Detecting Social Interactions in Indoor Environments with the Red-HuP Algorithm

Detecting social interactions among people represents a challenging task. In this study we evaluate the performance of the ReD-HuP algorithm. We study a real-world and useful experimental dataset and we provide a comparison with some classification methods. Interactions are inferred from co-location of people by exploiting Bluetooth Low Energy (BLE) beacons. Our analysis investigates how the different transmission powers affect the overall performance, we also analyze the results by varying the width of the time window used to analyze BLE beacons. Results obtained with the ReD-HuP algorithm have been compared against two well known and wide adopted machine learning classification methods.

[1]  Sune Lehmann,et al.  The Strength of Friendship Ties in Proximity Sensor Data , 2014, PloS one.

[2]  Paolo Barsocchi,et al.  Wi-Fi probes as digital crumbs for crowd localisation , 2016, 2016 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[3]  Ciro Cattuto,et al.  Dynamics of Person-to-Person Interactions from Distributed RFID Sensor Networks , 2010, PloS one.

[4]  Stefano Chessa,et al.  Remote Detection of Indoor Human Proximity using Bluetooth Low Energy Beacons , 2019, 2019 15th International Conference on Intelligent Environments (IE).

[5]  Mark S. Granovetter.  T H E S T R E N G T H O F WEAK TIES: A NETWORK THEORY REVISITED , 1983 .

[6]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[7]  Alain Barrat,et al.  Can co-location be used as a proxy for face-to-face contacts? , 2017, EPJ Data Science.

[8]  Kaitlin Kirasich,et al.  Random Forest vs Logistic Regression: Binary Classification for Heterogeneous Datasets , 2018 .

[9]  Stefano Chessa,et al.  Indoor Bluetooth Low Energy Dataset for Localization, Tracking, Occupancy, and Social Interaction , 2018, Sensors.

[10]  Aaron Striegel,et al.  Predicting Friendship Pairs from BLE Beacons Using Dining Hall Visits , 2019, 2019 28th International Conference on Computer Communication and Networks (ICCCN).

[11]  Paolo Barsocchi,et al.  Occupancy detection by multi-power bluetooth low energy beaconing , 2017, 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[12]  Piotr Sapiezynski,et al.  Measuring Large-Scale Social Networks with High Resolution , 2014, PloS one.

[13]  J. Friedman.  Special Invited Paper-Additive logistic regression: A statistical view of boosting , 2000 .

[14]  Michele Girolami,et al.  Detecting Social Interactions through Commercial Mobile Devices , 2018, 2018 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops).

[15]  Alex Pentland,et al.  Sensing and modeling human networks using the sociometer , 2003, Seventh IEEE International Symposium on Wearable Computers, 2003. Proceedings..

[16]  Alain Barrat,et al.  Contact Patterns among High School Students , 2014, PloS one.

[17]  Aaron Striegel,et al.  Face-to-Face Proximity EstimationUsing Bluetooth On Smartphones , 2014, IEEE Transactions on Mobile Computing.

[18]  E. Hall,et al.  The Hidden Dimension , 1970 .

[19]  Cecilia Mascolo,et al.  A Study of Bluetooth Low Energy performance for human proximity detection in the workplace , 2017, 2017 IEEE International Conference on Pervasive Computing and Communications (PerCom).