ABSTRACT
The different electronic devices we use on a daily basis produce distinct electromagnetic radiation due to differences in their underlying electrical components. We present MagnifiSense, a low-power wearable system that uses three passive magneto-inductive sensors and a minimal ADC setup to identify the device a person is operating. MagnifiSense achieves this by analyzing near-field electromagnetic radiation from common components such as the motors, rectifiers, and modulators. We conducted a staged, in-the-wild evaluation where an instrumented participant used a set of devices in a variety of settings in the home such as cooking and outdoors such as commuting in a vehicle. MagnifiSense achieves a classification accuracy of 82.6% using a model-agnostic classifier and 94.0% using a model-specific classifier. In a 24-hour naturalistic deployment, MagnifiSense correctly identified 25 of the total 29 events, while achieving a low false positive rate of 0.65% during 20.5 hours of non-activity.
- Arrillaga, J. and Watson, N. R. 2003. Power System Harmonics.Google Scholar
- Bao, L. and Intille, S. 2004. Activity Recognition from User-Annotated Accleration Data. In Proc. Pervasive Computing '04. (2004), 1--17.Google ScholarCross Ref
- Breiman, L. 1999. Random Forests. Machine Learning. 45, (1999), 1--35. Google ScholarDigital Library
- Chen, K., Gupta, S., Larson, E. and Patel, S. 2015. DOSE: Detecting User-Driven Operating States of Electronic Devices from a Single Sensing PointNo Title. IEEE Conference of Pervasive Computing (2015).Google Scholar
- Fishkin, K. P., Fox, D., Kautz, H., Patterson, D., Perkowitz, M. and Philipose, M. 2003. Guide: towards understanding daily life via autoidentification and statistical analysis. Proc. of Ubihealth '03 (2003).Google Scholar
- FreeLinc FreeLinc Near-Field Magnetic Induction Technology.Google Scholar
- Gupta, S., Reynolds, M. and Patel, S. N. 2010. ElectriSense: single-point sensing using EMI for electrical event detection and classification in the home. In Proc. UbiComp '10. (2010), 139--148. Google ScholarDigital Library
- Harma, A., McKinney, M. and Skowronek, J. 2005. Automatic surveillance of the acoustic activity in our living environment. IEEE Int'l Conf on Multimedia and Expo,. (2005).Google Scholar
- Hart, G. W. 1992. Nonintrusive appliance load monitoring. Proc. of the IEEE (1992), 1870--1891.Google ScholarCross Ref
- Hemminki, S., Nurmi, P. and Tarkoma, S. 2013. Accelerometer-based transportation mode detection on smartphones. In Proc. Embedded Network Sensor Systems (2013). Google ScholarDigital Library
- Idiculla, M. K. and Nair, A. S. 2006. Spectral Study on the Voltage Waveform of Claw Pole. In Proc. 20th European Conference on Modelling and Simulation (2006).Google Scholar
- Itoh, H. 2014. Magnetic Field Sensor and Its Application to Automobiles.Google Scholar
- Kocatepe, C., Yumurtacı, R., Arıkan, O., Baysal, M., Kekezoğlu, B., Bozkurt, A. and Kumru, C. F. 2013. Harmonic Effects of Power System Loads: An Experimental Study. Power Quality Issues.Google Scholar
- Larson, E., Froehlich, J., Campbell, T., Haggerty, C., Atlas, L., Fogarty, J. and Patel, S. N. 2012. Disaggregated water sensing from a single, pressure-based sensor: An extended analysis of HydroSense using staged experiments. Pervasive and Mobile Computing. 8, (2012), 82--102. Google ScholarDigital Library
- Lenz, J. and Edelstein, S. 2006. Magnetic sensors and their applications. IEEE Sensors Journal. 6, 3 (2006), 631--649.Google ScholarCross Ref
- Logan, B., Healey, J., Philipose, M., Tapia, E. M. and Intille, S. 2007. A Long-Term Evaluation of Sensing Modalities for Activity Recognition. In Proc. UbiComp '07 (2007), 483--500. Google ScholarDigital Library
- M. J. Humphreys, C. J. Hammerton, D. Brown, R. Miller and L. Burley 1994. Power Control with Thyristors and Triacs. Power Semiconductor Semiconductors. Philips Applications. 485--551.Google Scholar
- Miettinen, M. 2014. ConXsense -- Context Profiling and Classification for Context-Aware Access Control. ASIACCS '14. (2014), 293--304. Google ScholarDigital Library
- Patel, S., Gupta, S. and Reynolds, M. 2010. The design and evaluation of an end-user-deployable, whole house, contactless power consumption sensor. In Proc. CHI '10 (2010), 2471--2480. Google ScholarDigital Library
- Poppe, R. 2010. A survey on vision-based human action recognition. Image and Vision Computing. 28, 6 (2010), 976--990. Google ScholarDigital Library
- Prandoni, P. and Vetterli, M. 2008. Signal Processing for Communications.Google Scholar
- Rowe, A., Berges, M. and Rajkumar, R. 2010. Contactless sensing of appliance state transitions through variations in electromagnetic fields. In Proc. BuildSys '10 (2010), 19--24. Google ScholarDigital Library
- Smith, B. J. R., Fishkin, K. P., Jiang, B., Mamishev, A., Philipose, M., Rea, A. D., Roy, S. and Sundararajan, K. RFID-Based Techniques for Human-Activity Detection. Communications of the ACM. 48, 9, 39--44. Google ScholarDigital Library
- Tapia, E. M., Intille, S. S. and Larson, K. 2004. Activity recognition in the home using simple and ubiquitous sensors. Springer Berlin Heidelberg.Google Scholar
- Uddin, M. 2012. MagnoTricorder: What You Need To Do Before Leaving Home. In Proc. UbiComp '12 (2012), 1096--1101. Google ScholarDigital Library
- Vaucelle, C., Ishii, H. and Paradiso, J. a. 2008. Electromagnetic Field Detector Bracelet. In Extended Abstracts UbiComp '08. (2008).Google Scholar
- Wang, E., Ipser, S., Little, P., Duncan, N. and Liu, B. 2013. Design Considerations for Leveraging Over-familiar Items for Elderly Health Monitors. In Proc. HCII '13 (2013).Google Scholar
- Zhang, M. and Sawchuk, A. 2012. A preliminary study of sensing appliance usage for human activity recognition using mobile magnetometer. Proc. of UbiComp '12 (2012), 745--748. Google ScholarDigital Library
- Zouba, N., Boulay, B., Bremond, F. and Thonnat, M. 2008. Monitoring activities of daily living (ADLs) of elderly based on 3D key human postures. In Proc. ICVW '08 (2008), 37--50. Google ScholarDigital Library
Index Terms
- MagnifiSense: inferring device interaction using wrist-worn passive magneto-inductive sensors
Recommendations
Demo of MagnifiSense: inferring device interaction using wrist-worn passive magneto-inductive sensors
UbiComp/ISWC'15 Adjunct: Adjunct Proceedings of the 2015 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2015 ACM International Symposium on Wearable ComputersThe different electronic devices we use on a daily basis produce distinct electromagnetic radiation due to the differences in their underlying electrical components. We present MagnifiSense, a low-power wearable system that uses three passive magneto-...
Latent-Dynamic Conditional Random Fields for recognizing activities in smart homes
Ambient and Smart Component Technologies for Human Centric ComputingAs the number of elderly people in our society increases, the need of assistive technologies in home becomes urgent. Existing techniques allow elderly people to be better assisted through monitoring what goes on in smart homes and inferring their ...
CapSense: Capacitor-based Activity Sensing for Kinetic Energy Harvesting Powered Wearable Devices
MobiQuitous 2017: Proceedings of the 14th EAI International Conference on Mobile and Ubiquitous Systems: Computing, Networking and ServicesWe propose a new activity sensing method, CapSense, which detects activities of daily living (ADL) by sampling the voltage of the kinetic energy harvesting (KEH) capacitor at an ultra low sampling rate. Unlike conventional sensors that generate only ...
Comments