Human Scream Detection

Abstract

Crime, including murders, assaults, and thefts, is a persistent issue worldwide, posing a significant concern for society. A common challenge is that police often arrive at crime scenes too late, primarily due to insufficient access to timely and accurate information. To address this issue, a concealed desktop application is suggested. This application employs advanced technologies, such as machine learning and deep learning models like Support Vector Machines (SVM) and Multilayer Perceptron (MLP), to swiftly detect and analyze human sounds while operating discreetly in the background. In the event of an emergency, the application initiates an automated process that sends text messages to designated contacts. This innovative technology enhances the accuracy of threat detection and response times by differentiating specific human sounds from background noise. The aim is to mitigate the adverse effects of crime by improving community safety and reducing the impact of crime on individuals and society as a whole. Following these guidelines will increase public confidence in their ability to safeguard their communities and themselves.