SocialMotion: Measuring the Hidden Social Life of a Building

Wren, Christopher R.; Ivanov, Yuri; Kaur, Ishwinder; Leigh, Darren; Westhues, Jonathan

doi:10.1007/978-3-540-75160-1_6

Cited by 11 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PlaceLab [Larson and Intille ] is an example of a "living lab", where hundreds of sensors are built into objects and the home environment (as opposed to wearable sensors) for various research purposes including activity recognition [Intille et al 2006,Logan et al 2007,Tapia et al 2004. Similar work has been done in an office space in which hundreds of motion sensors were used to study the social interactions and behaviors of approximately 100 subjects [Wren et al 2007]. In [Liao et al 2006], GPS data from wearable sensors is used for place labeling, specifically, recognizing significant locations and associating activities to these locations, such as "walking", "visiting", and "leisure".…”

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.

193

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

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.

193

109

View full text Add to dashboard Cite

show abstract

“…The literature reviewed for activity recognition in office spaces mostly used a Markov model approach to recognize activities, for instance, on a multi-room scale [96], or in a smaller meeting room scale [68]. The work by Wren et al [97], models office activity as a Markov process, to detect deviations of short-term behavior patterns from long-term patterns. The method finds time periods where the dynamics of the group behavior deviate significantly from "usual" behavior, successfully identifying holidays, periods of vacation, and periods of organizational disruption to the group (e.g., senior manager change).…”

Section: Indoor Sensorsmentioning

confidence: 99%

A probabilistic approach to socio-geographic reality mining

Farrahi¹

2011

SIGMultimedia Rec.

View full text Add to dashboard Cite

show abstract

“…Prior responses to these challenges have addressed the awareness shortfall, ranging from artistic interventions (Jeremijenko's "Live Wire") [12], to more utilitarian solutions [13]. Informed by insights from these works and others, our research examines the mediated cultivation of community activity awareness in a dynamic, distributed learning environment.…”

Section: Introductionmentioning

confidence: 99%

Abstract rendering of human activity in a dynamic distributed learning environment

Danielescu

Spicer

Tinapple

et al. 2011

Proceedings of the 19th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Contemporary distributed enterprises present challenges in terms of demonstrating community activity awareness and coherence across individuals and teams in collaborating networks. Building with a Memory is an experiential media system that captures and represents human activity in a distributed workplace over time.The system senses and analyzes movement in two workspaces in a mixed-use building with the results rendered in an informative ambient display in the building entryway. We describe the design and development of the system, together with insights from two studies of the installation and promising future directions.

show abstract

SocialMotion: Measuring the Hidden Social Life of a Building

Cited by 11 publications

References 10 publications

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

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

A probabilistic approach to socio-geographic reality mining

Abstract rendering of human activity in a dynamic distributed learning environment

Contact Info

Product

Resources

About