Mobility Detection Using Everyday GSM Traces

By Timothy Sohn, Alex Varshavsky, Anthony LaMarca, Mike Y. Chen, Tanzeem Choudhury, I. Smith, Sunny Consolvo, Jeffrey Hightower, W. Griswold, Eyal de Lara. Ubiquitous Computing, 2006

334 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Transportation

View Paper: https://www.semanticscholar.org/paper/95b1ac775cc163008f2c82efc3b18ffe4c1ce0ab

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

In Transportation

Citations in the corpus

Activity sensing in the wild: a field trial of ubifit garden (2008, methodology): “’s [20] software for GSM smart phones that uses the rate of change in cell tower observations to approximate the user’s daily step count.”
PEIR, the personal environmental impact report, as a platform for participatory sensing systems research (2009, methodology): “The work of [25, 26] uses neighboring cells in addition to the current serving cell from mobile phones to recognize high-level properties of user mobility.”
Recommending friends and locations based on individual location history (2011, background): “11 [Krumm and Horvitz 2004] and GSM networks [Timothy et al. 2006], some projects attempt to recognize user mobility, such as stationary and walking, from the location histories of a group of people.”
Using mobile phones to determine transportation modes (2010, methodology): “In more recent implementations, audio is eliminated as a sensor modality, and instead either identifier/signal strength information from multiple cell towers (up to seven) [Froehlich et al. 2009; Sohn et al. 2006] or coarse speed measures from network endpoint localization [Welbourne et al.”
Ranges of human mobility in Los Angeles and New York (2011, methodology): “use GSM data to determine mobility modes, such as walking or driving, of three individuals [9].”
Energy-efficient rate-adaptive GPS-based positioning for smartphones (2010, methodology): “Prior work has proposed the use of GSM signatures, which include information about visible cell-towers and their RSS (Received Signal Strength), to detect large scale movement [6] or recognize mobility modes [24].”
Accelerometer-based transportation mode detection on smartphones (2013, methodology): “[27] use changes in the GSM signal environment for coarsegrained detection of transportation modalities.”
Mining user similarity based on location history (2008, background): “11 [11] and GSM network [16], some projects attempt to recognize user mobility, such as stationary and walking, etc.”
Trajectory Data Mining (2015, background): “[102] attempted to classify the mobility of a user into three status, consisting of stationary, walking and driving.”
Understanding mobility based on GPS data (2008, background): “Thus, only three simple motions including stationary, walking and driving can be inferred in paper [11], and LOCADIO can only differentiate two fundamental types of activities, Still and Moving.”
Mining Individual Life Pattern Based on Location History (2009, methodology): “[17] develops a system called LOCADIO, which uses Wi-Fi signal strengths from existing access points measured on the client to infer user mobility such as, stationary and walking, etc.”
Predicting User-Cell Association in Cellular Networks from Tracked Data (2009, background): “in [10] showed how coarse-grained GSM data from mobile phones (e.”
Urban Sensing Using Mobile Phone Network Data: A Survey of Research (2014, background): “For example, in (Sohn et al., 2006; Sevtsuk and Ratti, 2010; de Jonge et al., 2012) authors explore how coarse-grained GSM data from mobile phones can be used to recognize high-level properties of user mobility and daily step count.”
Understanding and capturing people’s privacy policies in a mobile social networking application (2009, methodology): “the user is indoors), the application falls back on a GSM triangulation solution developed by Intel Research Seattle [26].”