TouchSpeaker, a Multi-sensor Context-Aware Application for Mobile Devices: from Application to Implementation
- 56 Downloads
Tapping with your finger on any place on your mobile device is a promising candidate for enhanced interaction between users and their mobile device. So far the touchscreen and the accelerometer are commonly used to infer finger tap events. However, the touchscreen consumes a significant amount of power and is not always accessible (i.e., when the device is used as a running assistant). The accelerometer can be power efficient but can’t differentiate well between a variety of contexts and positions. To address these limitations, we present TouchSpeaker, a novel technique for finger tap detection on mobile devices using the built-in speakers as primary sensors. We show that a combination of the speakers with other built-in sensors can distinguish between 9 different tap events with an accuracy of 98.3%, outperforming the state of the art. In addition, a robust version is implemented resulting in a false positive rate below 1%. For power constrained devices, we propose a configuration consisting of only the speakers and the accelerometer, achieving an accuracy of 95.2%.
KeywordsMobile interaction Finger tap detection Speaker as microphone Feature extraction Classification methods
- 1.Beysens, J., Chiumento, A., Pollin, S., & Li, M. (2016). Touchspeaker, a multi-sensor context-aware application for mobile devices. In 2016 IEEE international workshop on signal processing systems (SiPS) (pp. 23–26).Google Scholar
- 2.Daniel, P. KnockOn app brings double-tap to lock to most Androids and wake to ones with OLED displays. http://www.phonearena.com/news/KnockOn-app-brings-double-tap-to-lock-to-most-Androids.-and-wake-to-ones-with-OLED-displays_id75033.
- 3.Harrison, C., Schwarz, J., & Hudson, S.E. (2011). TapSense: enhancing finger interaction on touch surfaces. In Proceedings of the 24th annual ACM symposium on User interface software and technology - UIST ’11 (pp. 627–636). https://doi.org/10.1145/2047196.2047279.
- 4.HTC Canada: HTC One (M7) Specs and Reviews. http://www.htc.com/ca/smartphones/htc-one-m7/.
- 5.Lu, H., & Li, Y. (2015). Gesture on: enabling always-on touch gestures for fast mobile access from the device standby mode. In Proceedings of the 33rd annual ACM conference on human factors in computing systems - CHI ’15 (Vol. 1, pp. 3355–3364). https://doi.org/10.1145/2702123.2702610.
- 6.MathWorks Benelux: MATLAB Profile execution time for functions. http://nl.mathworks.com/help/matlab/ref/profile.html.
- 7.McGrath, W., & Li, Y. (2014). Detecting tapping motion on the side of mobile devices by probabilistically combining hand postures. In Proceedings of the 27th annual ACM symposium on User interface software and technology - UIST ’14 (pp. 215–219). https://doi.org/10.1145/2642918.2647363.
- 8.NDT Resource center: Attenuation of Sound Waves. https://www.nde-ed.org/EducationResources/CommunityCollege/Ultrasonics/Physics/attenuation.htm.
- 10.The Engineering Toolbox: Speed of Sound in some common Solids. http://www.engineeringtoolbox.com/sound-speed-solids-d_713.html.
- 11.University of Waikato: Weka 3 - Data Mining with Open Source Machine Learning Software in Java. http://www.cs.waikato.ac.nz/ml/weka/.
- 12.Yacoub, M., & Yang, G.Z. (2007). Body Sensor Networks. Berlin: Springer Science & Business Media.Google Scholar
- 13.Zhang, C., Guo, A., Zhang, D., Southern, C., Arriaga, R., & Abowd, G. (2015). BeyondTouch: extending the input language with built-in sensors on commodity smartphones. In Proceedings of the 20th international conference on intelligent user interfaces - IUI ’15 (pp. 67–77). https://doi.org/10.1145/2678025.2701374.