Task Price Prediction Based on Clustering and DNN in Crowdsensing

Table 1

Automatic clustering.

Number of clusters	Schwarz’s Bayesian criterion (BIC)	BIC change	Ratio of BIC changes	Ratio of distance measures
1	1395505.120	—	—	—
2	1031788.811	−363716.308	1.000	1.529
3	793926.416	−237862.395	0.654	1.178
4	592106.081	−201820.335	0.555	1.994
5	490969.964	−101136.117	0.278	2.191
6	444899.938	−46070.026	0.127	1.403
7	412123.535	−32776.403	0.090	1.263
8	386203.133	−25920.402	0.071	1.004
9	360383.844	−25819.289	0.071	1.152
10	337997.111	−22386.733	0.062	1.035