ABSTRACT
Back-of-device (BoD) interaction using current smartphone sensors (e.g. accelerometer, microphone, or gyroscope) has recently emerged as a promising novel input modality. Researchers have used a different number of features derived from these commodity sensors, however it is unclear what sensors and which features would allow for practical use, since not all sensor measurements have an equal value for detecting BoD interactions reliably and efficiently. In this paper, we primarily focus on constructing and selecting a subset of features that is a good predictor of BoD tap-based input while ensuring low energy consumption. As a result, we build several classifiers for a variety of use cases (e.g. single or double taps with the dominant or non-dominant hand). We show that a subset of just 5 features provides high discrimination power and results in high recognition accuracy. We also make our software publicly available, so that others can build upon our work.
Supplemental Material
- Baudisch, P., and Chu, G. Back-of-device interaction allows creating very small touch devices. In Proc. CHI (2009). Google ScholarDigital Library
- Corsten, C., Cherek, C., Karrer, T., and Borchers, J. HaptiCase: Back-of-device tactile landmarks for eyes-free absolute indirect touch. In Proc. CHI (2015). Google ScholarDigital Library
- De Luca, A., von Zezschwitz, E., Nguyen, N. D. H., Maurer, M.-E., Rubegni, E., Scipioni, M. P., and Langheinrich, M. Back-of-device authentication on smartphones. In Proc. CHI (2013). Google ScholarDigital Library
- Gignac, G. E., and Vernon, P. A. Reaction time and the dominant and non-dominant hands: An extension of Hick's law. Personality and Individual Differences 36, 3 (2004).Google ScholarCross Ref
- Guyon, I., and Elisseeff, A. An introduction to variable and feature selection. J. Mach. Learn. Res. 3 (2003). Google ScholarDigital Library
- Hassan, N., Rahman, M., Irani, P., and Graham, P. Chucking: A one-handed document sharing technique. In Proc. INTERACT, vol. 5727 of LNCS. 2009. Google ScholarDigital Library
- Hastie, T., Tibshirani, R., and Friedman, J. The Elements of Statistical Learning, 2nd ed. Springer-Verlag, 2009.Google Scholar
- Heo, S., and Lee, G. ForceTap: extending the input vocabulary of mobile touch screens by adding tap gestures. In Proc. MobileHCI (2011). Google ScholarDigital Library
- Hinckley, K., and Song, H. Sensor synesthesia: touch in motion, and motion in touch. In Proc. CHI (2011). Google ScholarDigital Library
- Hirotaka, N. Reassessing current cell phone designs: using thumb input effectively. In Proc. CHI EA (2003). Google ScholarDigital Library
- Holman, D., Hollatz, A., Banerjee, A., and Vertegaal, R. Unifone: Designing for auxiliary finger input in one-handed mobile interactions. In Proc. TEI (2013). Google ScholarDigital Library
- Hudson, S. E., Harrison, C., Harrison, B. L., and LaMarca, A. Whack gestures: inexact and inattentive interaction with mobile devices. In Proc. TEI (2010). Google ScholarDigital Library
- Leiva, L. A., and Catalá, A. BoD Taps: An improved back-of-device authentication technique on smartphones. In Proc. MobileHCI (2014). Google ScholarDigital Library
- Lopes, P., Jota, R., and Jorge, J. A. Augmenting touch interaction through acoustic sensing. In Proc. ITS (2011). Google ScholarDigital Library
- Mohd Noor, M. F. Exploring back-of-device interaction. In Adj. Proc. UIST (2013). Google ScholarDigital Library
- Oakley, I., and Park, J. A motion-based marking menu system. In Proc. CHI EA (2007). Google ScholarDigital Library
- Proakis, J. G., and Manolakis, D. K. Digital Signal Processing, 4th ed. Prentice Hall, 2006. Google ScholarDigital Library
- Robinson, S., Rajput, N., Jones, M., Jain, A., Sahay, S., and Nanavati, A. TapBack: Towards richer mobile interfaces in impoverished contexts. In Proc. CHI (2011). Google ScholarDigital Library
- Roudaut, A., Baglioni, M., and Lecolinet, E. Timetilt: using sensor-based gestures to travel through multiple applications on a mobile device. In Proc. INTERACT, vol. 5726 of LNCS. 2009. Google ScholarDigital Library
- Saeedi, R., Schimert, B., and Ghasemzadeh, H. Cost-sensitive feature selection for on-body sensor localization. In Adj. Proc. UbiComp (2014). Google ScholarDigital Library
- Seipp, K., and Devlin, K. BackPat: One-handed off-screen patting gestures. In Proc. MobileHCI (2014). Google ScholarDigital Library
- Serrano, M., Lecolinet, E., and Guiard, Y. Bezel-Tap gestures: Quick activation of commands from sleep mode on tablets. In Proc. CHI (2013). Google ScholarDigital Library
- Siegel, S., and Castellan, N. J. Nonparametric Statistics for the Behavioural Sciences, 2nd ed. McGraw-Hill, 1988.Google Scholar
- Zhang, C., Guo, A., Zhang, D., Southern, C., Arriaga, R., and Abowd, G. BeyondTouch: Extending the input language with built-in sensors on commodity smartphones. In Proc. IUI (2015). Google ScholarDigital Library
- Zhang, C., Parnami, A., Southern, C., Thomaz, E., Reyes, G., Arriaga, R., and Abowd, G. D. BackTap: Robust four-point tapping on the back of an off-the-shelf smartphone. In Adj. Proc. UIST (2013). Google ScholarDigital Library
- Zhang, L., Tiwana, B., Qian, Z., Wang, Z., Dick, R. P., Mao, Z. M., and Yang, L. Accurate online power estimation and automatic battery behavior based power model generation for smartphones. In Proc. CODES+ISSS (2010). Google ScholarDigital Library
Index Terms
- Less Is More: Efficient Back-of-Device Tap Input Detection Using Built-in Smartphone Sensors
Recommendations
βTap: back-of-device tap input with built-in sensors
MobileHCI '17: Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and ServicesWe present βTap, a Back-of-device (BoD) tap detection software for mobile devices that uses commodity sensors, without the need to instrument the device. Although just basic interactions are supported (namely, single and double taps), βTap is highly ...
Sensor synaesthesia: touch in motion, and motion in touch
CHI '11: Proceedings of the SIGCHI Conference on Human Factors in Computing SystemsWe explore techniques for hand-held devices that leverage the multimodal combination of touch and motion. Hybrid touch + motion gestures exhibit interaction properties that combine the strengths of multi-touch with those of motion-sensing. This affords ...
An energy efficient Genetic Algorithm based approach for sensor-to-sink binding in multi-sink wireless sensor networks
Wireless sensor networks (WSNs) are ad-hoc networks in which sensors, that are designed to relay data back to sink nodes and/or Base Stations, are deployed in an area and may be configured in real time. Sensors, however, have limited energy supplies and ...
Comments