We introduce BeaMsteerX (BMX), a novel mmWave hand hygiene gesture recognition technique that improves accuracy in longer ranges (1.5m). BMX steers a mmWave beam towards multiple directions around the subject, generating multiple views of the gesture that are then intelligently combined using deep learning to enhance gesture classification. We evaluated BMX using off-the-shelf mmWave radars and collected a total of 7,200 hand hygiene gesture data from 10 subjects performing a 6-step hand-rubbing procedure, as recommended by the World Health Organization, using sanitizer, at 1.5m---over 5 times longer than in prior works. BMX outperforms state-of-the-art approaches by 31--43% and achieves 91% accuracy at boresight by combining only two beams, demonstrating superior gesture classification in low SNR scenarios. BMX maintained its effectiveness even when the subject was positioned 30° away from the boresight, exhibiting a modest 5% drop in accuracy.

Recent research has demonstrated the huge potential of WiFi for contactless sensing of human activities. Unfortunately, such sensing is highly sensitive to the relative orientation between the user and the WiFi receivers. To overcome this problem, existing solutions deploy multiple WiFi receivers at precise positions to capture orientation-independent view of the human activity. Orientation-independent single-receiver WiFi sensing is still considered an open problem. In this article, we propose a deep neural network architecture that uses radar data during training to learn high-precision Doppler features of human activities from the noisy channel states observed by a single WiFi receiver. Once trained with radars, the network can be used to detect human activities at any arbitrary orientations based only on WiFi signals. Using extensive experiments with millimeter-wave radars, we demonstrate that the proposed approach, called WiFi2Radar in this article, significantly outperforms state-of-the-art for detecting human activities in untrained orientations using only a single WiFi receiver. Our results show that WiFi2Radar can detect orientation-independent human activities with up to 91% accuracy, which outperforms the state of the art by 19%.

Wireless Sensing has been a topic in contemporary research for years and popularity is still intact as its ubiquitous and non-invasive nature. Human activity recognition using wireless sensing is leveraged by the deep learning advancements. However, maintaining the robustness of the sensing model in sensitive wireless environments is a non-trivial task to achieve. We propose a deep learning based signal translation framework for multiple variations observed in sensing environments such as transceiver variance and configuration of the user who performing the activities. Our approach has two major pipelines, translation pipeline which translates from novel configuration to a reference configuration and an inference pipeline which classifies the activities performed by the user. We further expect to extend this model to more complex multi user interacting sensing environments and to In-Situ setups.

Sensitivity of WiFi channel measurements to the transceiver placement is a major limitation for on-demand deployment of device-free WiFi sensing in environments where the transmitting/receiving devices may move. Using publicly available datasets, we show that even slight deviations of transmitter/receiver placements from the reference values can degrade device-free gesture recognition accuracy significantly. We design a convolutional autoencoder to translate WiFi spectrograms from arbitrary receiver placements to a reference placement configuration in a given area of interest with minimal human effort. Our experiments with the public datasets reveal that the proposed autoencoder can successfully reduce WiFi measurement variability caused by transmitter/receiver movement, which ultimately increases gesture recognition accuracy by up to 58%.