WiFi Channel State Information Research Articles

Wi-CaL: WiFi Sensing and Machine Learning Based Device-Free Crowd Counting and Localization

Wireless sensing represented by WiFi channel state information (CSI) is now enabling various fields of applications such as person identification, human activity recognition, occupancy detection, localization, and crowd estimation these days. So far, those fields are mostly considered as separate topics in WiFi CSI-based methods, on the contrary, some camera and vision-based crowd estimation systems intuitively estimate both crowd size and location at the same time. Our work is inspired by the idea that WiFi CSI also may be able to perform the same as the camera does. In this paper, we construct <i>Wi-CaL</i>, a simultaneous crowd counting and localization system by using ESP32 modules for WiFi links. We extract several features that contribute to dynamic state (moving crowd) and static state (location of the crowd) from the CSI bundles, then assess our system by both conventional machine learning (ML) and deep learning (DL). As a result of ML-based evaluation, we achieved 0.35 median absolute error (MAE) of counting and 91.4&#x0025; of localization accuracy with five people in a small-sized room, and 0.41 MAE of counting and 98.1&#x0025; of localization accuracy with 10 people in a medium-sized room, by leave-one-session-out cross-validation. We compared our result with percentage of non-zero elements metric (PEM), which is a state-of-the-art metric for crowd counting, and confirmed that our system shows higher performance (0.41 MAE, 81.8&#x0025; of within-1-person error) than PEM (0.62 MAE, 66.5&#x0025; of within-1-person error).

Monitoring Respiratory Motion With Wi-Fi CSI: Characterizing Performance and the BreatheSmart Algorithm.

Respiratory motion (i.e., motion pattern and rate) can provide valuable information for many medical situations. This information may help in the diagnosis of different health disorders and diseases. Wi-Fi-based respiratory monitoring schemes utilizing commercial off-the-shelf (COTS) devices can provide contactless, low-cost, simple, and scalable respiratory monitoring without requiring specialized hardware. Despite intense research efforts, an in-depth investigation on how to evaluate this type of technology is missing. We demonstrated and assessed the feasibility of monitoring and extracting human respiratory motion from Wi-Fi channel state information (CSI) data. This demonstration involves implementing an end-to-end system for a COTS-based hardware platform, control software, data acquisition, and a proposed processing algorithm. The processing algorithm is a novel deep-learning-based approach that exploits small changes in both CSI amplitude and phase information to learn high-level abstractions of breathing-induced chest movements and to reveal the unique characteristics of their difference. We also conducted extensive laboratory experiments demonstrating an assessment technique that can be replicated when quantifying the performance of similar systems. The results indicate that the proposed scheme can classify respiratory patterns and rates with an accuracy of 99.54% and 98.69%, respectively, in moderately degraded RF channels. Comprehensive data acquisition revealed the capability of the proposed system in detecting and classifying respiratory motions. Understanding the feasible limits and potential failure factors of Wi-Fi CSI-based respiratory monitoring scheme - and how to evaluate them - is an essential step toward the practical deployment of this technology. This study discusses ideas for further expansion of this technology.

Crowd Counting Based on WiFi Channel State Information and Transfer Learning

With the popularity and development of indoor WiFi equipment, they have more sensing capability and can be used as a human monitoring device. We can collect the channel state information (CSI) from WiFi device and acquire the human state based on the measurements. These studies have attracted wide attention and become a hot research topic. This paper concentrated on the crowd counting based on CSI and transfer learning. We utilized the CSI signal fluctuations caused by human motion in WiFi coverage to identify the person count because different person counts would lead to unique signal propagation characteristics. First, this paper presented recent studies of crowd counting based on CSI. Then, we introduced the basic concept of CSI, and described the fundamental principle of CSI-based crowd counting. We also presented the system framework, experiment scenario, and neural network structure transferred from the ResNet. Next, we presented the experiment results and compared the accuracy using different neural network models. The system achieved recognition accuracy of this 100 percent for seven participants using the transfer learning technique. Finally, we concluded the paper by discussing the current problems and future work.

Human Activity Recognition based on Wi-Fi CSI Data -A Deep Neural Network Approach

Using Wi-Fi Channel State Information (CSI) is a novel way of environmental sensing and human activity recognition (HAR). These methods can be used for several safety and security applications by (re)using Wi-Fi routers without the need for additional costly hardware required for vision-based approaches, known also to be particularly privacy-intrusive. This work introduces a full pipeline of a Wi-Fi CSI-based system for human activity recognition that assesses and compares two deep learning methods. We analyze how different hardware configurations affect WiFi CSI signals. We contribute a novel and more realistic data collection process, in which human activity recognition is seamlessly integrated in real-life, resulting in more reliable assessments of the model classification performance. We analyze how InceptionTime and LSTM-based classification models perform in human activity recognition. The source code and collected dataset are made publicly available for reproducibility and encouraging further research in the community.

Adaptive Scheme for Crowd Counting Using off-the-Shelf Wireless Routers

Since the outbreak of the world-wide novel coronavirus pandemic, crowd counting in public areas, such as in shopping centers and in commercial streets, has gained popularity among public health administrations for preventing the crowds from gathering. In this paper, we propose a novel adaptive method for crowd counting based on Wi-Fi channel state information (CSI) by using common commercial wireless routers. Compared with previous researches on device-free crowd counting, our proposed method is more adaptive to the change of environment and can achieve high accuracy of crowd count estimation. Because the distance between access point (AP) and monitor point (MP) is typically non-fixed in real-world applications, the strength of received signals varies and makes the traditional amplitude-related models to perform poorly in different environments. In order to achieve adaptivity of the crowd count estimation model, we used convolutional neural network (ConvNet) to extract features from correlation coefficient matrix of subcarriers which are insensitive to the change of received signal strength. We conducted experiments in university classroom settings and our model achieved an overall accuracy of 97.79% in estimating a variable number of participants.

TIPS: Transformer Based Indoor Positioning System Using Both CSI and DoA of WiFi Signal

In a channel state information (CSI) based indoor positioning system, the positioning performance becomes susceptible to multipath fading effects especially in non-line-of-sight environments. We propose a transformer-based indoor positioning system (TIPS) to address this challenge. The proposed TIPS utilizes a self-attention mechanism to process the continuous WiFi CSI observed from predetermined routes as fingerprints in a given indoor environment. Each route is then considered a sentence, whereas the position along the route is treated as a word in terms of natural language processing. Consequently, the problem of predicting the position with the fingerprints can then be considered the task of predicting the current word with previous words, which can be efficiently solved using the proposed TIPS. In order to fully exploit the relations among positions, we propose embedding the information of the direction of arrival (DoA) on top of the collected CSI as inputs to the TIPS. Thus, the transformer of the proposed TIPS can better capture the dependencies of the positions in the route and significantly boost positioning accuracy. To exhibit the superiority of the proposed TIPS in a radio frequency (RF) environment, we demonstrate a hardware implementation of an RF testbed consisting of an emulator of WiFi access point and user equipment. Through extensive computer simulations and experimental tests, it is demonstrated that the proposed TIPS can reduce the positioning error down to 20 cm, which is a significant improvement compared to the current state-of-the-art models.

Wi-Fruit

People usually assess fruit qualities from external features such as color, shape, size, and texture. However, it is quite common that we select fruits with perfect appearances but rotten inside, especially for fruits with thick pericarps. Thus the accurate measurement is desirable to evaluate the internal conditions of fruits. As two key features of fruit internal qualities, existing methods on measuring fruit moisture and soluble solid contents (SSC) are either destructive or costly, limiting their adoption in daily life. In this paper, we propose Wi-Fruit, a non-destructive and low-cost fruit moisture and SSC measurement system leveraging Wi-Fi channel state information (CSI). First, to cope with the fruit structure dependency challenge, we propose a double-quotient model to pre-process CSI on adjacent antennas. Second, to address the fruit size and type dependency challenges, a lightweight artificial neural network (ANN) model with visual information fusion is proposed for fruit moisture and SSC estimations. Extensive evaluations are conducted on 6 types of fruits with both thick (i.e., watermelon and grapefruit) and thin pericarps (i.e., dragon fruit, apple, pear, and orange) over a month in either an empty laboratory room or a library with massive books. Results demonstrate that Wi-Fruit achieves an acceptable estimation accuracy (RMSE=0.319). It is independent of various fruit structures, sizes, and types, while also robust to time and environmental changes. The fruit internal sensing capabilities of Wi-Fruit can help fruit saving and safety in both pre-harvest and post-harvest applications.

A Domain-Independent Generative Adversarial Network for Activity Recognition Using WiFi CSI Data.

Over the past years, device-free sensing has received considerable attention due to its unobtrusiveness. In this regard, context recognition using WiFi Channel State Information (CSI) data has gained popularity, and various techniques have been proposed that combine unobtrusive sensing and deep learning to accurately detect various contexts ranging from human activities to gestures. However, research has shown that the performance of these techniques significantly degrades due to change in various factors including sensing environment, data collection configuration, diversity of target subjects, and target learning task (e.g., activities, gestures, emotions, vital signs). This problem, generally known as the domain change problem, is typically addressed by collecting more data and learning the data distribution that covers multiple factors impacting the performance. However, activity recognition data collection is a very labor-intensive and time consuming task, and there are too many known and unknown factors impacting WiFi CSI signals. In this paper, we propose a domain-independent generative adversarial network for WiFi CSI based activity recognition in combination with a simplified data pre-processing module. Our evaluation results show superiority of our proposed approach compared to the state of the art in terms of increased robustness against domain change, higher accuracy of activity recognition, and reduced model complexity.

CSITime: Privacy-preserving human activity recognition using WiFi channel state information

Human activity recognition (HAR) is an important task in many applications such as smart homes, sports analysis, healthcare services, etc. Popular modalities for human activity recognition involving computer vision and inertial sensors are in the literature for solving HAR, however, they face serious limitations with respect to different illumination, background, clutter, obtrusiveness, and other factors. In recent years, WiFi channel state information (CSI) based activity recognition is gaining momentum due to its many advantages including easy deployability, and cost-effectiveness. This work proposes CSITime, a modified InceptionTime network architecture, a generic architecture for CSI-based human activity recognition. We perceive CSI activity recognition as a multi-variate time series problem. The methodology of CSITime is threefold. First, we pre-process CSI signals followed by data augmentation using two label-mixing strategies — mixup and cutmix to enhance the neural network’s learning. Second, in the basic block of CSITime, features from multiple convolutional kernels are concatenated and passed through a self-attention layer followed by a fully connected layer with Mish activation. CSITime network consists of six such blocks followed by a global average pooling layer and a final fully connected layer for the final classification. Third, in the training of the neural network, instead of adopting general training procedures such as early stopping, we use one-cycle policy and cosine annealing to monitor the learning rate. The proposed model has been tested on publicly available benchmark datasets, i.e., ARIL, StanWiFi, and SignFi datasets. The proposed CSITime has achieved accuracy of 98.20%, 98%, and 95.42% on ARIL, StanWiFi, and SignFi datasets, respectively, for WiFi-based activity recognition. This is an improvement on state-of-the-art accuracies by 3.3%, 0.67%, and 0.82% on ARIL, StanWiFi, and SignFi datasets, respectively. In lab-5 users’ scenario of the SignFi dataset, which has the training and testing data from different distributions, our model achieved accuracy was 2.17% higher than state-of-the-art, which shows the comparative robustness of our model.

Wi-Sense: a passive human activity recognition system using Wi-Fi and convolutional neural network and its integration in health information systems

A human activity recognition (HAR) system acts as the backbone of many human-centric applications, such as active assisted living and in-home monitoring for elderly and physically impaired people. Although existing Wi-Fi-based human activity recognition methods report good results, their performance is affected by the changes in the ambient environment. In this work, we present Wi-Sense—a human activity recognition system that uses a convolutional neural network (CNN) to recognize human activities based on the environment-independent fingerprints extracted from the Wi-Fi channel state information (CSI). First, Wi-Sense captures the CSI by using a standard Wi-Fi network interface card. Wi-Sense applies the CSI ratio method to reduce the noise and the impact of the phase offset. In addition, it applies the principal component analysis to remove redundant information. This step not only reduces the data dimension but also removes the environmental impact. Thereafter, we compute the processed data spectrogram which reveals environment-independent time-variant micro-Doppler fingerprints of the performed activity. We use these spectrogram images to train a CNN. We evaluate our approach by using a human activity data set collected from nine volunteers in an indoor environment. Our results show that Wi-Sense can recognize these activities with an overall accuracy of 97.78%. To stress on the applicability of the proposed Wi-Sense system, we provide an overview of the standards involved in the health information systems and systematically describe how Wi-Sense HAR system can be integrated into the eHealth infrastructure.

C-Chirp: Towards Symmetric Cross-Technology Communication Over Asymmetric Channels

Cross-Technology Communication (CTC) is an emerging technique that enables direct interconnection among incompatible wireless technologies. However, CTC channels are inherently asymmetric because of either the one-way nature of emulation or the asymmetric communication range caused by the asymmetric transmission power. In this paper, we focus on establishing symmetric CTC over asymmetric CTC channels. The bottleneck is the short communication range from the low-power and narrow-band technology to the high-power and wide-band technology. To compensate the inevitable distortions, we take advantage of the channel asymmetry and construct chirps in WiFi Channel State Information (CSI) to extend the communication range from ZigBee to WiFi. We build the theoretical model of CSI chirp based CTC and design c-Chirp, a novel CTC from ZigBee to WiFi. Due to channel asymmetry and discreteness, the WiFi receiver can only observe partial and distorted CSI chirps. To cope with this issue, we design a matching based chirp decoding method as well as an adaptation algorithm to reliably decode the symbols. We further extend c-Chirp to one-to-multiple concurrent transmission scenario. The evaluation results show that c-Chirp can achieve a communication range of 60m, which is 6× longer than ZigFi, an existing representative CTC from ZigBee to WiFi.

Improving human action recognition by jointly exploiting video and WiFi clues

Recent years have witnessed the increasing attentions on human action recognition(HAR). Traditional methods are prone to explore the optimum spatiotemporal feature representation of human actions in video clips so as to achieve high recognition performance. However, the optical limitations, such as inappropriate view, dim illumination and object occlusion, usually degrade video quality and affect the recognition performance a lot. Considering that wireless signals are robust against optical limitations, we thus incorporate WiFi signals with video streams for HAR. Specifically, we use WiFi Channel State Information as a compensator for video streams. A great challenge is how to effectively fuse the video and WiFi information to achieve better prediction performance. To this end, we employ convolution neural networks and statistic analysis algorithms to extract video and WiFi features respectively, and propose a novel multi-modal learning approach for video and WiFi feature fusion, where the video and WiFi features are projected to a common space by supervised learning. The experimental results indicate that the recognition precision of human actions in videos improved obviously with the aid of WiFi signals and the proposed multi-modal learning approach rivals the state of art methods.

A Stacked Neural Network-Based Machine Learning Framework to Detect Activities and Falls Within Multiple Indoor Environments Using Wi-Fi CSI

Device-free methods for activity or fall detection using Wi-Fi channel state information (CSI) have become popular in the literature as they are not intrusive to privacy like competing camera-based solutions. However, such methods require significant setup processes. The objective of this letter is to improve upon the current CSI-based systems by proposing a two-stage modular architecture. A stacked neural network is developed that selects which environment or room a person is located within, before engaging a room-level model for activity recognition. This allows machine learning models to be iteratively deployed to multiple environments without retraining previously deployed room-level models.

WiONE: One-Shot Learning for Environment-Robust Device-Free User Authentication via Commodity Wi-Fi in Man–Machine System

User authentication is the first and most critical step in protecting a man-machine system from a malicious spoofer. However, security and privacy are just like the two sides of one coin, hard to see both at the same time, especially by the current mainstream credential- and biometric-based approaches. To this end, we propose WiONE, a safe and privacy-preserving user authentication system leveraging the ubiquitous Wi-Fi infrastructure by exploring “how you behave” rather than “who you are”. The key idea is to apply deep learning to user physical behavior captured by Wi-Fi channel state information (CSI) to identify legitimate users while rejecting spoofers. The design of WiONE faces two challenges, namely, how to capture the subtle behavior, such as a keystroke on CSI, and how to mitigate the heavy environment-specific training required by deep learning. For the former, we design a behavior enhancement model based on the Rician fading to highlight the behavior-induced information by suppressing the behavior-unrelated information on channel response. For the latter, we develop a behavior characterization method tailored for the prototypical networks to facilitate the extraction of the domain-independent behavioral features and enable one-shot recognition of a new user in a new environment. Numerous experiments are conducted in several real-world environments, and the results show that WiONE outperforms its state-of-the-art rivals in authentication performance with much less training effort.

Human fall recognition based on WiFi CSI with dynamic subcarrier extraction of interference index

Recently, human fall recognition based on channel state information(CSI) were emerging technologies. However, the widespread deployment of WiFi may cause wireless interference problems for such WiFi CSI recognition, which will reduce the accuracy of human fall activity recognition. So, the paper proposed a dynamic subcarrier extraction method based on interference index (CII-DSE). It used the interference index to divide the interference level and determined the corresponding weak correlation subcarrier combination to reduce the presence of channel interference. Experiment results shown that in the WiFi overlapping channel interference environment, the accuracy of CII-DSE was 95. 8%, which effectively improves human the fall recognition influence.

CSI-based human sensing using model-based approaches: a survey

Abstract Currently, human sensing draws much attention in the field of ubiquitous computing, and human sensing based on WiFi CSI (channel state information) becomes a hot research topic due to the easy deployment and availability of WiFi devices. Although various human sensing applications based on the CSI signal model are emerging, the model-based approach has not been studied thoroughly. This paper provides a comprehensive survey of the latest model-based human sensing methods and their applications. First, the CSI signal and framework of model-based human sensing methods are introduced. Then, related models and fundamental signal preprocessing techniques are described. Next, typical human sensing applications are investigated, and the crucial characteristics are summarized. Finally, the advantages, limitations, and future research trends of model-based human sensing methods are concluded in this paper.

A Framework for Human Activity Recognition Based on WiFi CSI Signal Enhancement

With the advancement of wireless technologies and sensing methodologies, many studies have shown that wireless signals can sense human behaviors. Human activity recognition using channel state information (CSI) in commercial WiFi devices plays an important role in many applications. In this paper, a framework for human activity recognition was constructed based on WiFi CSI signal enhancement. Firstly, the sensitivity of different antennas to human activity was studied. An antenna selection algorithm was proposed, which can make a choice of the antenna automatically based on their sensitivity in accordance with different activities. Secondly, two signal enhancement approaches, which can strengthen the active signals and weaken the inactive signals, were proposed to extract the active interval caused by human activity. Finally, an activity segmentation algorithm was proposed to detect the start and end time of activity. In order to verify and evaluate the methods, extensive experiments have been conducted in real indoor environments. The experimental results have demonstrated that our solutions can eliminate a large number of redundant information brought by insensitive and inactive signals. Our research results can be put into use to improve recognition accuracy significantly and decrease the cost of recognition time.

WS-WiFi: Wired Synchronization for CSI Extraction on COTS-WiFi-Transceivers

WiFi channel state information (CSI) is a key enabler of precise radio sensing applications for commercially available off-the-shelf hardware. By utilizing colocated WiFi devices, this article aims to perform Angle-of-Arrival (AoA) estimation as one instance of radio sensing. However, unsynchronized local oscillators (LOs) in a WiFi network can cause carrier frequency offsets and sampling frequency offsets, which can lead to imperfect CSI. To this end, we propose a wired LO clocking scheme to eliminate residual impairments on regular WiFi transceivers. By utilizing a common oscillator, we transform a standard WiFi setup to a frequency-aligned transceiver architecture across several colocated devices. Building upon the proposed scheme, we present a detailed investigation of hardware-related impairments and environmental conditions. In particular, we are the first to investigate the temperature-dependent behavior of the CSI phase across multiple devices. We validate the performance in a lab setup as well as in a real-world application assembly, namely, a nine-antenna uniform circular array for AoA estimation. Furthermore, we show that with only a single received packet and minor hardware adjustments, we are able to obtain the AoA of a WiFi transmitter with a mean absolute error of 1.5° in line-of-sight conditions and 19.9° in strong multipath living room conditions.

Federated Self-Supervised Learning of Multisensor Representations for Embedded Intelligence

Smartphones, wearables, and Internet of Things (IoT) devices produce a wealth of data that cannot be accumulated in a centralized repository for learning supervised models due to privacy, bandwidth limitations, and the prohibitive cost of annotations. Federated learning provides a compelling framework for learning models from decentralized data, but conventionally, it assumes the availability of labeled samples, whereas on-device data are generally either unlabeled or cannot be annotated readily through user interaction. To address these issues, we propose a self-supervised approach termed \textit{scalogram-signal correspondence learning} based on wavelet transform to learn useful representations from unlabeled sensor inputs, such as electroencephalography, blood volume pulse, accelerometer, and WiFi channel state information. Our auxiliary task requires a deep temporal neural network to determine if a given pair of a signal and its complementary viewpoint (i.e., a scalogram generated with a wavelet transform) align with each other or not through optimizing a contrastive objective. We extensively assess the quality of learned features with our multi-view strategy on diverse public datasets, achieving strong performance in all domains. We demonstrate the effectiveness of representations learned from an unlabeled input collection on downstream tasks with training a linear classifier over pretrained network, usefulness in low-data regime, transfer learning, and cross-validation. Our methodology achieves competitive performance with fully-supervised networks, and it outperforms pre-training with autoencoders in both central and federated contexts. Notably, it improves the generalization in a semi-supervised setting as it reduces the volume of labeled data required through leveraging self-supervised learning.

A Survey of User Authentication Based on Channel State Information

Recently, human behavior sensing based on WiFi channel state information has drawn more attention in the ubiquitous computing field because it can provide accurate information about the target under a device‐free scheme. This paper concentrates on user authentication applications using channel state information. We investigate state‐of‐the‐art studies and survey their characteristics. First, we introduce the concept of channel state information and outline the fundamental principle of user authentication. These systems measure the dynamic channel state information profile and implement user authentication by exploring the channel state information variation caused by users because each user generates unique channel state information fluctuations. Second, we elaborate on signal processing approaches, including signal selection and preprocessing, feature extraction, and classification methods. Third, we thoroughly investigate the latest user authentication applications. Specifically, we analyze these applications from typical human action, including gait, activity, gesture, and stillness. Finally, we provide a comprehensive discussion of user authentication and conclude the paper by presenting some open issues, research directions, and possible solutions.