Translation Resilient Opportunistic WiFi Sensing
read more
Citations
OPERAnet, a multimodal activity recognition dataset acquired from radio frequency and vision-based sensors
OPERAnet: A Multimodal Activity Recognition Dataset Acquired from Radio Frequency and Vision-based Sensors.
UWB and WiFi Systems as Passive Opportunistic Activity Sensing Radars
WiFi Sensing on the Edge: Signal Processing Techniques and Challenges for Real-World Systems
Commodity WiFi Sensing in Ten Years: Status, Challenges, and Opportunities
References
Tool release: gathering 802.11n traces with channel state information
Whole-home gesture recognition using wireless signals
Understanding and Modeling of WiFi Signal Based Human Activity Recognition
E-eyes: device-free location-oriented activity identification using fine-grained WiFi signatures
RT-Fall: A Real-Time and Contactless Fall Detection System with Commodity WiFi Devices
Related Papers (5)
Frequently Asked Questions (16)
Q2. What have the authors contributed in "Translation resilient opportunistic wifi sensing" ?
In this paper, the authors present a new signal processing pipelines required for effective wireless sensing.
Q3. What is the CSI for a wireless channel?
The equaliser uses the CSI to reverse the effects of the channel such as multipath propagation, attenuation, phase shift, scattering, etc., to recover the transmitted signal.
Q4. How many antennas were used to collect CSI?
The CSI was collected over 3 antennas (30 subcarriers each) on the receiver side (NUC) in the 2.4 GHz band (20 MHz bandwidth) by pinging the AP at a rate of 1 kHz.
Q5. What is the phase of the ith subcarrier?
The measured phase φ̂i of the ith subcarrier be expressed as:φ̂i = φi − 2π ki N δt+ β + Z, (8)where φ is the true phase, β is the phase offset due to CFO, δt is the timing offset between the transmitter and receiver, ki is the index of the ith subcarrier and Z is noise.
Q6. What is the CSI for a wireless system with MIMO-OFDM capability?
For a WiFi system with MIMO-OFDM capability, in each packet the CSI is obtained as a 3-dimensional (3D) matrix with nt×nr ×N complex values, where nt is the number of transmit antennas, nr is the number of receive antennas and N is the number of subcarriers.
Q7. What is the purpose of the CSI method?
PCA is used to identify the timevarying correlations between the CSI streams which are then optimally combined to extract components that represent the variation caused by human activities.
Q8. What is the CSI of a MIMO-OFDM system?
For a MIMO system, Hk has a dimension of Nr ×Nt and is represented asHk = h1,1 h1,2 · · · h1,nt h2,1 h2,2 · · · h2,nt ... ... . . . ...hnr,1 hnr,2 · · · hnr,nt , (5) where hi,j is the complex-valued channel coefficient between the jth transmit antenna and ith receive antenna.
Q9. What was the purpose of this study?
The scope of this study was to evaluate the activity recognition performance in different physical geometry as would be the case in a real-world environment.
Q10. What is the phase offset for the raw data?
In this work, the phase is calibrated as in [20] where a linear transformation is applied to the raw phase data to eliminate the phase offset.
Q11. What are the requirements of different WiFi sensing applications?
Different WiFi sensing applications have specific requirements in terms of their signal processing techniques and classification/estimation algorithms.
Q12. What is the purpose of the work?
In this work, instead of manually identifying a set of features, the authors use a 2D Convolutional Neural Network (CNN) for classification purposes.
Q13. Why is the CSI spectrogram low accuracy?
The reason for the low accuracy is because the LoS and non-LoS data from the different layouts are mixed together and these have different Doppler signatures.
Q14. How many subcarriers are used for each transmitreceive antenna?
Recall that the Intel 5300 Linux CSI tool extracts the CSI measurements from 30 out of 56 subcarriers for each transmitreceive antenna pair.
Q15. What is the frequency domain input-output relation in a MIMO-OFDM?
Assuming a narrowband flatfading channel, the frequency domain input-output relation in a MIMO-OFDM system with N subcarriers can be represented asyk =
Q16. What is the moving variance of a CSI stream?
For a CSI stream consisting of M packets, the moving variance is defined asCSImv = M∑m=1[ 1L− 1 L∑ l=1 |CSIl∈L − µ2|] , (9)µ = 1L L∑ l=1 CSIl,where µ and l denote the mean and packet number in the sliding window of length L, respectively, and m is the current sample position in the CSI stream.