Seybold Report ISSN: 1533-9211
P. Suneel Kumar
Professor,Department of Electronics and Communication, Sridevi Women’s Engineering College, Hyderabad, India. psunilkumar.ece@gmail.com
V. Preethi Chowdary
U.G Student,Department of Electronics and Communication, Sridevi Women’s Engineering College, Hyderabad, India
Ch. Vyshnavi
U.G Student,Department of Electronics and Communication, Sridevi Women’s Engineering College, Hyderabad, India
M. Chandana
U.G Student,Department of Electronics and Communication, Sridevi Women’s Engineering College, Hyderabad, India
Vol 17, No 07 ( 2022 ) | DOI: 10.5281/zenodo.6876638 | Licensing: CC 4.0 | Pg no: 95-105 | Published on: 25-07-2022
Abstract
Now-a-days crime is one of the biggest and dominating problem in our society and its prevention is an important task. Daily there are huge numbers of crimes that are being committed frequently. Occurrence of these types of crimes requires keeping track of all the crimes and maintaining a database for same which may be used for future reference. The present problems faced are maintaining of proper dataset of crimes occurred and analyzing this data to help in predicting and solving the crimes in the future. The objective of this project is to analyze dataset which consist of number of crimes and predicting the types of crimes which may occur in future depending upon various circumstances. The thesis aim is to visualize and explore the methodological approach in finding the spatial patterning of crime through a geographical information system as a means for future guidance within spatial crime analysis. Two spatial analysis are performed, the Optimized Hot Spot-analysis tool and the kernel density estimation analysis tool. The average Nearest Neighbor-model was applied to the data for further statistical accuracy. For this supervised classification problem, Decision tree, Gaussian Tree, Gaussian Naïve Bayes, KNN, logistic Regression. This approach involves predicting crimes, classifying, Pattern detection and visualization with effective tools and technologies. Usage of past crime data trends helps us to correspond factors which might help understanding the future scope of crimes. In this work, various visualizing techniques and machine learning algorithms are acquired for predicting the crime distribution over a particular area. In the beginning step, the raw datasets were processed and visualized based on the requirement.
Keywords: