Ngoc Thanh Nguyen Satoshi Tojo Le Minh Nguyen - Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2
Here you can read online Ngoc Thanh Nguyen Satoshi Tojo Le Minh Nguyen - Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2 full text of the book (entire story) in english for free. Download pdf and epub, get meaning, cover and reviews about this ebook. City: Cham, year: 2017, publisher: Springer International Publishing, genre: Home and family. Description of the work, (preface) as well as reviews are available. Best literature library LitArk.com created for fans of good reading and offers a wide selection of genres:
Choose a favorite category and find really read worthwhile books. Enjoy immersion in the world of imagination, feel the emotions of the characters or learn something new for yourself, make an fascinating discovery.
Book:
Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2
Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2: summary, description and annotation
We offer to read an annotation, description, summary or preface (depends on what the author of the book "Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2" wrote himself). If you haven't found the necessary information about the book — write in the comments, we will try to find it.
Ngoc Thanh Nguyen Satoshi Tojo Le Minh Nguyen: author's other books
Who wrote Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2? Find out the surname, the name of the author of the book and a list of all author's works by series.
Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2 — read online for free the complete book (whole text) full work
Below is the text of the book, divided by pages. System saving the place of the last page read, allows you to conveniently read the book "Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2" online for free, without having to search again every time where you left off. Put a bookmark, and you can go to the page where you finished reading at any time.
Ngoc Thanh Nguyen , Satoshi Tojo , Le Minh Nguyen and Bogdan Trawiski (eds.) Intelligent Information and Database Systems Lecture Notes in Computer Science 10192 10.1007/978-3-319-54430-4_1
Exploring Spatial and Social Factors of Crime: A Case Study of Taipei City
Nathan Kuo 1
(1)
Taipei American School, Taipei, 11152, Taiwan
(2)
Institute of Information Science, Academia Sinica, Taipei, 11529, Taiwan
Nathan Kuo (Corresponding author)
Email:
Chun-Ming Chang (Corresponding author)
Email:
Kuan-Ta Chen
Email:
Abstract
Recognizing the significance of transparency and accessibility of government information, the Taipei Government recently published city-wide crime data to encourage relevant research. In this project, we explore the underlying relationships between crimes and various geographic, demographic and socioeconomic factors. First we collect a total of 25 datasets from the City and other publicly available sources, and select statistically significant features via correlation tests and feature selection techniques. With the selected features, we use machine learning techniques to build a data-driven model that is capable of describing the relationship between high crime rate and the various factors. Our results demonstrate the effectiveness of the proposed methodology by providing insights into interactions between key geographic, demographic and socioeconomic factors and city crime rate. The study shows the top three factors affecting crime rate are educational attainment, marital status, and distance to schools. The result is presented to the Taipei City officials for future government policy decision making.
Keywords
Crime factor analysis Geographic information system Demographics Socio-economics Crime hotspots
Introduction
Study of crime, criminology, has long been a key area of research spanning across multiple disciplines from behavioral science, sociology, government and education policy planning, to the more recent interdisciplinary data science research. The extreme complexity, and the multifaceted nature of the problem has lead to a recent trend to focus heavily on empirical data analysis approach, with the help of increasing availability of data, and advancements in machine learning techniques in data science.
The study of crime often are in two main branches, one focuses on human side of criminal patterns, be it an individual repeated offender, or group/gangs of criminal organizations, with the goal of assisting police investigators in criminal investigations and crime prevention. The other branch focuses on the geographical, spatial, and demographics feature analysis, with the goal of better understanding key factors of why certain areas have higher crime rate (termed hotspots ). The immediate benefits of this branch of research is more effective law enforcement resource allocation, while the medium and long term goals are to better assist government policy making, which is the focus of our research.
Related Work
Chen et al. [] deserves a special mentioning in that it combines the traditional demographic features, such as migrant population, ethnicity, employment and so on, with anonymized and aggregated human behavioral data computed from mobile network activity (called smartsteps ) to better the prediction accuracy from averaging 50% to 70%.
All of the previous related work exhibits a common theme typical of the modeling and prediction of a complex problem based on incomplete datasets: the devil is in the detail , in all aspects of the process, from data collection, cleaning, feature selection/grouping, model building, to repetitive run-through specific model learning and approximation mechanisms. The paper takes the approach of combining spatial and demographic datasets, and uses SVM machine learning techniques to build the most accurate model. This work is summarized as follows: Sect. concludes our paper.
Data Description
Data used in this study are from various government open data repositories and publicly available sources []. We aggregate these data sources into three datasets, one describing the criminal cases, the other describing demographic characteristics of villages, and the last containing the physical locations of infrastructure and services in Taipei City.
3.1 Criminal Cases Dataset
The criminal cases dataset made available by the City covers three types of crime: burglary, car theft and bike theft, covering the time span from January 2015 to April 2016, with a total of 746 household theft, 132 car theft, and 452 bike theft records. Each record contains the crime ID, time (within 3 hours), date, and street address.
3.2 Village Profiling Dataset
Villages, under districts, are the fourth administrative subdivision of Taiwan, and there are, in total, 456 villages in Taipei. This dataset describes demographic and socioeconomic characteristics of the village and includes the following data fields: boundary, area, population, sex ratio. The datasets from various sources are matched with their village ID.
3.3 Point of Interest Dataset
This dataset includes the Point of Interest of infrastructure and services with potential impact on crime factors, including parks, banks, bus stops, Metro stations, street surveillance cameras, public restrooms, convenience stores, factories/warehouses, public parking lots, street-side parking spaces, police stations and city street lamps. Note that the location of schools include the location of kindergarten, elementary, junior and senior high school. Because these datasets come from a variety of sources with different coordinate systems, as a part of the data cleaning process, we use Google Maps Geocoding API for converting street addresses to WGS84-coordinates, and tools from the Information Science Institute from Academia Sinica [] for converting TWD97-coordinates to WGS84-coordinates.
Methodology
In this section, we apply the grip thematic mapping technique [] to combine the different layers of spatial data, including criminal cases dataset, village profiling dataset and point of interest dataset to predefined 500 m by 500 m cells. We extract various features from the above datasets and exploit feature selection and ranking methods to identify high impact features. We then build a data-driven model using the selected features to predict the probability of high crime rate of each individual cell. The remaining section details this experimental process.
4.1 Granularity Definition and Data Preprocessing
Each field in our datasets, such as location of police stations and marital status of villages, can be thought of as individual spatial layers. However, these data are not valuable or informative unless we define a suitable referencing system to combine and relate the various spatial layers. In order to address this, we apply the grid thematic technique and draw a grid over Taipei that creates 500 m by 500 m cells as visualized in Fig.. The reasons are two fold:
Fig. 1.
Visualization of every 500 * 500 cell in the Taipei City
Manually defining the grid ensures that each of our boundaries enclose the same area. Because the variance in the area of villages is too large, then it is more difficult to perform proximity analysis that can be generalized to each village.
Similar books «Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2»
Look at similar books to Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2. We have selected literature similar in name and meaning in the hope of providing readers with more options to find new, interesting, not yet read works.
Reviews about «Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2»
Discussion, reviews of the book Intelligent information and database systems: 9th Asian conference, ACIIDS 2017, Kanazawa, Japan April 3-5, 2017: proceedingsnPart 2 and just readers' own opinions. Leave your comments, write what you think about the work, its meaning or the main characters. Specify what exactly you liked and what you didn't like, and why you think so.
