Abstract
Nowadays, the increase in criminal activities has resulted in a massive generation of crime reports describing the details of the crime incidents. Analyzing these reports for crime type prediction helps the law enforcement agencies deal with crime prevention strategies. But it is quite a demanding and difficult task to consider these reports individually and determine their crime types. In the proposed work, an efficient classifier has been designed to analyze the crime reports which not only predict the crime types of the reports but at the same time upgrades itself with the help of new crime reports. Therefore, this task demands an incremental supervised learning technique that continuously learns the existing classifier based on the new set of reports and information already extracted from the old set of reports. Developing an incremental classifier infuses the knowledge that keep coming from the newly generated reports and help in increasing the report-discriminating power of the classifier. In this work, we have applied a Bi-objective Particle Swarm Optimization technique for generating an efficient incremental classifier for classifying and predicting the crime reports dynamically. Crime reports of different countries, such as India, the United States of America, and the United Arab Emirates, have been collected from online classified newspapers to measure the performance of the proposed as well as some state-of-the-art classifiers. Also, the method has been evaluated based on an unbiased police witness narrative crime reports and finally, a statistical test has been performed using all four considered datasets to measure the statistical significance of the proposed methodology.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.