Crime Prediction and Analysis against women Using LRSRI-Missing Value Imputation and FIPSO - Optimum Feature Selection Methods

Abstract

Data investigation is the method of considering crude measurements in arrange to draw conclusions around them. Many statistics evaluation techniques and tendencies had been automated into mechanical techniques and algorithms in such a manner that they provided raw statistics for human consumption. Machine learning could be a portion of artificial intelligence that permits computer frameworks to "analyze" their own statistics and improve them over time without being explicitly programmed. Machine learning algorithms can understand patterns in statistics and analyze them to make their own predictions. Lost esteem ascription is one of the foremost vital procedures in data pre-processing and it is additionally the most prepare of information examination. Ascription of lost information for a variable replaces lost information with a esteem inferred from an assess of the dispersion of that variable. Basic accusation employments as it were one suspicion. Numerous ascriptions employments diverse gauges to reflect the instability in evaluating this dispersion. In this article, The proposed method LRSRI used for impute the missing values on Crime against Women Data-set(CAW).The Linear Regression Imputation and Stochastic regression imputations are used in this method.Feature selection is another important data preprocessing techniques.This is often called attribute selection or feature selection. The most important problem in predictive modeling is the mechanical selection of features in the data. In this work,the proposed method FIPSO implemented for feature selection.This is feature importance and Particle Swarm Optimization based method.The main objective of this work is predict the crime rate against women in India based on 2001 to 2021 crime recorded against women in India.This Data set is collected from Data.gov.in.Finally The predicted result is compared with recent NCRB crime report.The proposed method LRSRI and FIPSO has given 98.34% accuracy of crime prediction.In feature,This outcome will be valuable for the crime office to control the CAW in India.