problem. Our algorithms aim to output a small set of paths that provide tradeoffs between distance and safety. Our experiments demonstrate the efficacy of our algorithms and their practical applicability.     

新时期手机网络犯罪研究

随着科技的发展,手机网络犯罪现象越来越多。文章介绍了新时期手机网络犯罪的概念,分析了手机网络犯罪的表现形式和特点,提出了针对手机网络犯罪的几点防范措施。     

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.     

The strongest does not attract all but it does attract the most – evaluating the criminal attractiveness of shopping malls using fuzzy logic

Crime attractors are locations (e.g. shopping malls) that attract criminally motivated offenders because of the presence of known criminal opportunities. Although there have been many studies that explore the patterns of crime in and around these locations, there are still many questions that linger. In recent years, there has been a growing interest to develop mathematical models in attempts to help answer questions about various criminological phenomena. In this paper, we are interested in applying a formal methodology to model the relative attractiveness of crime attractor locations based on characteristics of offenders and the crime they committed. To accomplish this task, we adopt fuzzy logic techniques to calculate the attractiveness of crime attractors in three suburban cities in the Metro Vancouver region of British Columbia, Canada. The fuzzy logic techniques provide results comparable with our real‐life expectations that offenders do not necessarily commit significant crimes in the immediate neighbourhood of the attractors, but travel towards it, and commit crimes on the way. The results of this study could lead to a variety of crime prevention benefits and urban planning strategies.     

基于自监督学习语言模型的罪名预测研究

针对解决法律判决预测中的罪名预测问题,为了更高效地捕捉案件事实描述中上下文的语义信息,提出了一种结合ALBERT（A Lite BERT）和卷积神经网络CNN（TextCNN）的中文罪名预测模型ALBT。模型利用ALBERT模型将法律文本的事实描述转化成向量表示,提取事实描述中的关键特征,把提取到的特征送入卷积神经网络TextCNN模型中进行分类预测,最终完成对事实描述中的罪名预测。实验在2018“中国法研杯”司法人工智能挑战赛构建的数据集上精度达到了88.1%。实验结果表明,模型在中文罪名预测上能够达到更好的预测效果。     

Exploring associations between streetscape factors and crime behaviors using Google Street View images

Understanding the influencing mechanism of the urban streetscape on crime is fairly important to crime prevention and urban management. Recently, the development of deep learning technology and big data of street view images, makes it possible to quantitatively explore the relationship between streetscape and crime. This study computed eight streetscape indexes of the street built environment using Google Street View images firstly. Then, the association between the eight indexes and recorded crime events was revealed with a poisson regression model and a geographically weighted poisson regression model. An experiment was conducted in downtown and uptown Manhattan, New York. Global regression results show that the influences of Motorization Index on crimes are significant and positive, while the effects of the Light View Index and Green View Index on crimes depend heavily on the socio-economic factors. From a local perspective, the Pedestrian Space Index, Green View Index, Light View IndexandMotorization Index have a significant spatial influence on crimes, while the same visual streetscape factors have different effects on different streets due to the combination differences of socio-economic, cultural and streetscape elements. The key streetscape elements of a given street that affect a specific criminal activity can be identified according to the strength of the association. The results provide both theoretical and practical implications for crime theories and crime prevention efforts.     

网络诈骗的概念、主要表现及犯罪构成研究

随着互联网的发展,网络成为一种新型的犯罪工具、犯罪场所和犯罪对象。作为网络犯罪的一种,网络诈骗指以非法占有为目的,利用互联网采用虚拟事实或者隐瞒事实真相的方法,骗取数额较大的公私财物的行为。本文在界定网络犯罪概念的基础上,对其基本特征、主要表现形式和犯罪构成作了进一步的分析探讨。     

A model to estimate and interpret the energy-efficiency of movement patterns in urban road traffic

Urban road traffic is highly dynamic. Traffic conditions vary in time and with location and so do the movement patterns of individual road users. In this article, a movement pattern is the behaviour of a car when traversing a road link in an urban road network. A movement pattern can be recorded with a global navigation satellite system (GNSS), such as the Global Positioning System (GPS). A movement pattern has a specific energy-efficiency, which is a measure of how fuel-intensively the car is moving. For example, a car driving uniformly at medium speed consumes little fuel and, therefore, is energy-efficient, whereas stop-and-go driving consumes much fuel and is energy-inefficient. In this article we introduce a model to estimate the energy-efficiency of movement patterns in urban road traffic from GNSS data. First, we derived statistical features about the car's movement along the road. Then, we compared these to fuel consumption data from the car's controller area network (CAN) bus, normalized to the car's overall range of fuel consumption. We identified the optimal feature set for prediction. With the optimal feature set we trained, tested and verified a model to estimate energy-efficiency, with the fuel consumption serving as ground truth. Existing fuel consumption models usually view movement as a snapshot. Thus, the behaviour of the car remains unknown that causes a movement pattern to be energy-efficient or energy-inefficient. Our model views movement as a process and allows to interpret this process. A movement pattern can, for example, be energy-inefficient because the car is driving in stop-and-go traffic, because it is travelling at high speed, or because it is accelerating. Our model allows to distinguish between these different types of behaviours. Thus, it can provide new insights into the dynamics of urban road traffic and its energy-efficiency.     

Vehicle collision risk estimation based on RGB-D camera for urban road

Traffic violation is the main cause of traffic accidents. To reduce the incidence of traffic accidents, the common practice at present is to strength the penalties for traffic violation. However, little attention has been paid to issue warning for dangerous driving behaviors, especially for the case where two vehicles have a good chance of collision. In this paper, a framework for collision risk estimation using RGB-D camera is proposed for vehicles running on the urban road, where the depth information is fused with the video information for accurate calculation of the position and speed of the vehicles, two essential parameters for motion trajectory estimation. Considering that the motion trajectory or its differences can be considered as a steady signal, a method based on autoregressive integrated moving average (ARIMA) models is presented to predict vehicle trajectory. Then, the collision risk is estimated based on the predicted trajectory. The experiments are carried out on the data from the real vehicles. The result shows that the accuracy of position and speed estimation can be guaranteed within urban road and the error of trajectory prediction is very minor which is unlikely to have a significant impact on calculating the probability of collision in most situations, so the proposed framework is effective in collision risk estimation.     

An investigation of email processing from a risky decision making perspective

The prevalence of cyber crimes has threatened the business model enabled by email. Users have to evaluate email related risks before forming their attitude and read intention toward commercial emails. Drawing on a seminal theoretical framework in risky decision making, we propose a research model that incorporates computer risk taking propensity and email risk perception as influential in cultivating commercial email attitude and read intention. The research model is empirically validated using survey data and the results provide significant support. This study contributes to the literature on email use by exploring the process of risky decision making and influence sources.     

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.     

Crime analysis through spatial areal aggregated density patterns

Intelligent crime analysis allows for a greater understanding of the dynamics of unlawful activities, providing possible answers to where, when and why certain crimes are likely to happen. We propose to model density change among spatial regions using a density tracing based approach that enables reasoning about large areal aggregated crime datasets. We discover patterns among datasets by finding those crime and spatial features that exhibit similar spatial distributions by measuring the dissimilarity of their density traces. The proposed system incorporates both localized clusters (through the use of context sensitive weighting and clustering) and the global distribution trend. Experimental results validate and demonstrate the robustness of our approach.     

Deep learning based origin-destination prediction via contextual information fusion

Origin-Destination (OD) prediction which aims to predict the number of passenger’s travel demands from one region to another, is critically important to many real applications including intelligent transportation systems and public safety. The challenges of this problem lie in both the dynamic patterns of the human mobility data and data sparsity in issue in some regions. Thus it is difficult to model the complex spatio-temporal correlations of the human mobility data to predict the OD of their trips. Meanwhile, the crowd flows in different regions of a city and the context features (e.g. holiday, weather and POIs) are potentially useful to alleviate the data sparsity issue and improve the OD prediction, but are largely ignored by existing works. In this paper, we propose a deep spatio-temporal framework which named Auxiliary-tasks Enhanced Spatio-Temporal Network (AEST) to more effectively address the OD prediction problem. AEST trains a model to conduct OD inference via learning crowd flow and external data as auxiliary task. The novel Hierarchical Convolutional LSTM (HC-LSTM) Network is proposed which combines CNN, GCN and LSTM to effectively capture spatiao-temporal correlations. In addition, we design a Contextual Network (ContextNet) which learns representations of contextual information to assist OD prediction. We conduct extensive experiments over bike and taxicab trip datasets in New York. The results show that our method is superior to the state-of-art approaches.

     

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.