Automated time activity classification based on global positioning system (GPS) tracking data

Table 1 Time activity classification using the rule-based model^a

		Indoor (modeled)	Outdoor static (modeled)	Outdoor walking (modeled)	In-vehicle travel (modeled)	Sensitivity^b	Specificity^c	Precision^d
Model evaluation against the HCTLS data	Indoor (coded)	284830	9840	1002	1362	84.1%	81.9%	95.9%
	Outdoor static (coded)	51991	12901	2336	5994	51.7%	84.2%	17.6%
	Outdoor walking (coded)	1102	1145	9096	827	68.4%	99.2%	74.7%
	In-vehicle travel (coded)	778	1073	857	21127	72.1%	99.3%	88.6%
Model evaluation against the supplemental UCI data	Indoor (coded)	103930	5430	134	144	94.8%	82.6%	98.2%
	Outdoor static (coded)	1558	2298	169	214	54.2%	94.4%	26.0%
	Outdoor walking (coded)	284	764	646	193	34.2%	99.6%	57.4%
	In-vehicle travel (coded)	114	336	176	4512	87.8%	99.5%	89.1%

^aThe rule-based model was developed based on logic and the summary statistics of manually-classified time activity classifications of HCTLS data.
^bSensitivity was calculated as true positive estimation/(true positive estimation + false negative estimation).
^cSpecificity was calculated as true negative estimation/(true negative estimation + false positive estimation).
^dPrecision was calculated as true positive estimation/(true positive estimation + false positive estimation).

ISSN: 1476-069X