In recent years, we have seen efforts made to simultaneously monitor the respiration of multiple persons based on the channel state information (CSI) retrieved from commodity WiFi devices. Existing approaches mainly rely on spectral analysis of the CSI amplitude to obtain respiration rate information, leading to multiple limitations: (1) spectral analysis works when multiple persons exhibit dramatically different respiration rates, however, it fails to resolve similar rates; (2) spectral analysis can only obtain the average respiration rate over a period of time, and it is unable to capture the detailed rate change over time; (3) they fail to sense the respiration when a target is located at the "blind spots" even the target is close to the sensing devices. To overcome these limitations, we propose MultiSense, the first WiFi-based system that can robustly and continuously sense the detailed respiration patterns of multiple persons even they have very similar respiration rates and are physically closely located. The key insight of our solution is that the commodity WiFi hardware nowadays is usually equipped with multiple antennas. Thus, each individual antenna can receive a different mix copy of signals reflected from multiple persons. We successfully prove that the reflected signals are linearly mixed at each antenna and propose to model the multi-person respiration sensing as a blind source separation (BSS) problem. Then, we solve it using independent component analysis (ICA) to separate the mixed signal and obtain the reparation information of each person. Extensive experiments show that with only one pair of transceivers, each equipped with three antennas, MultiSense is able to accurately monitor respiration even in the presence of four persons, with the mean absolute respiration rate error of 0.73 bpm (breaths per minute).

MultiSense: Enabling Multi-person Respiration Sensing with Commodity WiFi

Recent advances in device-free wireless sensing have created the emerging technique of device-free human gesture recognition (DFHGR), which could recognize human gestures by analyzing their shadowing effect on surrounding wireless signals. DFHGR has many potential applications in the fields of human–machine interaction, smart home, intelligent space, etc. State-of-the-art work has achieved satisfactory recognition accuracy when there are a sufficient number of training samples. However, it is time consuming and labor intensive to collect samples, thus how to realize DFHGR under a small training sample set becomes an urgent problem to solve. Motivated by the excellent ability of the generative adversarial network in synthesizing samples, in this article, we explore and exploit the idea of leveraging it to realize virtual samples augmentation. Specifically, we first design a single scenario network with new architecture and better-designed loss function to generate virtual samples using a few number of real samples. Then, we further develop a scenario transferring network to generate virtual samples by utilizing the real samples not only from the current scenario but also from another available scenario as well, which could improve the quality of synthesized samples with the extra knowledge learned from another scenario. We design an mmWave-based DFHGR testbed to test the proposed networks, extensive experimental results demonstrate that the augmented virtual samples are of high quality and facilitate DFHGR systems to achieve better accuracy.

Device-Free Human Gesture Recognition With Generative Adversarial Networks

Sitting posture has a close relationship with our health, and keeping a healthy sitting posture is critical to each of us. Poor sitting postures often inevitably increase the risk of modern health musculoskeletal disorders. Previous works either used a camera to record the image or attached wearable sensors on the human body to recognize sitting postures. However, video-based approaches may face privacy issues while the wearable sensor-based approaches may cause uncomfortable to the user. In this work, we propose SitR, the first sitting posture recognition system using RF signals alone, which neither compromises the privacy nor requires wearing various sensors on the human body. We demonstrate that SitR can successfully recognize seven habitual sitting postures with just three lightweight and low-cost RFID tags pasted to the user’s back. Our design exploits the correlation between the phase change of RFID tags and the sitting postures. By extracting effective features of the measured phase sequences and employing appropriate machine learning algorithm, SitR can achieve robust and high performance. We evaluate the performance of SitR with ten volunteers in two different scenarios. Extensive experiments show SitR can recognize seven sitting postures with a high accuracy across different scenarios and various conditions. SitR can further detect the abnormal respiration, stand up, and sit down and provide sitting posture history for sedentary people.

SitR: Sitting Posture Recognition Using RF Signals

Goal: The SARS-CoV-2 viral infection could cause severe acute respiratory syndrome, disturbing the regular breathing and leading to continuous coughing. Automatic respiration monitoring systems could provide the necessary metrics and warnings for timely intervention, especially for those with mild symptoms. Current respiration detection systems are expensive and too obtrusive for any large-scale deployment. Thus, a low-cost pervasive ambient sensor is proposed. Methods: We will posit a barometer on the working desk and develop a novel signal processing algorithm with a sparsity-based filter to remove the similar-frequency noise. Three modes (coughing, breathing and others) will be conducted to detect coughing and estimate different respiration rates. Results: The proposed system achieved 97.33% accuracy of cough detection and 98.98% specificity of respiration rate estimation. Conclusions: This system could be used as an effective screening tool for detecting subjects suffering from COVID-19 symptoms and enable large scale monitoring of patients diagnosed with or recovering.

/pdf/a-pervasive-respiratory-monitoring-sensor-for-covid-19-4sfrmfwfqa.pdf

A Pervasive Respiratory Monitoring Sensor for COVID-19 Pandemic

Sleep apnea is a sleep disorder in which breathing is briefly and repeatedly interrupted. Polysomnography (PSG) is the standard clinical test for diagnosing sleep apnea. However, it is expensive and time-consuming which requires hospital visits, specialized wearable sensors, professional installations, and long waiting lists. To address this problem, we design a smartwatch-based system called ApneaDetector, which exploits the built-in sensors in smartwatches to detect sleep apnea. Through a clinical study, we identify features of sleep apnea captured by smartwatch, which can be leveraged by machine learning techniques for sleep apnea detection. However, there are many technical challenges such as how to extract various special patterns from the noisy and multi-axis sensing data. To address these challenges, we propose signal denoising and data calibration techniques to process the noisy data while preserving the peaks and troughs which reflect the possible apnea events. We identify the characteristics of sleep apnea such as signal spikes which can be captured by smartwatch, and propose methods to extract proper features to train machine learning models for apnea detection. Through extensive experimental evaluations, we demonstrate that our system can detect apnea events with high precision (0.9674), recall (0.9625), and F1-score (0.9649).

ApneaDetector: Detecting Sleep Apnea with Smartwatches

Sleep sound-activities including snore, cough and somniloquy are closely related to sleep quality, sleep disorder and even illnesses. To obtain the information of these activities, current solutions either require the user to wear various sensors/devices, or use the camera/microphone to record the image/sound data. However, many people are reluctant to wear sensors/devices during sleep. The video-based and audio-based approaches raise privacy concerns. In this work, we propose a novel system TagSleep to address the issues mentioned above. For the first time, we propose the concept of two-layer sensing. We employ the respiration sensing information as the basic first-layer information, which is applied to further obtain rich second-layer sensing information including snore, cough and somniloquy. Specifically, without attaching any device to the human body, by just deploying low-cost and flexible RFID tags near to the user, we can accurately obtain the respiration information. What's more interesting, the user's cough, snore and somniloquy all affect his/her respiration, so the fine-grained respiration changes can be used to infer these sleep sound-activities without recording the sound data. We design and implement our system with just three RFID tags and one RFID reader. We evaluate the performance of TagSleep with 30 users (13 males and 17 females) for a period of 2 months. TagSleep is able to achieve higher than 96.58% sensing accuracy in recognizing snore, cough and somniloquy under various sleep postures. TagSleep also boosts the sleep posture recognition accuracy to 98.94%.

Beyond Respiration: Contactless Sleep Sound-Activity Recognition Using RF Signals

Today, sedentary behaviors and bad sitting postures are the main causes of modern health musculoskeletal disorders and illnesses. Previous works either used a camera to record the image or attached wearable sensors on human body to recognize sitting postures. However, video-base approaches may face privacy issue while the wearable sensor-based approaches may cause uncomfortable to the user. This paper introduces SitR, the first sitting posture recognition system using RF signals alone. We demonstrate that with just three tags pasted to one’s back, SitR can successfully recognize three habitual sitting postures. Our design exploits the correlation between the phase change of RFID tags and the sitting postures. By extracting effective features from the measured phase sequences and employing machine learning algorithm, SitR can achieve robust and high performance. We evaluated SitR through extensive experiments including 14 volunteers under 3 different scenarios. The experiment results show that SitR can recognize sitting postures with an average accuracy of 99.27%. Our system can further detect the abnormal respiration and provide sitting posture history for sedentary people.

Lin Feng

Papers

Beyond Respiration: Contactless Sleep Sound-Activity Recognition Using RF Signals

SitR: Sitting Posture Recognition Using RF Signals

Are you sitting right?-Sitting Posture Recognition Using RF Signals