Designing a Crime-Prevention System by Converging Big Data and IoT

Jeon, Jin-Ho; Jeong, Seung-Ryul

doi:10.7472/jksii.2016.17.3.115

Cited by 14 publications

(19 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Except for the structured data source from crime-related government organizations, published crime open data and call data records, the collection of data from social network services, newspaper articles, and public information repository are unstructured and incomplete [5]- [11]. The data collection techniques used to collect unstructured data is mainly web crawler [5], [9], [10]. After the collection of unstructured data, Isuru et al used a classifier, entity extractor, and duplicate detector techniques to preprocess the data [10].…”

Section: A Crime Data Collection and Preprocessingmentioning

confidence: 99%

“…After the collection of unstructured data, Isuru et al used a classifier, entity extractor, and duplicate detector techniques to preprocess the data [10]. Likewise, Nasution et al and Jeon et al used map-reduce while Zhang used intelligence analysis for data preprocessing [5], [9], [11]. Despite various techniques used during data preprocessing, all the techniques are aimed to reduce and eliminate the duplication of data during data collection.…”

Section: A Crime Data Collection and Preprocessingmentioning

confidence: 99%

“…For structured data, preprocessing techniques are used to transform the data into the desired format. The techniques used are XML parser, metadata, map reduce and GIS raster data analysis [5]- [8]. Table I is the summary of researches in crime data collection and preprocessing.…”

Section: A Crime Data Collection and Preprocessingmentioning

confidence: 99%

See 2 more Smart Citations

A Proposed Bi-layer Crime Prevention Framework Using Big Data Analytics

Tao¹,

Yang²,

Salim³

et al. 2018

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

The future of science and technology sounds very promising. The need to adopt new technologies while navigating towards industry 4.0 has changed the perceptions of law enforcement agency to contend against criminal minds. It is sad but true that the conventional crime prevention system followed by government agencies is not effective for long-term implications. With advanced technologies that continuously generate and exchange data, big data analytics can be applied to predict and prevent crime from happening. However, dealing with the overwhelming amount of complex and heterogeneous crime-related data is never an easy task. There are many data analysis techniques, and each of them has its strengths and weaknesses. In order to identify the most efficient techniques, recent literature is reviewed to spotlight the trend as well as to shed light on the research gaps and challenges in various areas. The areas include crime data collection and preprocessing, crime data analysis, crime prediction and crime prevention. These techniques are further analyzed by considering the advantages and disadvantages, which then provides insight to propose a bi-layer crime prevention framework. The first layer intends to support the law enforcement agency's daily operation while the second layer serves as a countermeasure for the first layer. Both layers aim to reduce the crime rate by involving law enforcement agency through the utilization of various significant data sources and techniques effectively. The proposed crime prevention framework will progressively collect data to deter criminal behavior for the city's environmental design. Ultimately, a safe and secure city is molded shortly.

show abstract

Section: A Crime Data Collection and Preprocessingmentioning

confidence: 99%

Section: A Crime Data Collection and Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

A Proposed Bi-layer Crime Prevention Framework Using Big Data Analytics

Tao¹,

Yang²,

Salim³

et al. 2018

Int. J. Adv. Sci. Eng. Inf. Technol.

View full text Add to dashboard Cite

show abstract

“…There is a new phenomenon: the 'predictive power' of BD (McGregor et al, 2013;Siegel, 2013;Simon, 2014;White House, 2014;Ferguson, 2015;Jeon and Jeong, 2016). A company can look much more deeply than before into its customers' habits with the help of BD, and based on that, it can exercise, for example, discriminatory practices.…”

Section: Risksmentioning

confidence: 99%

Law and Legal Science in the Age of Big Data

Ződi

2017

Intersections

View full text Add to dashboard Cite

The connection between Big Data (BD) and law can be thematised in several ways. This article aims to contribute to the understanding of the different levels of interplay between Big Data, law and legal science. The paper firstly considers Big Data as the subject of legal regulation. Accordingly, it overviews the moral questions surrounding Big Data, BD's predictive potential as well as the impacts of it on legal framework rules regarding privacy, data protection, competition and business regulation. The next section understands Big Data as a tool in the regulator's and the lawyer's hand. It discusses the new ways of 'Big Data-based social engineering' as well as the creation of predictive tools and inferencing techniques based on Big Data in policing, law enforcement and litigation. Then the paper investigates the use of BD in legal science, thus the fourth section considers Big Data as a research tool. It seeks to explore the use of legal data-sets and textual corpuses as BD. In addition, it sheds some light on the wider impacts of statistical analysis, natural language processing, content analysis, machine learning and behavioural prediction on legal science. Finally, the paper gives some insight into the relationship between traditional doctrinal scholarship and the new types of BD-based research.

show abstract

“…Clustering data mining technique can be used for crime detection and crime prevention. Jin-ho & Seung-Ryul [18] used text mining to extract and treat useful information based on the natural language processing, opinion mining to assigned positive and negative or neutral preference to social media unstructured data, and social network analysis to discover viral objects by measuring a user's reputation or influence based on their connection network and clustering analysis. Ceccato, & Uittenbogaard [19] assessed the crime rates in underground stations using space crime.…”

Section: Literature Reviewmentioning

confidence: 99%