Human activity recognition (HAR) plays a critical role in a wide range of real-world applications, and it is traditionally achieved via wearable sensing. Recently, to avoid the burden and discomfort caused by wearable devices, device-free approaches exploiting radio-frequency (RF) signals arise as a promising alternative for HAR. Most of the latest device-free approaches require training a large deep neural network model in either time or frequency domain, entailing extensive storage to contain the model and intensive computations to infer human activities. Consequently, even with some major advances on device-free HAR, current device-free approaches are still far from practical in real-world scenarios where the computation and storage resources possessed by, for example, edge devices, are limited. To overcome these weaknesses, we introduce HAR-SAnet which is a novel RF-based HAR framework. It adopts an original signal adapted convolutional neural network architecture: instead of feeding the handcraft features of RF signals into a classifier, HAR-SAnet fuses them adaptively from both time and frequency domains to design an end-to-end neural network model. We apply point-wise grouped convolution and depth-wise separable convolutions to confine the model scale and to speed up the inference execution time. The experiment results show that the recognition accuracy of HAR-SAnet substantially outperforms the state-of-the-art algorithms and systems.

Object detection with on-board sensors (e.g., lidar, radar, and camera) is crucial to autonomous driving (AD), and these sensors complement each other in modalities. While crowdsensing may potentially exploit these sensors (of huge quantity) to derive more comprehensive knowledge, federated learning (FL) appears to be the necessary tool to reach this potential: it enables autonomous vehicles (AVs) to train machine learning models without explicitly sharing raw sensory data. However, the multimodal sensors introduce various data heterogeneity across distributed AVs (e.g., label quantity skews and varied modalities), posing critical challenges to effective FL. To this end, we present AutoFed as a heterogeneity-aware FL framework to fully exploit multimodal sensory data on AVs and thus enable robust AD. Specifically, we first propose a novel model leveraging pseudo labeling to avoid mistakenly treating unlabeled objects as the background. We also propose an autoencoder-based data imputation method to fill missing data modality (of certain AVs) with the available ones. To further reconcile the heterogeneity, we finally present a client selection mechanism based on client model similarities to improve training stability and convergence rate. Our experiments confirm that AutoFed substantially improves over status quo in both precision and recall, while demonstrating strong robustness to adverse weather.

Having been studied for more than a decade, Wi-Fi human sensing still faces a major challenge in the presence of multiple persons, simply because the limited bandwidth of Wi-Fi fails to provide a suficient range resolution to physically separate multiple subjects. Existing solutions mostly avoid this challenge by switching to radars with GHz bandwidth, at the cost of cumbersome deployments. Therefore, could Wi-Fi human sensing handle multiple subjects remains an open question. This paper presents MUSE-Fi, the first Wi-Fi multi-person sensing system with physical separability. The principle behind MUSE-Fi is that, given a Wi-Fi device (e.g., smartphone) very close to a subject, the near-field channel variation caused by the subject significantly overwhelms variations caused by other distant subjects. Consequently, focusing on the channel state information (CSI) carried by the trafic in and out of this device naturally allows for physically separating multiple subjects. Based on this principle, we propose three sensing strategies for MUSE-Fi: i) uplink CSI, ii) downlink CSI, and iii) downlink beamforming feedback, where we specifically tackle signal recovery from sparse (per-user) trafic under realistic multi-user communication scenarios. Our extensive evaluations clearly demonstrate that MUSE-Fi is able to successfully handle multi-person sensing with respect to three typical applications: respiration monitoring, gesture detection, and activity recognition.

Contact-free vital-signs monitoring enabled by radio frequency (RF) sensing is gaining increasing attention, thanks to its non-intrusiveness, noise-resistance, and low cost. Whereas most of these systems only perform respiration monitoring or retrieve heart rate, few can recover fine-grained heartbeat waveform. The major reason is that, though both respiration and heartbeat cause detectable micro-motions on human bodies, the former is so strong that it overwhelms the latter. In this paper, we aim to answer the question in the paper title, by demystifying how heartbeat waveform can be extracted from RF-sensing signal. Applying several mainstream methods to recover heartbeat waveform from raw RF signal, our results reveal that these methods may not achieve what they have claimed, mainly because they assume linear signal mixing whereas the composition between respiration and heartbeat can be highly nonlinear. To overcome the difficulty of decomposing nonlinear signal mixing, we leverage the power of a novel deep generative model termed variational encoder-decoder (VED). Exploiting the universal approximation ability of deep neural networks and the generative potential of variational inference, VED demonstrates a promising capability in recovering fine-grained heartbeat waveform from RF-sensing signal; this is firmly validated by our experiments with 12 subjects and 48-hour data.

In recent years, radio frequency (RF) sensing has gained increasing popularity due to its pervasiveness, low cost, non-intrusiveness, and privacy preservation. However, realizing the promises of RF sensing is highly nontrivial, given typical challenges such as multipath and interference. One potential solution leverages deep learning to build direct mappings from the RF domain to target domains, hence avoiding complex RF physical modeling. While earlier solutions exploit only simple feature extraction and classification modules, an emerging trend adds functional layers on top of elementary modules for more powerful generalizability and flexible applicability. To better understand this potential, this article takes a layered approach to summarize RF sensing enabled by deep learning. Essentially, we present a four-layer framework: physical, backbone, generalization, and application. While this layered framework provides readers a systematic methodology for designing deep interpreted RF sensing, it also facilitates making improvement proposals and hints at future research opportunities.

The contact-free sensing nature of Wi-Fi has been leveraged to achieve privacy breaches, yet existing attacks relying on Wi-Fi CSI (channel state information) demand hacking Wi-Fi hardware to obtain desired CSIs. Since such hacking has proven prohibitively hard due to compact hardware, its feasibility in keeping up with fast-developing Wi-Fi technology becomes very questionable. To this end, we propose WiKI-Eve to eavesdrop keystrokes on smartphones without the need for hacking. WiKI-Eve exploits a new feature, BFI (beamforming feedback information), offered by latest Wi-Fi hardware: since BFI is transmitted from a smartphone to an AP in clear-text, it can be overheard (hence eavesdropped) by any other Wi-Fi devices switching to monitor mode. As existing keystroke inference methods offer very limited generalizability, WiKI-Eve further innovates in an adversarial learning scheme to enable its inference generalizable towards unseen scenarios. We implement WiKI-Eve and conduct extensive evaluation on it; the results demonstrate that WiKI-Eve achieves 88.9% inference accuracy for individual keystrokes and up to 65.8% top-10 accuracy for stealing passwords of mobile applications (e.g., WeChat).