We Can Hear You with Wi-Fi!

By Guan-Ru Wang, Yongpan Zou, Zimu Zhou, Kaishun Wu, Lionel Ming-shuan Ni. IEEE Transactions on Mobile Computing, 2014

501 citations recorded by the source corpus.

Subfields: Electrical and Electronic Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/d3b990e17a6f5a3c792e29b2191dbf98cbdb56ed

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

1. Gang Zhou
2. Wen Wang
3. Alex X. Liu
4. Yongsen Ma
5. Shuangquan Wang
6. Zachary Kabelac
7. Fadel M. Adib
8. Dina Katabi

In Signal Processing

1. Gang Zhou
2. Jun Liu
3. Zhenjiang Li
4. Mo Li
5. Qiuhong Ke
6. Bin Guo
7. Fadel M. Adib
8. Dina Katabi

Citations in the corpus

• Deep Learning for Sensor-based Human Activity Recognition (2020, background): “In addition to coarse activities like walking and jogging, CSI can also be used to recognize small movements like lip movements [152], keystrokes [5], and heartbeats [156].”
• Gait recognition using wifi signals (2016, background): “With the success of WiFi industry, commercially available WiFi devices can not only achieve high speed and low cost, but can also measure small changes in WiFi signals and thus sense the changes in their surrounding environments caused by moving objects such as humans [30, 31].”
• Device-Free Human Activity Recognition Using Commercial WiFi Devices (2017, background): “It is shown that CSI is also able to detect and recognize small movements such as lip movements [26], keystrokes [7], and heartbeats [36].”
• Keystroke Recognition Using WiFi Signals (2015, methodology): “Some recent work, namely WiHear, uses CSI values to extract the micro-movements of mouth to recognize 9 syllables in the spoken words [10].”
• Multi-Person Localization via RF Body Reflections (2015, background): “0 is also related to non-localization systems that employ RF reflections off the human body [4, 20, 33, 35].”
• Understanding and Modeling of WiFi Signal Based Human Activity Recognition (2015, background): “However, due to the high energy and high bandwidth of impulse noises in CSI, the pass band for the low-pass filters usually need to be less than one-twentieth of the sampling rate so that the energy of residual noise in the pass band becomes negligible compared to the signal energy [26].”
• Towards Environment Independent Device Free Human Activity Recognition (2018, methodology): “11n CSI Tool [16], recently a lot of research work have been conducted to utilize CSI for the task of human activity recognition [3, 8, 14, 38, 47, 48, 50, 52, 55] or gesture recognition [17, 24, 37, 42, 45, 46, 59].”
• Precise Power Delay Profiling with Commodity Wi-Fi (2015, methodology): “Instead, the relative change of the power level of each NLoS path indicates the multipath channel dynamics, which has been used for activity or gesture recognitions [24, 33, 35].”
• Human Action Recognition From Various Data Modalities: A Review (2020, background): “The work of [342] used specialized directional antennas to obtains CSI variations caused by lip movements.”
• WiFi Sensing with Channel State Information (2019, background): “WiHear [90] NR: Butterworth BPF; ST: IFFT, DWT M: PDP, Multi-Path Reflection; L: DTW, Pattern Matching Speaking Recognition Accuracy: 91%/74% (1 person/3 persons, <6 words)”