Learning and Recognizing the Places We Go

Hightower, Jeffrey; Consolvo, Sunny; LaMarca, Anthony; Smith, Ian; Hughes, Jeff

doi:10.1007/11551201_10

Cited by 205 publications

(174 citation statements)

References 9 publications

Supporting

Mentioning

168

Contrasting

Unclassified

Order By: Relevance

“…Recently, Hightower et al [11] and then Kim et al [14] presented algorithms for determining semantically meaningful places based on continuous tracking of GSM and WiFi beacons. Kang et al [13] explored how clustering locations obtained through WiFi beacons can be used for identifying places people visit.…”

Section: Related Workmentioning

confidence: 99%

Identifying Important Places in People’s Lives from Cellular Network Data

Isaacman

Becker

Cáceres

et al. 2011

Lecture Notes in Computer Science

301

241

View full text Add to dashboard Cite

Abstract. People spend most of their time at a few key locations, such as home and work. Being able to identify how the movements of people cluster around these "important places" is crucial for a range of technology and policy decisions in areas such as telecommunications and transportation infrastructure deployment. In this paper, we propose new techniques based on clustering and regression for analyzing anonymized cellular network data to identify generally important locations, and to discern semantically-meaningful locations such as home and work. Starting with temporally sparse and spatially coarse location information, we propose a new algorithm to identify important locations. We test this algortihm on arbitrary cellphone users, including those with low call rates, and find that we are within 3 miles of ground truth for 88% of volunteer users. Further, after locating home and work, we achieve commute distance estimates that are within 1 mile of equivalent estimates derived from government census data. Finally, we perform carbon footprint analyses on hundreds of thousands of anonymous users as an example of how our data and algorithms can form an accurate and efficient underpinning for policy and infrastructure studies.

show abstract

Section: Related Workmentioning

confidence: 99%

Identifying Important Places in People’s Lives from Cellular Network Data

Isaacman

Becker

Cáceres

et al. 2011

Lecture Notes in Computer Science

301

241

View full text Add to dashboard Cite

show abstract

“…Also connected to our work is the problem of discovering places, which has been widely studied in mobile and ubiquitous computing using several types of location data [2,17,24,29]. The relation between places and interaction is evident in everyday life: specific interactions happen at specific places.…”

Section: Related Workmentioning

confidence: 99%

Human interaction discovery in smartphone proximity networks

Minh

Gática-Pérez

2011

Pers Ubiquit Comput

View full text Add to dashboard Cite

Since humans are fundamentally social beings and interact frequently with others in their daily life, understanding social context is of primary importance in building context-aware applications. In this paper, using smartphone Bluetooth as a proximity sensor to create social networks, we present a probabilistic approach to mine human interaction types in real life. Our analysis is conducted on Bluetooth data continuously sensed with smartphones for over one year from 40 individuals who are professionally or personally related. The results show that the model can automatically discover a variety of social contexts. We objectively validated our model by studying its predictive and retrieval performance.

show abstract

“…Other location-driven tasks have made use of Global System for Mobile Communications (GSM) data for indoor localization [Otsason et al 2005] or WiFi for large-scale localization [Letchner et al 2005]. The BeaconPrint algorithm [Hightower et al 2005] uses both WiFi and GSM to learn the places a user goes and detect if the user returns to these places.…”

Section: Related Workmentioning

confidence: 99%

Discovering routines from large-scale human locations using probabilistic topic models

Farrahi

Gática-Pérez

2011

ACM Trans. Intell. Syst. Technol.

195

109

View full text Add to dashboard Cite

In this work we discover the daily location-driven routines which are contained in a massive reallife human dataset collected by mobile phones. Our goal is the discovery and analysis of human routines which characterize both individual and group behaviors in terms of location patterns. We develop an unsupervised methodology based on two differing probabilistic topic models and apply them to the daily life of 97 mobile phone users over a 16 month period to achieve these goals. Topic models are probabilistic generative models for documents that identify the latent structure that underlies a set of words. Routines dominating the entire group's activities, identified with a methodology based on the Latent Dirichlet Allocation topic model, include "going to work late", "going home early", "working non-stop" and "having no reception (phone off)" at different times over varying time-intervals. We also detect routines which are characteristic of users, with a methodology based on the Author-Topic model. With the routines discovered, and the two methods of characterizing days and users, we can then perform various tasks. We use the routines discovered to determine behavioral patterns of users and groups of users. For example, we can find individuals that display specific daily routines, such as "going to work early" or "turning off the mobile (or having no reception) in the evenings". We are also able to characterize daily patterns by determining the topic structure of days in addition to determining whether certain routines occur dominantly on weekends or weekdays. Furthermore, the routines discovered can be used to rank users or find subgroups of users who display certain routines. We can also characterize users based on their entropy. We compare our method to one based on clustering using K-means. Finally, we analyze an individual's routines over time to determine regions with high variations, which may correspond to specific events.

show abstract

Learning and Recognizing the Places We Go

Cited by 205 publications

References 9 publications

Identifying Important Places in People’s Lives from Cellular Network Data

Identifying Important Places in People’s Lives from Cellular Network Data

Human interaction discovery in smartphone proximity networks

Discovering routines from large-scale human locations using probabilistic topic models

Contact Info

Product

Resources

About