Contextual Grouping: Discovering Real-Life Interaction Types from Longitudinal Bluetooth Data

Tri, Trinh Minh; Gática-Pérez, Daniel

doi:10.1109/mdm.2011.18

Cited by 13 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Vahdatpour et al [26] find recurrent patterns from multidimensional time-series given by multiple wearable sensors. In a few recent papers, we proposed several topic models for capturing group interaction patterns from Bluetooth proximity networks [10,11]. While these previous studies focus on activity discovery, this paper also considers the automatic labeling task for the discovered activities.…”

Section: Related Workmentioning

confidence: 99%

Inferring social activities with mobile sensor networks

Tri

Kalimeri

Lepri

et al. 2013

Proceedings of the 15th ACM on International Conference on Multimodal Interaction

Self Cite

View full text Add to dashboard Cite

While our daily activities usually involve interactions with others, the state-of-the-art methods on activity recognition do not exploit the relationship between social interactions and human activity. This paper addresses the problem of interpreting social activity from human-human interactions captured by mobile sensing networks. Our first goal is to discover different social activities such as chatting with friends from human-human interaction logs and then characterize them by the set of people involved, time and location of the occurring event. Our second goal is to perform automatic labeling of the discovered activities using predefined semantic labels such as coffee breaks, weekly meetings, or random discussions. Our analysis was conducted on interaction networks sensed with Bluetooth and infrared sensors by about fifty subjects who carried sociometric badges over 6 weeks. We show that the proposed system reliably recognized coffee breaks with 99% accuracy, while weekly meetings were recognized with 88% accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Inferring social activities with mobile sensor networks

Tri

Kalimeri

Lepri

et al. 2013

Proceedings of the 15th ACM on International Conference on Multimodal Interaction

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this paper, we discuss it in more details, evaluate it thoroughly, and also include additional nearby Bluetooth devices in the analysis. In an earlier work, we also proposed a model which focuses on discovering emergent group structure of proximity networks [7]. The main ideas are that dynamical networks have a limited number of emergent structures, and that each structure corresponds to a mapping from the set of people in the network to the set of latent groups, in which group members have high probability to interact with each other.…”

Section: Related Workmentioning

confidence: 99%

Human interaction discovery in smartphone proximity networks

Minh

Gática-Pérez

2011

Pers Ubiquit Comput

Self Cite

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

“…The detection of following and leadership patterns enable new analysis methods within areas such as reality mining [7], computational social science [5], emergency research and marketing research [11], and provides new primitives for pervasive computing and location-based games. Firstly, for computational social sciences and reality mining to extract patterns among moving coworkers including staff at hospitals, caretakers in large buildings and workers in warehouses.…”

Section: Introductionmentioning

confidence: 99%

“…Several works have utilized Bluetooth [1], [7], [8] for proximity detection. Eagle et al [7] proposed methods for modeling users' behavior from such data and Do et al [5] proposed methods for utilizing it for building probabilistic models of the latent group structures. Efstratiou et al [8] used Bluetooth data to detect social interactions in a group and Adams et al [1] used Bluetooth and GPS data to understand proximity and then model user behavior as rhythms of place visits and social interactions.…”

Section: Introductionmentioning

confidence: 99%

Time-lag method for detecting following and leadership behavior of pedestrians from mobile sensing data

Kjargaard

Blunck

Wüstenberg

et al. 2013

2013 IEEE International Conference on Pervasive Computing and Communications (PerCom)

View full text Add to dashboard Cite

Abstract-The vast availability of mobile phones with built-in movement and location sensors enable the collection of detailed information about human movement even indoors. As mobility is a key element of many processes and activities, an interesting class of information to extract is movement patterns that quantify how humans move, interact and group. In this paper we propose methods for detecting two common pedestrian movement patterns, namely individual following relations and group leadership. The proposed methods for identifying following patterns employ machine learning on features derived using similarity analysis on time lagged sequences of WiFi measurements containing either raw signal strength values or derived locations. To detect leadership we combine the individual following relations into directed graphs and detect leadership within groups by graph link analysis. Methods for detecting these movement patterns open up new possibilities in -amongst others -computational social science, reality mining, marketing research and location-based gaming. We provide evaluation results that show error rates down to 7%, improving over state of the art methods with up to eleven percentage points for following patterns and up to twenty percentage points for leadership patterns. Our method is, contrary to state of the art, also applicable in challenging indoor environments, e.g., multi-story buildings. This implies that even quite small samples allow us to detect information such as how events and campaigns in multistory shopping malls may trigger following in small groups, or which group members typically take the lead when triggered by e.g. commercials, or how rescue or police forces act during training exercises.

show abstract

Contextual Grouping: Discovering Real-Life Interaction Types from Longitudinal Bluetooth Data

Cited by 13 publications

References 22 publications

Inferring social activities with mobile sensor networks

Inferring social activities with mobile sensor networks

Human interaction discovery in smartphone proximity networks

Time-lag method for detecting following and leadership behavior of pedestrians from mobile sensing data

Contact Info

Product

Resources

About