Innovative LSGTime Model for Crime Spatiotemporal Prediction Based on MindSpore Framework
This work addresses crime prediction for urban safety and resource allocation, but it is incremental as it combines existing techniques like LSTM, GRU, and attention mechanisms.
The paper tackled crime spatiotemporal prediction by proposing the LGSTime model, which integrates LSTM, GRU, and Multi-head Sparse Self-attention, achieving performance improvements of 2.8%, 1.9%, and 1.4% in MSE, MAE, and RMSE metrics compared to a CNN baseline on real-world datasets.
With the acceleration of urbanization, the spatiotemporal characteristics of criminal activities have become increasingly complex. Accurate prediction of crime distribution is crucial for optimizing the allocation of police resources and preventing crime. This paper proposes LGSTime, a crime spatiotemporal prediction model that integrates Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and the Multi-head Sparse Self-attention mechanism. LSTM and GRU capture long-term dependencies in crime time series, such as seasonality and periodicity, through their unique gating mechanisms. The Multi-head Sparse Self-attention mechanism, on the other hand, focuses on both temporal and spatial features of criminal events simultaneously through parallel processing and sparsification techniques, significantly improving computational efficiency and prediction accuracy. The integrated model leverages the strengths of each technique to better handle complex spatiotemporal data. Experimental findings demonstrate that the model attains optimal performance across four real - world crime datasets. In comparison to the CNN model, it exhibits performance enhancements of 2.8\%, 1.9\%, and 1.4\% in the Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE) metrics respectively. These results offer a valuable reference for tackling the challenges in crime prediction.