Fig 1.
Methodology for crime forecasting.
Fig 2.
Exponential smoothing and Bi-LSTM hybrid.
Fig 3.
Architectural details of bi-directional LSTM and ES hybrid.
Table 1.
Hyperparameters for hourly prediction model.
Table 2.
Depiction of NULL value in the dataset.
Fig 4.
Training, validation, and testing for time-series forecasting.
Fig 5.
Sliding window strategy for selecting the best input.
Table 3.
Results of using various moving window sizes hourly.
Table 4.
The results of forecasting the number of crimes hourly for the two models using two methods.
Fig 6.
Hourly loss plot between training and evaluation without including the number of crime types in ES-BiLSTM.
Fig 7.
Hourly loss plot between training and evaluation by including the number of crime types in ES-BiLSTM.
Fig 8.
Histogram of seasonal, hourly crime prediction without including crime types.
The blue color refers to the actual, while the orange color refers to the forecasting data.
Fig 9.
Histogram of seasonal, hourly predictions with including crime types.
The blue line refers to the actual, while the orange line refers to the forecast data.
Fig 10.
Comparison of the proposed approach with state-of-the-art methods.