Prediction of Criminal Suspect Characteristics with Application of Wavelet Neural Networks

Abstract

Crime incidents grow at a certain rate every year and become more complicated day by day, but at this stage, the development of the field of crime analysis and prediction is still lagging, so this paper applies a wavelet neural network to predict the characteristics of criminal suspects. Analyze the applicability of the WNN model, explore the principle of criminal suspect feature prediction, and study the basis of wavelet neural network analysis. Establish the face feature recognition framework, use the Morlet function and Mexican Hat function pair to optimize and improve the wavelet neural network, and construct the model evaluation index for evaluating the model prediction effect. Preprocessing the suspect feature point data by using the grayscale reflection in Haar features. Simulation experiments are used to analyze the performance of different algorithms and the prediction effect of criminal suspect features on wavelet neural networks. The proposed algorithm in this study is superior and has a lesser number of parameters than ResNet. From the loss curves of different algorithms, the algorithm proposed in this study has a faster-descending loss curve and a smaller loss rate in the epoch value of [100, 200] interval. The overall range of the evaluation indexes of the algorithms proposed in this study is above 88%, and the highest accuracy rate can reach 94.234%, which is a good performance of the algorithms and accurate prediction.