Big data analytics and mining for effective visualization and trends forecasting of crime data

Mingchen Feng, Jiangbin Zheng, Jinchang Ren, Amir Hussain, Xiuxiu Li, Yue Xi, Qiaoyuan Liu

Research output: Contribution to journalArticle

Abstract

Big data analytics (BDA) is a systematic approach for analyzing and identifying different patterns, relations, and trends within a large volume of data. In this paper, we apply BDA to criminal data where exploratory data analysis is conducted for visualization and trends prediction. Several the state-of-the-art data mining and deep learning techniques are used. Following statistical analysis and visualization, some interesting facts and patterns are discovered from criminal data in San Francisco, Chicago, and Philadelphia. The predictive results show that the Prophet model and Keras stateful LSTM perform better than neural network models, where the optimal size of the training data is found to be three years. These promising outcomes will benefit for police departments and law enforcement organizations to better understand crime issues and provide insights that will enable them to track activities, predict the likelihood of incidents, effectively deploy resources and optimize the decision making process.

LanguageEnglish
Article number8768367
Pages106111-106123
Number of pages13
JournalIEEE Access
Volume7
Early online date22 Jul 2019
DOIs
Publication statusE-pub ahead of print - 22 Jul 2019

Fingerprint

Crime
Law enforcement
Visualization
Data mining
Statistical methods
Decision making
Neural networks
Big data
Deep learning

Keywords

  • big data analytics (BDA)
  • data mining
  • data visualization
  • neural network
  • time series forecasting

Cite this

Feng, Mingchen ; Zheng, Jiangbin ; Ren, Jinchang ; Hussain, Amir ; Li, Xiuxiu ; Xi, Yue ; Liu, Qiaoyuan. / Big data analytics and mining for effective visualization and trends forecasting of crime data. In: IEEE Access. 2019 ; Vol. 7. pp. 106111-106123.
@article{6ce2c614ccbf4609b138bc7f2dd0b875,
title = "Big data analytics and mining for effective visualization and trends forecasting of crime data",
abstract = "Big data analytics (BDA) is a systematic approach for analyzing and identifying different patterns, relations, and trends within a large volume of data. In this paper, we apply BDA to criminal data where exploratory data analysis is conducted for visualization and trends prediction. Several the state-of-the-art data mining and deep learning techniques are used. Following statistical analysis and visualization, some interesting facts and patterns are discovered from criminal data in San Francisco, Chicago, and Philadelphia. The predictive results show that the Prophet model and Keras stateful LSTM perform better than neural network models, where the optimal size of the training data is found to be three years. These promising outcomes will benefit for police departments and law enforcement organizations to better understand crime issues and provide insights that will enable them to track activities, predict the likelihood of incidents, effectively deploy resources and optimize the decision making process.",
keywords = "big data analytics (BDA), data mining, data visualization, neural network, time series forecasting",
author = "Mingchen Feng and Jiangbin Zheng and Jinchang Ren and Amir Hussain and Xiuxiu Li and Yue Xi and Qiaoyuan Liu",
year = "2019",
month = "7",
day = "22",
doi = "10.1109/ACCESS.2019.2930410",
language = "English",
volume = "7",
pages = "106111--106123",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "IEEE",

}

Big data analytics and mining for effective visualization and trends forecasting of crime data. / Feng, Mingchen; Zheng, Jiangbin; Ren, Jinchang; Hussain, Amir; Li, Xiuxiu; Xi, Yue; Liu, Qiaoyuan.

In: IEEE Access, Vol. 7, 8768367, 22.07.2019, p. 106111-106123.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Big data analytics and mining for effective visualization and trends forecasting of crime data

AU - Feng, Mingchen

AU - Zheng, Jiangbin

AU - Ren, Jinchang

AU - Hussain, Amir

AU - Li, Xiuxiu

AU - Xi, Yue

AU - Liu, Qiaoyuan

PY - 2019/7/22

Y1 - 2019/7/22

N2 - Big data analytics (BDA) is a systematic approach for analyzing and identifying different patterns, relations, and trends within a large volume of data. In this paper, we apply BDA to criminal data where exploratory data analysis is conducted for visualization and trends prediction. Several the state-of-the-art data mining and deep learning techniques are used. Following statistical analysis and visualization, some interesting facts and patterns are discovered from criminal data in San Francisco, Chicago, and Philadelphia. The predictive results show that the Prophet model and Keras stateful LSTM perform better than neural network models, where the optimal size of the training data is found to be three years. These promising outcomes will benefit for police departments and law enforcement organizations to better understand crime issues and provide insights that will enable them to track activities, predict the likelihood of incidents, effectively deploy resources and optimize the decision making process.

AB - Big data analytics (BDA) is a systematic approach for analyzing and identifying different patterns, relations, and trends within a large volume of data. In this paper, we apply BDA to criminal data where exploratory data analysis is conducted for visualization and trends prediction. Several the state-of-the-art data mining and deep learning techniques are used. Following statistical analysis and visualization, some interesting facts and patterns are discovered from criminal data in San Francisco, Chicago, and Philadelphia. The predictive results show that the Prophet model and Keras stateful LSTM perform better than neural network models, where the optimal size of the training data is found to be three years. These promising outcomes will benefit for police departments and law enforcement organizations to better understand crime issues and provide insights that will enable them to track activities, predict the likelihood of incidents, effectively deploy resources and optimize the decision making process.

KW - big data analytics (BDA)

KW - data mining

KW - data visualization

KW - neural network

KW - time series forecasting

UR - http://www.scopus.com/inward/record.url?scp=85071171694&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2019.2930410

DO - 10.1109/ACCESS.2019.2930410

M3 - Article

VL - 7

SP - 106111

EP - 106123

JO - IEEE Access

T2 - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8768367

ER -