2 January 2024 in IEEE Transactions on Mobile Computing
Contactless WiFi based human action recognition exhibits remarkable prospects in the fields such as human-computer interaction and smart home. However, domain dependency restricts its generalization into the real-world deployment. Since it is expensive to label enough new data for retaining a model, it is beneficial to explore few-shot learning for cross-domain sensing with limited target labels. Nevertheless, there are two challenges to be addressed. The first challenge is how to select a suitable dataset from a series of available source domains to prevent negative transfer. The second is to mine action-related characteristics by the feature learning model for the following effective knowledge transfer. In order to tackle the above challenges, we present a cross-domain sensing framework named CDFi, which consists of Nearest Neighbor based Domain Selector (NNDS) and Fine-to-Coarse-Grained Transformer Network (FCGTN). NNDS is proposed to evaluate the source-target domain similarities by measurements among local and global feature distributions. Besides, FCGTN embeds convolution map based hierarchical transformer structures and the modified linear layer into an end-to-end deep network, which can quickly adapt to the unseen domain by few samples. Comprehensive experiments show that CDFi can effectively realize cross-domain action recognition, and achieve about 4% and 10% improvement on cross-user and cross-scene cases, respectively, compared to the state-of-the-art.
23 May 2024 in IEEE Transactions on Mobile Computing
Passive human tracking plays a critical role in the field of ubiquitous sensing, offering customized services such as real-time location tracking for vital sign monitoring and motion detection. Traditional contact-free tracking systems are primarily designed for Line-of-Sight (LOS) scenarios, requiring a direct path between the radio device and the target. However, in Non-Line-of-Sight (NLOS) scenarios, where obstacles obstruct this direct path, these systems suffer from sensing failures and are unable to accurately obtain the motion trajectory of the sensing target. In this paper, we propose the UWTracking system, which utilizes the Commercial Off-the-Shelf (COTS) Impulse Radio-Ultra Wideband (IR-UWB) radars to enable precise indoor passive human tracking in both LOS and NLOS scenarios. To effectively capture the motion information of a moving target in NLOS scenarios, we present the Reconstructed Distributed-Doppler Frequency Shift (RD-DFS) features. We then binarize the RD-DFS features and design the Distance Extraction Algorithm (DEA) to obtain the target's distance in both scenarios. Subsequently, the Circle Intersection Method with Distance Stretching (CIM-DS) algorithm is developed to determine the indoor position of the sensing target, and the Scanning Angle and Velocity Particle Filter (SAV-PF) algorithm facilitates high-precision trajectory tracking. We implement a prototype of UWTracking system and conduct extensive evaluations to showcase its trajectory tracking performance under various scenarios. The results demonstrate that UWTracking achieves effective real-time tracking, with a median tracking error of 17.65 cm in the LOS scenario and 23.34 cm in the NLOS scenario, outperforming the state-of-the-art trajectory tracking systems based on COTS IR-UWB Radars.
23 May 2024 in IEEE Transactions on Vehicular Technology
WiFi-based Human Activity Recognition (HAR) plays a crucial role in achieving device-free Human-Machine Interaction (HMI). Due to the strong dependence of WiFi Channel State Information (CSI) on the target environment, current WiFi-based activity recognition methods often require extensive training data and struggle to adapt to new environments. To enhance the generalization ability of wireless sensing, we propose a cross-domain activity recognition system based on WiFi, WiCro. Wi-Cro utilizes Generative Adversarial Network (GAN) to transform source domain data into target domain data, supplemented by a small number of target domain samples to achieve cross-domain human activity recognition. We design a Subcarrier Dimension Reduction Algorithm (SDRA) to mitigate computational complexity of the system. This algorithm calculates the correlation between different CSI subcarriers and extracts principal components to reduce sample dimensions. Furthermore, we develop a data augmentation method based on GAN to transform source domain data into the target domain, addressing issues related to overfitting and domain adaptation due to insufficient samples. Finally, a metric learning approach is designed to further enhance the cross-domain sensing capability of the Wi-Cro system. Extensive experiments are performed using data collected in real-world environments and two public datasets. The results demonstrate that the Wi-Cro system consistently achieves high accuracy in human activity recognition across different datasets, proving its generalization abilities of cross-domain sensing.
3 August 2022 in IEEE Systems Journal
Human identification is essential for current intelligent applications. Traditional human identification methods usually require dedicated collection equipment or user cooperation, which limits the application scope of human identification. Recent research works have shown that Wi-Fi signals can support fine-grained sensing for human respiration. In this article, we leverage Wi-Fi signals to collect and recognize a unique physiological feature of humans, i.e., the respiration, for device-free and nonintrusive human identification. We propose a respiration sensing-based human identification system, namely BreathID. BreathID explores the nature of the amplitude and phase data in the CSI ratio model through vector analysis. By jointly using the discrete wavelet transform (DWT) and fake peak removal method, we accurately calculate the respiration rate and extract the breathing feature. We also propose a weighted multidimensional dynamic time warping (WMD-DTW) algorithm to realize the human identification based on multiple input multiple output (MIMO) technology. We implement the BreathID system on commercial Wi-Fi devices. The results show that BreathID can identify 11 users in three typical scenarios in daily life with an average accuracy of 97.52%. In particular, the average absolute error of the respiration rate in BreathID is about 0.1 bpm, which is better than the state-of-the-art algorithms.
2 October 2023 in IEEE Transactions on Mobile Computing
Sedentary behaviors are shown to be hazardous to human health. Detecting sedentary behaviors in a ubiquitous way can be realized by the promising WiFi sensing technique. The accurate detection of sedentary behaviors is determined by the accurate recognition of sit-stand postural transition (SPT). However, according to our findings, SPT recognition errors are inevitable even with advanced machine-learning methods, because different SPTs may result in a similar change in WiFi channel state information (CSI). To effectively reduce SPT recognition errors, in this paper we propose RoSeFi, a robust sedentary behavior monitoring system. We first classify the errors in SPT recognition results into two categories: the errors violating SPT's consistency and the errors violating SPTs’ symmetry. To correct the above errors, we reveal two inherent features in the CSI data of SPTs, i.e., contextual association and waveform mirror symmetry. Then a novel metric named WMSF is defined to quantify the degree of waveform mirror symmetry between two SPTs’ CSI data. Integrating the above features, the problem of recognition error correction can be modeled as a constrained nonlinear optimization problem (CNOP). To solve the problem, we design a unified error detection/correction scheme, named UEDC, which converts the CNOP into a sequence decoding problem in Hidden Markov Model (HMM). A tailored Viterbi algorithm combined with WMSF is proposed to detect and correct the errors simultaneously. The experimental results show that RoseFi reduces 60-82% SPT recognition errors, gains 15-20% relative improvement in the accuracy of SPT recognition, and eventually reduces the sedentary time estimation errors by 10%-20%, compared with typical existing systems. In addition, our error correction method can be adapted to most existing machine learning based human action recognition methods, effectively improving their performance.
11 May 2024 in ACM Transactions on Sensor Networks
As two important contents in WiFi-based action perception, detection and recognition require localizing motion regions from the entire temporal sequences and classifying the corresponding categories. Existing approaches, though yielding reasonably acceptable performances, are suffering from two major drawbacks: heavy empirical dependency and large computational complexity. In order to solve these issues, we develop LiteWiSys in this article, a lightweight system in an end-to-end deep learning manner to simultaneously detect and recognize WiFi-based human actions. Specifically, we assign different attentions on sub-carriers, which are then compressed to reduce noise and information redundancy. Then, LiteWiSys integrates deep separable convolution and a channel shuffle mechanism into a multi-scale convolutional backbone structure. By feature channel split, two network branches are obtained and further trained with a joint loss function for dual tasks. We collect different datasets at multi-scenes and conduct experiments to evaluate the performance of LiteWiSys. In comparison to existing WiFi sensing systems, LiteWiSys achieves promising precision with lower complexity.