Mobile Information Systems / 2019 / Article / Tab 3

Research Article

Detecting Suspects by Large-Scale Trajectory Patterns in the City

Table 3

Experimental results with different classification methods.

ModelMethodsAccuracyPrecisionRecallF3 measure

RFSPM0.8180.0090.6020.079
LCM0.8670.0280.7860.212
TPM0.9120.0210.6940.165
LCM + TPM0.9150.0420.960.301

NBSPM0.8520.0070.7140.064
LCM0.8610.0180.7260.147
TPM0.9230.0150.8570.114
LCM + TPM0.9350.0140.8180.121

GBDTSPM0.8070.0120.6540.103
LCM0.8440.0290.7850.218
TPM0.9560.0220.7030.172
LCM + TPM0.9620.0510.9720.346

LRSPM0.8440.0090.6510.08
LCM0.8510.0130.6730.111
TPM0.8920.0180.6640.145
LCM + TPM0.9060.0190.8860.159

KNNSPM0.8370.0140.710.119
LCM0.8520.0340.710.238
TPM0.8690.0150.690.125
LCM + TPM0.9500.0350.860.256

OSCVMSPM0.9070.0180.9120.153
LCM0.9120.0190.9950.162
TPM0.9090.0180.9320.154
LCM + TPM0.9210.0170.9300.146

Deep learningMST-CNN0.9810.1910.6500.524

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19. Sign up here as a reviewer to help fast-track new submissions.