IEEE Consumer Electronics Magazine - March 2018 - 82

values for the clap and vertical-hand gestures are approximately 0.85 and 0.8, respectively. The gesture of moving
the hand toward the receiver has the lowest sensitivity, specificity, and efficiency values, which were approximately 0.74.
In summary, the sensitivity, specificity, and efficiency values of the recognition of all four hand gestures in our application are above 0.7.

THE RSSI AND OTHER MEASUREMENTS
FROM WI-FI TECHNOLOGY
Using a Wi-Fi RSSI to recognize hand gestures has the
advantage of low cost, as it does not require additional dedicated hardware. Also, RSSI signals can overcome obstacles and are robust to sound noise when compared to
camera and sound sensors. Additionally, as Wi-Fi is everywhere, it facilitates the wide deployment of Wi-Fi-RSSIbased applications. However, an RSSI is not suitable for
recognizing the precise movement of hand gestures or
object movements.
Besides an RSSI, CSI, and angle-of-arrival (AoA) information from Wi-Fi technology can also be used to detect
hand gestures. CSI recognition can achieve higher accuracy
and is more robust to environmental changes. However, it is
not easy to extract, as it requires the modification of the wireless module of the mobile device or the use specific hardware. It also requires a more complex algorithm to process.
Alternatively, AoA can be used to recognize the direction of a
hand movement and achieve higher accuracy. However, it
requires users to hold a wireless transmitter or use a specific
wearable device, and it is not able to detect motion when the
transmitter or receiver is mobile.

CONCLUSION
In this article, the changes of Wi-Fi-RSSI values for different
hand gestures have been evaluated. For the evaluation of the
hand gestures, the average, maximum, and minimum Wi-FiRSSI values of no gesture and a stop gesture were clearly different from those of other gestures. Moving a hand toward and
away from the receiver showed a pattern of frequently changing
RSSI values at the end of the graph. A clap displayed a strong
up-and-down wave between the maximum and minimum values. The "come here" motion showed a clear peak and trough at
the minimum value.
As a result, the hand-toward, hand-away, clap, and comehere gestures can be identified and used in application
designs. We used three hand gestures to design and implement
an application with an interactive interface. A clap gesture
can trigger the launch of a video player and start the playback.
The gesture of placing a hand in front of the receiver can
pause the playback, and the gesture of moving a hand toward
the receiver can close the video player. This application demonstrates that an RSSI can be used to recognize different hand
gestures, and they can be utilized in the design of various
kinds of interactive applications.

82 IEEE Consumer Electronics Magazine

MARCH 2018

ABOUT THE AUTHORS
Ricky Lap-Hou Lao (laphou@gmail.com) earned his B.S.
degree in computer engineering from the Open University of
Hong Kong. He is currently pursuing a master's degree in
information technology at the Polytechnic University of
Hong Kong.
Angus Kin-Yeung Wong (akywong@ouhk.edu.hk) earned
his B.Sc. and Ph.D. degrees in information technology from
the City University of Hong Kong. He is currently an associate professor in the School of Science and Technology and
head of the Centre of Research for Advanced Network Technology in the Open University of Hong Kong. His research
interests include Internet systems, network infrastructure
security, and social network analysis.

REFERENCES
[1] M. Haghighi and C. J. Musselle, "Dynamic collaborative change
point detection in wireless sensor networks," in Proc. Int. Conf. CyberEnabled Distributed Computing and Knowledge Discovery, Oct. 201, pp.
332-339.
[2] Q. Chen, B. Tan, K. Woodbridge, and K. Chetty, "Indoor target tracking using high doppler resolution passive Wi-Fi radar," in Proc. IEEE Int.
Conf. Acoustics, Speech, and Signal Processing (ICASSP), Apr. 2015,
pp. 5565-5569.
[3] S. Sigg, U. Blanke, and G. Troster, "The telepathic phone: Frictionless activity recognition from WiFi-RSSI," in Proc. IEEE Int. Conf. Pervasive Computing and Communications (PerCom), Mar. 2014, pp.
148-155.
[4] I. Kononenko and I. Bratko, Information-Based Evaluation Criterion
for Classifier's Performance. Norwell, MA: Kluwer, Jan. 1991.
[5] D. McCormick. (2015, Aug. 10). See through walls by the glow of
your Wi-Fi. IEEE Spectrum. [Online]. Available: https://spectrum.ieee
.org/tech-talk/at-work/test-and-measurement/see-through-walls-by-theglow-of-your-wifi
[6] F. Adib, Z. Kabelac, D. Katabi, and R. C. Miller, "3D Tracking
via body radio reflections," in Proc. USENIX Symp. Networked
Systems Design and Implementation, Seattle, WA, Apr. 2014, pp.
1-13.
[7] I. Bisio, F. Lavagetto, M. Marchese, and A. Sciarrone, "Energy efficient WiFi-based fingerprinting for indoor positioning with smartphones," in Proc. IEEE Global Communications Conf. (GLOBECOM),
Dec. 2013, pp. 4639-4643.
[8] M. A. A. Al-qaness and F. Li. (2016, June 14). WiGeR: WiFi-based
gesture recognition system. Int. J. Geo-Information. [Online]. 5(6).
Available: http://www.mdpi.com/2220-9964/5/6/92
[9] L. Sun, H. S. Sen, D. Koutsonikolas, and K.-H. Han, "Widraw:
Enabling hands-free drawing in the air on commodity WiFi devices," in
Proc. ACM 21st Annu. Int. Conf. Mobile Computing and Networking,
2015, pp. 1-13.
[10] H. Abdelnasser, Y. Moustafa, and K. A. Harras, "Wigest: A ubiquitous WiFi-based gesture recognition system," in Proc. IEEE Conf. Computer Communications (INFOCOM), 2015, pp. 1-9.
[11] K. Ali, A. Liu, W. Wang, and M. Shahzad, "Recognizing keystrokes using WiFi devices," IEEE J. Sel. Areas Comm., pp. 1175-
1190, 2017.
[12] Z. Liang, X. Xu, and C. Qing, "Natural interaction in freehand
pointing: Designing the mapping of interaction space," IEEE Consum. Electron. Mag., vol. 6, no. 2, pp. 89-93, 2017.
[13] IEEE. (2017). IEEE 802.11 working group project timeline.
[Online]. Available: http://grouper.ieee.org/groups/802/11/
Reports/802.11_Timelines.htm

https://www.spectrum.ieee.org/tech-talk/at-work/test-and-measurement/see-through-walls-by-the-glow-of-your-wifi https://www.spectrum.ieee.org/tech-talk/at-work/test-and-measurement/see-through-walls-by-the-glow-of-your-wifi https://www.spectrum.ieee.org/tech-talk/at-work/test-and-measurement/see-through-walls-by-the-glow-of-your-wifi http://www.mdpi.com/2220-9964/5/6/92 http://grouper.ieee.org/groups/802/11/Reports/802.11_Timelines.htm http://grouper.ieee.org/groups/802/11/Reports/802.11_Timelines.htm

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - March 2018