Jove
Visualize
Contact Us

Related Experiment Video

Updated: Mar 3, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.2K

Prediction of crime occurrence from multi-modal data using deep learning.

Hyeon-Woo Kang1, Hang-Bong Kang1

  • 1Dept. of Digital Media, Catholic University of Korea, Bucheon, Gyonggi-Do, Korea.

Plos One
|April 25, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A New 3D Object Pose Detection Method Using LIDAR Shape Set.

Sensors (Basel, Switzerland)·2018
Same author

Strain-dependent response to Cu(2+) in the expression of laccase in Pycnoporus coccineus.

Archives of microbiology·2015
Same author

Cloning and Molecular Characterization of β-1,3-Glucan Synthase from Sparassis crispa.

Mycobiology·2014
Same author

Generation and Evaluation of High β-Glucan Producing Mutant Strains of Sparassis crispa.

Mycobiology·2013
Same author

Breeding of new strains of mushroom by basidiospore chemical mutagenesis.

Mycobiology·2012
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

This study introduces a novel deep neural network (DNN) for enhanced crime prediction. By integrating environmental context with diverse data, the model improves accuracy in forecasting crime occurrences for better prevention strategies.

Area of Science:

  • Criminology
  • Data Science
  • Artificial Intelligence

Background:

  • Existing crime prediction models struggle with complex, non-linear data relationships and redundancies.
  • Traditional methods often treat diverse data sources (demographics, economics, education) equally, limiting predictive power.
  • Environmental context, like broken windows theory, is crucial for understanding and preventing crime.

Purpose of the Study:

  • To develop an enhanced crime prediction model using a feature-level data fusion method.
  • To incorporate environmental context information into deep neural network (DNN) based crime prediction.
  • To improve the accuracy and efficiency of crime occurrence forecasting.

Main Methods:

  • A deep neural network (DNN) architecture was designed with spatial, temporal, environmental context, and joint feature representation layers.

Related Experiment Videos

Last Updated: Mar 3, 2026

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

11.2K
  • Feature-level data fusion was employed, integrating crime statistics, demographic, meteorological data, and images from Chicago.
  • Statistical analyses were used to select crime-related data and manage data redundancy before training.

    • Main Results:

    • The proposed DNN model demonstrated superior accuracy in predicting crime occurrences compared to existing models.
    • The integration of environmental context significantly enhanced the model's predictive capabilities.
    • The feature-level fusion approach effectively handled data from multiple domains and reduced redundancies.

    Conclusions:

    • The DNN model incorporating environmental context offers a more accurate and efficient approach to crime prediction.
    • This method provides a robust framework for leveraging diverse datasets and contextual information for crime prevention.
    • The findings support the use of advanced machine learning techniques for optimizing police resource allocation and public safety.