Currently, a major issue of WiFi-based sensing technologies is how to adapt to changes in the surrounding environment. The extreme sensitivity ofChannel State Information(CSI) makes many WiFi sensing arts frustrated when applied to the complex and unknown real world. To solve this problem, in this paper, we proposefreeEnvdesigned to automatically identify the micro-environmental changes (even tiny movements of the laptop) using WiFi devices, which can coexist with other WiFi sensing tasks with zero effort. To achieve automatic identification of micro-environmental changes, we quantify micro-environmental changes based on the physical propagation laws of WiFi signals and the main factors that affect CSI measurements. Then, we design a micro-environmental changes identification method, which determines whether the environment has changed by calculating theEarth Mover's Distance(EMD) of theProbability Density Function(PDF) of continuous CSI, without requiring training data. To remove the influence of dynamic human behaviors, we design a human dynamic detection scheme, which is achieved by obtaining the average inter-cluster distance of performingGaussian Mixture Model(GMM) clustering on CSI. We evaluatefreeEnvin real-world scenarios with six different hardware, four different scenarios, and twenty-four ways of micro-environmental changes. The results show that our method is robust to different devices and scenarios, and can achieve the average precision of 96.1% and 93.2% for micro-environmental changes identification and human dynamic behavior detection. By testing on a case study of threshold-based human presence detection,freeEnvcan effectively improve the detection performance.

Exercise speed is a crucial indicator in bodyweight exercise assessment, directly reflecting muscular strength, energy expenditure, and exercise power. Benefiting from ubiquitous infrastructure and non-intrusive properties, WiFi-based sensing has emerged as a promising technique for motion speed estimation. However, existing WiFi sensing systems are significantly influenced by user diversity, positional variations, and orientation changes, which limit their applicability in real-world scenarios. In this work, we propose a learning-based framework, named SpeedFi , to estimate exercise speed from WiFi Channel State Information (CSI). An encoder-decoder network is designed to infer body speed, while temporal–frequency constraints are introduced to model consistent speed dynamics. To enhance user generalization, a domain adversarial strategy is adopted to extract user-invariant features. Moreover, two orthogonal WiFi links are deployed to capture complementary spatial perspectives, and an attention-based fusion module is employed for effective feature integration. A physics-inspired simulation model is further developed to synthesize CSI frequency variations, guiding the design of a diversified data collection strategy covering multiple positions, orientations, and environmental configurations. We conduct extensive experiments involving 10 participants performing 3 types of bodyweight exercises across 5 distinct environments. In controlled settings, SpeedFi achieves an average speed estimation error of 0.113 m/s for peak speeds around 1 m/s. Real-time analysis indicates that the system runs at over 40 FPS on a mid-range GPU, supporting its potential for real-time deployment. Additional tests under multi-person scenarios, complex multipath conditions, and varying WiFi link configurations are conducted to assess the system’s operational boundaries and robustness, validating its applicability across diverse settings.

Human presence detection is crucial in various scenarios, from law enforcement surveillance to smart health-care systems. Traditional methods like cameras and acoustic signals face challenges such as privacy concerns, the need for line of sight (LoS), and susceptibility to environmental noise. This paper proposes MULiving, a real-time RFID-based system designed to monitor the survival status of multiple users simultaneously. Unlike previous RFID-based solutions, MULiving addresses two key challenges: achieving real-time detection and accurately identifying stationary users. By leveraging a signal threshold-based approach that adapts automatically to non-living states, MULiving can distinguish between living and non-living users, even during periods of minimal movement(e.g., sleep). Extensive experiments using Commercial off-the-shelf (COTS) RFID devices demonstrate that MULiving is not only highly accurate but also robust across different users, RFID tags, and behaviors. The results confirm MULiving as a promising solution for real-time multi-user survival monitoring, with significant potential for practical deployment in real-world applications.

Currently, a major challenge in WiFi-based respiration monitoring systems is overcoming issues such as hardware noise interference and sensitivity to the user's location and orientation. To address these challenges, we propose LOAR-Fi, a novel, low-cost, non-contact respiration monitoring system based on the commercial WiFi chip ESP32. LOAR-Fi utilizes a flexible, scalable one-transmitter, multiple- receivers ($1 ~\mathrm{T}-\text{nR}$) architecture to improve accuracy and stability while maintaining low power consumption and cost. To enhance the quality of respiration signal extraction, we introduce two key innovations. First, a subcarrier ratio-based method that selects the most sensitive subcarrier combinations for respiration signal detection, improving system robustness, especially under noisy conditions. Second, an optimal receiver selection method is proposed, quantifying each receiver's sensing capability and intelligently selecting the best combination to optimize signal fusion. We evaluate LOAR-Fi in real-world environments, demonstrating exceptional performance with a mean absolute error of 0.31 bpm in respiration rate measurement, and over 90 % of data errors remaining below 0.5 bpm. LOAR-Fi achieves a 96 % detection accuracy for respiration presence, even under different user locations and orientations. These results show that LOAR-Fi significantly enhances the performance, adaptability, and reliability of WiFi-based respiration monitoring, providing a promising solution for healthcare applications.

With the rapid development of wireless sensing, trajectory-tracking methods based on Wi-Fi channel state information (CSI) have broad applicability in intelligent security systems, indoor navigation, and related scenarios owing to their low cost, contactless operation, and ease of deployment. Nevertheless, the high variability and noise of CSI limit the robustness and accuracy of existing methods, particularly in complex environments with dynamic pedestrian behavior. This paper proposes an indoor pedestrian trajectory-tracking framework that integrates deep learning, diffusion-based data augmentation, and particle filtering. First, we collect CSI in real environments and employ a diffusion model to augment the dataset, thereby improving the model's generalization. Next, a CNN-LSTM architecture extracts spatiotemporal features from CSI and learns a mapping from CSI to pedestrian positions. Finally, particle filtering is applied to smooth and reconstruct continuous position states over time. The proposed system achieves high-accuracy trajectory reconstruction in dynamic environments, with localization errors of approximately 0.5 m. It generalizes across diverse settings and demonstrates strong practical value and scalability.

Nowadays, voice input on earphones has become one of the most paramount human-computer interaction approaches. Traditional voice interaction is built on the air channel, which is highly noise-susceptible and suffers from being falsely triggered by nearby competing users. In our work, we design a noise-resistant voice interaction interface on earphones, namedEarOE, which takes advantage of the narrow-bandwidth body channel to reconstruct high-fidelity audible speech. Although promising, directly taking the body channel as a voice interaction interface is nontrivial since the limited bandwidth of body-channel speech causes the original timbre information and linguistic content to be lost. To address these issues, we employ an electro-acoustic (EA) model for occlusion effect-based cross-channel correlation analysis. Based on that, we carefully design an attention-based encoder-decoder network to embrace cross-channel correlation for high-quality wide-bandwidth spectrum synthesis. To accommodate individual differences and improve model generalization, we implement a physics-based data augmentation strategy to expand the scale of the training dataset. Through extensive real-world experiments with 28 participants,EarOE can achieve an average Mel-cepstral distance of 8.08, an average modulation spectra distance of 0.82, and an average log-spectral distance of 11.16, outperforming existing solutions.

The effectiveness of WiFi-based localization systems heavily relies on the spatial accuracy of WiFi AP. In real-world scenarios, factors such as AP rotation and irregular antenna tilt contribute significantly to inaccuracies, surpassing the impact of imprecise AP location and antenna separation. In this paper, we proposeAnteumbler, a non-invasive, accurate, and efficient system for measuring the orientation of each antenna in physical space. By leveraging the fact that maximum received power occurs when a Tx-Rx antenna pair is perfectly aligned, we build a spatial angle model capable of determining antennas’ orientations without prior knowledge. However, achieving comprehensive coverage across the spatial angle necessitates extensive sampling points. To enhance efficiency, we exploit the orthogonality of antenna directivity and polarization, and adopt an iterative algorithm, thereby reducing the number of sampling points by several orders of magnitude. Additionally, to attain the required antenna orientation accuracy, we mitigate the influence of propagation distance using a dual plane intersection model while filtering out ambient noise. Our real-world experiments, covering six antenna types, two antenna layouts, two antenna separations ($\lambda /2$and$\lambda$), and three AP heights, demonstrate thatAnteumblerachieves median errors below$\text{6}^\circ$for both elevation and azimuth angles, and exhibits robustness in NLoS and dynamic environments. Moreover, when integrated into the reverse localization system,Anteumblerdeployed over LocAP reduces antenna separation error by$10 \,\mathrm{mm}$, while for user localization system, its integration over SpotFi reduces user localization error by more than$1 \,\mathrm{m}$.

WiFi-based gait recognition technologies have seen significant advancements in recent years. However, most existing approaches rely on a critical assumption: users must walk continuously and maintain a consistent body posture. This poses a substantial challenge when users engage in non-periodic or discontinuous behaviors (e.g., stopping, starting, or turning mid-walk), which can disrupt the extraction of gait-related features and degrade recognition performance. To address this issue, we proposefreeGait, a novel approach designed to mitigate the impact of non-gait behaviors in WiFi-based gait recognition systems. Our solution models this problem as domain adaptation, where we learn domain-independent representations to isolate gait features from behavior-dependent noise. We treat human behaviors with labeled user data as source domains and behaviors without user labels as target domains. However, applying domain adaptation directly is challenging due to the ambiguous classification boundaries in the target domains for WiFi signals. To overcome this, we align the posterior distributions between the source and target domains and constrain the conditional distribution within the target domains to enhance gait classification accuracy. Additionally, we implement a data augmentation module to generate data resembling the labeled data, while supervised learning ensures distinctiveness between users. Our experiments, conducted with 20 participants across 3 different scenarios, demonstrate thatfreeGaitcan accurately predict data across 15 domains by labeling only a small subset from 6 source domains, achieving up to a 45% improvement in user classification accuracy compared to existing methods.

Accurately estimating the velocity (including speed and direction) of moving targets has recently attracted widespread attention in augmented reality, security monitoring and sports health. In particular, the Doppler Frequency Shift (DFS)-based velocity estimation schemes using WiFi devices have shown great potential and have been widely studied. However, previous Fast Fourier Transform (FFT)-based and path-parameter-based arts have inherent limitations in DFS estimation and, worse still, ignore the nonlinear measurement errors caused by the relative orientation between the moving target and the WiFi transceiver. The above limitations make it difficult to meet the requirements for fine-grained velocity estimation in practical applications. To cope with these limitations, in this article, we propose a learning-based velocity estimation framework, named freeDoppler , to achieve fine-grained, multi-target and orientation-independent velocity estimation. Specifically, we construct a WiFi-based Velocity Estimation Network (VEN), which leverages continuous complex-valued Channel State Information (CSI) sequences as input, to fully learn the inherent information of the Doppler effect and accurately predict velocity series. In addition, we adopt the electric field scattering model of Maxwell’s equations to construct a physics-informed CSI Generation Model (CGM), thereby generating large-scale and high-quality simulated CSI samples to improve the generalization of the VEN model. Throughout extensive real-world experiments, freeDoppler can achieve median errors of 7.98 cm/s for speed estimation, 28° for direction estimation and 35 cm for human tracking in one or two moving targets, significantly outperforming the state-of-the-art methods.

The performance of WiFi-based localization systems is affected by the spatial accuracy of WiFi AP. Compared with the imprecision of AP location and antenna separation, the imprecision of AP’s or antenna’s orientation is more important in real scenarios, including AP rotation and antenna irregular tilt. In this paper, we propose Anteumbler that non-invasively, accurately and efficiently measures the orientation of each antenna in physical space. Based on the fact that the received power is maximized when a Tx-Rx antenna pair is perfectly aligned, we construct a spatial angle model that can obtain the antennas’ orientations without prior knowledge. However, the sampling points of traversing the spatial angle need to cover the entire space. We use the orthogonality of antenna directivity and polarization and adopt an iterative algorithm to reduce the sampling points by hundreds of times, which greatly improves the efficiency. To achieve the required antenna orientation accuracy, we eliminate the influence of propagation distance using a dual plane intersection model and filter out ambient noise. Our real-world experiments with six antenna types, two antenna layouts and two antenna separations show that Anteumbler achieves median errors below 6 ° for both elevation and azimuth angles, and is robust to NLoS and dynamic environments. Last but not least, for the reverse localization system, we deploy Anteumbler over LocAP and reduce the antenna separation error by 10 mm, while for the user localization system, we deploy Anteumbler over SpotFi and reduce the user localization error by more than 1 m.

Recently, WiFi-based gait recognition technologies have been widely studied. However, most of them work on a strong assumption that users need to walk continuously and periodically under a constant body posture. Thus, a significant challenge arises when users engage in non-periodic or discontinuous behaviors (e.g., stopping and going, turning around during walking). This is because variations of non-gait behaviors interfere with the extraction of gait-related features, resulting in recognition performance degradation. To solve this problem, we propose freeGait, which aims to mitigate the user's non-gait behaviors of WiFi-based gait recognition system. Specifically, we model this problem as domain adaptation, by learning domain-independent representations to extract behavior-independent gait features. We consider human behaviors with labels of users as source domains, and human behaviors without labels of users as target domains. However, directly applying domain adaptation to our specific problem is challenging, because the classification boundaries of the unknown target domains are unclear for WiFi signals. We align the posterior distributions of the source and target domains, and constrain the conditional distribution of the target domains to optimize the gait classification accuracy. To obtain enough source domains data, we build a data augmentation module to generate data similar to the labeled data, and use supervised learning to make the data different between users. We conduct experiments with 20 people and 3 different scenarios, and the results show that accurate predictions of a total of 15 domains data can be achieved by only collecting and labeling a small amount of data from 6 source domains, and user classification accuracy can be improved by up to 45% compared to other existing techniques.

Recently, Wi-Fi based sensing technology has been widely studied to provide more convenient services for humans. Although previous arts claim to achieve diverse fine-grained sensing using Wi-Fi signals, most of them assume that the data such as Channel State Information (CSI) used to achieve the sensing tasks can be sufficiently collected. However, in practical, due to the competitive nature of Wi-Fi and the frequent intermittent traffic, Wi-Fi based sensing applications often encounter problems of irregular intervals and insufficient sampling. Therefore, in this paper, we propose a Wi-Fi signal sparse recovery system (WiSR) that aims to recover sufficient and uniform sensing data from unevenly spaced and under-sampled CSI. Inspired by the success of image and audio restoration, we improve the Generative Adversarial Network (GAN) to recover Wi-Fi CSI. However, the direct application of GAN technologies for image and audio to CSI is not effective due to the difference in data representation. First, to avoid spectral impairments after conversion from time domain to frequency domain, we directly operate on the original time series CSI waveforms, thus being able to recover continuous channel variations from intermittent sparse samples. Second, to enhance the above recovery process, we utilize two novel denoising methods to obtain clean CSI, and introduce restrictions in the time and frequency domains to optimize low-level features and high-frequency information, respectively. Real-world experiments show that WiSR can accurately recover CSI, even at a rate of 10 packets per second. Through practical applications of gait recognition and gesture recognition, WiSR significantly improves accuracy compared to traditional linear interpolation and cubic interpolation.

Due to contactless and convenient experiences, WiFi-based device-free fingerprints localization technologies have extensively attracted research attention. However, they are studied based on an assumption that the user is stationary and face a major challenge in the presence of users motions. That is because users motions induced CSIWiFi variations results in inconsistent location fingerprints during training and prediction, leading to system ineffective. To solve this problem, in this paper, we propose freeLoc, which aims to free users motions (even unseen) while maintaining accurate localization. Specifically, we construct a domain adaptation network that defines different users and motions as different domains, and learns domain-independent representations to extract location fingerprints independent of users motions. Unfortunately, collecting sufficient amounts of WiFi data is difficult. To reduce the cost of labeling data and ensure the performance of domain adaptation network, we utilize adversarial autoencoder to build a data augmentation module to introduce data diversity. We deploy experiments in a real scenario, and the results show that only by labeling three motions of three users, we can achieve accurate localization (the nearest locations are about one meter away) for a total of 36 domains including 6 users and 6 motions. Compared to other existing technologies, freeLoc can improve location prediction accuracy by up to 35%.

WiFi connections are vulnerable to simulated attacks from rogue access points (APs) or devices whose SSID and/or MAC/IP address are the same as legitimate devices. This kind of attack is difficult to counter with traditional network security mechanisms. In this article, we propose a new security mechanism that uses environment-independent features extracted from channel state information (CSI) to detect and identify rogue WiFi devices or APs, and reject their connections. We find that due to the$I/Q$imbalance and imperfect oscillator of each WiFi network card (NIC), the nonlinear phase error of different subcarriers will vary with the NIC. Through our experimental verification, this cross-subcarrier phase feature is invariant to the location and the environment. We deploy systems on two platforms that can extract constant phase errors from the constantly changing CSI in less than 1 s, which is at least$8 \times $faster than that of the state-of-the-art solution. Extensive experiments on commercial routers and end devices in different scenarios show that based on the Industrial Platform Computer (IPC) platform, where only nonencrypted rogue connections can be detected, the detection accuracy rate reaches 96%, and the false alarm rate is less than 2%. Based on the ASUS router platform (a commercial WiFi router), WiFi channels and smart device types are not restricted, which greatly improved universality, and the accuracy of device connection detection can even reach more than 99%. We improve a device-type identification method based on the communication traffic features of the device when connected to WiFi. Experiments show that even if there are multiple similar devices from the same manufacturer, the accuracy of device-type detection exceeds 99%.