Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Methodology for crime forecasting.

More »

Fig 1 Expand

Fig 2.

Exponential smoothing and Bi-LSTM hybrid.

More »

Fig 2 Expand

Fig 3.

Architectural details of bi-directional LSTM and ES hybrid.

More »

Fig 3 Expand

Table 1.

Hyperparameters for hourly prediction model.

More »

Table 1 Expand

Table 2.

Depiction of NULL value in the dataset.

More »

Table 2 Expand

Fig 4.

Training, validation, and testing for time-series forecasting.

More »

Fig 4 Expand

Fig 5.

Sliding window strategy for selecting the best input.

More »

Fig 5 Expand

Table 3.

Results of using various moving window sizes hourly.

More »

Table 3 Expand

Table 4.

The results of forecasting the number of crimes hourly for the two models using two methods.

More »

Table 4 Expand

Fig 6.

Hourly loss plot between training and evaluation without including the number of crime types in ES-BiLSTM.

More »

Fig 6 Expand

Fig 7.

Hourly loss plot between training and evaluation by including the number of crime types in ES-BiLSTM.

More »

Fig 7 Expand

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.

More »

Fig 8 Expand

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.

More »

Fig 9 Expand

Fig 10.

Comparison of the proposed approach with state-of-the-art methods.

More »

Fig 10 Expand