Comparison of home detection algorithms using smartphone GPS data

Verma, Rajat; Mittal, Shagun; Lei, Zengxiang; Chen, Xiaowei; Ukkusuri, Satish V.

doi:10.1140/epjds/s13688-023-00447-w

EPJ Data Science

Table 1 Summary of commonly used HDAs for different data and algorithm types

From: Comparison of home detection algorithms using smartphone GPS data

Kind	Algorithm class	Dataset type	Sources	Definition of home location
Supervised	Clustering	CDR	[17]	Most popular important cluster (Hartigan clustering of cell towers) using a logistic regression model
		GPS Survey / Tracking	[18]	Density-based spatial clustering of points with noise (DBSCAN)
			[19]	Most popular of the clusters based on DJ-cluster algorithm (modified DBSCAN clustering)
			[20]	Most popular of the ‘locations’ (obtained using modified k-means clustering of “places”)
	Clustering and heuristic	CDR	[21]	Binary classification algorithms; logistic regression, random forest, adaboosting and neural network models
	Heuristic	CDR	[12, 16, 22]	Most active tower for several data filter criteria such as nighttime constraints, weekday/weekend, and distinct days
Unsupervised	Clustering	CDR	[23]	Most frequent stay place (determined based on mean-shift clustering of sequenced cell tower locations)
		Passive GPS	[24]	Largest hierarchical cluster of stay points (detected based on Liu et al. (2008))
		Passive GPS	[3, 25]	Largest cluster of nighttime records using mean-shift clustering
	Heuristic	CDR	[26]	Location of the more popular of the two cell towers with the most records during non-work time
			[27]	Most frequently communicated tower during nights of weekdays, and weekends over the study period
			[28]	Most frequent location during night time
			[29]	Most common visited locations during night time
			[30]	Anchor point determination model (cell tower location satisfying specific rules of call count)
		Passive GPS	[31]	The centroid of the most visited 20 × 20 m cell during night hours
		Smart card	[32]	Center point-based HDA (iteratively updated centroid between pairs of subway stations)
			[33]	Most visited transit station
			[34]	Most popular transaction place (overall and active days); place with most nighttime activity
		Social media	[35, 36]	Place with the most check-ins on 3 social networks
		Social media	[37]	Place with the most check-ins during midnight

Back to article page