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.

MTDP-FD framework.

More »

Fig 1 Expand

Fig 2.

Transform trajectory data into trajectory images.

The input is a GPS trajectory sequence Tr, and the output is a two-dimensional trajectory image Is.

More »

Fig 2 Expand

Fig 3.

Frequency domain processing of trajectory image.

More »

Fig 3 Expand

Fig 4.

Process of extracting deep features from trajectory image.

More »

Fig 4 Expand

Fig 5.

The processes of convolution.

(a) and (b) are two processes of convolution.

More »

Fig 5 Expand

Fig 6.

Max pooling.

More »

Fig 6 Expand

Fig 7.

The processes of RNN prediction.

More »

Fig 7 Expand

Fig 8.

The prediction accuracy of different D0.

More »

Fig 8 Expand

Fig 9.

The prediction accuracy of different D1.

More »

Fig 9 Expand

Fig 10.

The prediction accuracy of different D2 and D3.

More »

Fig 10 Expand

Fig 11.

The prediction accuracy of different input.

More »

Fig 11 Expand

Fig 12.

The prediction accuracy of different combinations.

More »

Fig 12 Expand

Table 1.

Comparison results.

More »

Table 1 Expand

Fig 13.

The spatial domain image and its deep features.

More »

Fig 13 Expand

Fig 14.

The low-frequency representation of image and its deep features.

More »

Fig 14 Expand

Fig 15.

The high-frequency representation of image and its deep features.

More »

Fig 15 Expand

Fig 16.

The intermediate-frequency representation of image and its deep features.

More »

Fig 16 Expand