Predictive Analytics for Crime Prevention in Smart Cities Using Machine Learning

Crime prevention in smart city infrastructure significantly impacts improving quality of human life. However, the substantial increase in the urban population in recent years affects accuracy, safety, and security. This paper presents a solution using the Hyperplane to improve the Radial Basis Function with Support Vector Machine (SVM) based on Machine Learning techniques to enhance accuracy, safety, and security. The SVM method aims to reduce crime rates through proactive measures based on predictive insights. The RBF kernel handles nonlinear relationships by mapping input features into a higher-dimensional space, allowing the model to capture complex patterns. Initially, data is obtained from the Chicago crime dataset and pre-processed by checking for missing values and performing feature scaling to ensure consistency. Feature selection is conducted using Principal Component Analysis (PCA) to identify relevant features from the data. Crime prediction using RBF with SVM is performed efficiently to enhance accuracy. The proposed RBF-SVM model is evaluated using the Chicago crime dataset, achieving a high accuracy of 0.89, a precision of 0.80, a recall of 0.82, and an F1-score of 0.85. The performance is compared to existing techniques such as Decision Tree (DT) and Long Short-Term Memory (LSTM).