Chenshu Wu

• Doctor of Philosophy
• University of Maryland, College Park

Inertial measurements are critical to almost any mobile applications. It is usually achieved by dedicated sensors (e.g., accelerometer, gyroscope) that suffer from significant accumulative errors. This paper presents RIM, an RF-based Inertial Measurement system for precise motion processing. RIM turns a commodity WiFi device into an Inertial Measur...

Voice interfaces have become one of the most ubiquitous human-computer interaction methods in recent years. Voice Activity Detection (VAD) is typically the first building block of a complex voice interface, often relying on audio signals. Acoustics-based VAD systems do not perform well in noisy and interference-prone environments. Smart assistants...

As WiFi has become a ubiquitous medium for communication, its role in sensing applications has expanded. However, the current WiFi sensing applications are limited by their assumption that any detected motion signifies human activity, overlooking the potential impact of non-human subjects. Existing attempts to recognize the interference from non-hu...

Speech enhancement and separation have been a long-standing problem, especially with the recent advances using a single microphone. Although microphones perform well in constrained settings, their performance for speech separation decreases in noisy conditions. In this work, we propose RadioSES , an audioradio speech enhancement and separation sy...

Indoor intelligent perception systems have gained significant attention in recent years. However, accurately detecting human presence can be challenging in the presence of non-human subjects such as pets, robots, and electrical appliances, limiting the practicality of these systems for widespread use. In this paper, we propose a novel system (“WI-M...

Child Presence Detection (CPD) is becoming a regulatory requirement for car manufacturers to save children’s lives when they are left alone in unattended vehicles. However, most of the existing solutions require dedicated devices and suffer from limited accuracy and coverage. In this paper, we build WiCPD, the first-of-its-kind in-car child presenc...

The next big deal for Wi-Fi is not about communication and networking, but sensing. Wireless sensing technology is turning a Wi-Fi device into a ubiquitous sensor, which not only adds a brand new dimension to the functions, capabilities, and applications of all Wi-Fi systems, but also revolutionizes how sensing, especially human-centric sensing, is...

Speech enhancement and separation have been a long-standing problem, especially with the recent advances using a single microphone. Although microphones perform well in constrained settings, their performance for speech separation decreases in noisy conditions. In this work, we propose RadioSES, an audioradio speech enhancement and separation syste...

Driving safety has been attracting more and more interest due to the unprecedented proliferation of vehicles and the subsequent increase of traffic accidents. As such the research community has been actively seeking solutions that can make vehicles more intelligent and thus improve driving safety in everyday life. Among all the existing approaches,...

Voice interfaces have become an integral part of our lives with the proliferation of smart devices. Today, IoT devices mainly rely on microphones to sense sound. Microphones, however, have fundamental limitations, such as weak source separation, limited range in the presence of acoustic insulation, and being prone to multiple side-channel attacks....

Indoor target detection through motion sensing based on Wi-Fi signals has gained much attention recently. However, most of the existing motion detection approaches can only detect motion in a large coverage area without knowing the distance of the target motion from the transmitter (Tx)/receiver (Rx). Passive positioning techniques can provide the...

Indoor location-based services rely on indoor maps, which are yet widely available despite numerous efforts from the industry. Existing solutions employ costly hardware (e.g., lidar) to achieve accurate mapping of indoor environments, or resort to crowdsourcing for floor plan generation at the cost of precision due to inaccurate inertial sensing. I...

Extensive efforts have been devoted to human gesture recognition with radio frequency (RF) signals. However, their performance degrades when applied to novel gesture classes that have never been seen in the training set. To handle unseen gestures, extra efforts are inevitable in terms of data collection and model retraining. In this article, we pre...

As automobiles have become an essential part to facilitate our daily life, Advanced Driver Assistance Systems (ADAS) have been gaining more and more interest in assisting drivers to enhance both safety and convenience. To respond timely in case of an emergency, ADAS needs to keep track of the driver’s health/consciousness, which is generally achiev...

Heart rate variability (HRV), which measures the fluctuation of heartbeat intervals, has been considered as an important indicator for general health evaluation. To alleviate the user burden and explore the usability for long-term health monitoring, noncontact methods for HRV monitoring have drawn tremendous attention. In this article, we present m...

Indoor localization has gained increasing attention in the era of the Internet of Things. Among various technologies, WiFi fingerprint-based localization has become a mainstream solution. However, RSS fingerprints suffer from critical drawbacks of spatial ambiguity and temporal instability that root in multipath effects and environmental dynamics,...

Fall is recognized as one of the most frequent accidents among elderly people. Many solutions, either wearable or non-contact, have been proposed for fall detection recently. Among them, WiFi-based non-contact approaches are gaining popularity due to the ubiquity and non-invasiveness. The existing works, however, usually rely on labor-intensive and...

With the development of signal processing technology, the ubiquitous Wi-Fi devices open an unprecedented opportunity to solve the challenging human gesture recognition problem by learning motion representations from wireless signals. Wi-Fi-based gesture recognition systems, although yield good performance on specific data domains, are still practic...

Voice interfaces has become an integral part of our lives, with the proliferation of smart devices. Today, IoT devices mainly rely on microphones to sense sound. Microphones, however, have fundamental limitations, such as weak source separation, limited range in the presence of acoustic insulation, and being prone to multiple side-channel attacks....

Keyboard acts as one of the most commonly used mediums for human–computer interaction. Today, massive Internet-of-Things (IoT) devices are designed without a physical keyboard as they go tiny, but are almost all equipped with a wireless module for networks. In this work, we aim to enable a universal virtual keyboard using wireless signals, which wo...

Indoor moving direction and rotation angle measurements are crucial to many ubiquitous mobile computing applications. Most of the state-of-the-art approaches rely on inertial sensors, e.g., accelerometers, gyroscopes and magnetometers, which suffer from severe accumulative errors or accuracy degradation indoors. This paper presents an RF-based dire...

Existing indoor navigation solutions usually require pre-deployed comprehensive location services with precise indoor maps and, more importantly, all rely on dedicatedly installed or existing infrastructure. In this article, we present Pair-Navi, an infrastructure-free indoor navigation system that circumvents all these requirements by reusing a pr...

In the era of pervasively connected and sensed Internet of Things, many of our interactions with machines have been shifted from conventional computer keyboards and mouses to hand gestures and writing in the air. While gesture recognition and handwriting recognition have been well studied, many new methods are being investigated to enable pervasive...

RF imaging is a dream that has been pursued for years yet not achieved in the evolving wireless sensing. The existing solutions on WiFi bands, however, either require specialized hardware with large antenna arrays or suffer from poor resolution due to fundamental limits in bandwidth, the number of antennas, and the carrier frequency of 2.4GHz/5GHz...

Target material sensing in ubiquitous contexts plays an important role in various applications. Recently, a few wireless sensing systems have been proposed for material identification. Yet, prior work usually requires to capture the signals penetrating a target (with devices set up on both sides of the target) or to instrument the target (e.g., by...

The continuous development of 802.11ad technology provides new opportunities in wireless sensing. In this work, we propose ViMo, a calibration-free remote Vital sign Monitoring system that can detect stationary/non-stationary users and estimate the respiration rates (RRs) as well as heart rates (HRs) built upon a commercial 60GHz WiFi. The design o...

Despite decades of efforts, existing indoor location systems do not easily scale with low cost while maintaining high accuracy. We present EasiTrack, an indoor tracking system that achieves decimeter accuracy using a single commodity WiFi access point (AP) under non-line-of-sight (NLOS) conditions and can deploy at scale with almost zero cost. Easi...

Wireless detection of respiration rates is crucial for many applications. Most of the state-of-art solutions estimate breathing rates with the prior knowledge of crowd numbers as well as assuming the distinct breathing rates of different users, which is neither natural nor realistic. However, few of them can leverage the estimated breathing rates t...

Interests in monitoring and recognizing gait have surged significantly over the past decades. Traditional approaches rely on camera array, floor sensors, or wearables, none of which are suitable for continuous and ubiquitous everyday use. In this paper, we present GaitWay, the first system that monitors and recognizes an individual's gait speed thr...

Hidden screen-camera communication techniques emerge as a new paradigm that embeds data imperceptibly into regular videos while remaining unobtrusive to human viewers. Three key goals on imperceptible, high rate, and reliable communication are desirable but conflicting, and existing solutions usually made a trade-off among them. In this paper, we p...

Sensorless sensing using wireless signals has been rapidly conceptualized and developed recently. Among numerous applications of WiFi-based sensing, human presence detection acts as a primary and fundamental function to boost applications in practice. Many complicated approaches have been proposed to achieve high detection accuracy, but they freque...

Motion detection acts as a key component for a range of applications such as home security, occupancy and activity monitoring, retail analytics, etc. Most existing solutions, however, require special installation and calibration and suffer from frequent false alarms with very limited coverage. In this paper, we propose WiDetect, a highly accurate,...

Smartphone localization is essential to a wide range of applications in shopping malls, museums, office buildings, and other public places. Existing solutions relying on radio fingerprints and/or inertial sensors suffer from large location errors and considerable deployment efforts. We observe an opportunity in the recent trend of increasing number...

We present the model, design, and implementation of SMARS, the first practical Sleep Monitoring system that exploits Ambient Radio Signals to recognize sleep stages and assess sleep quality. This will enable a future smart home that monitors daily sleep in a ubiquitous and contactless manner. The key enabler underlying SMARS is a statistical model...

Wi-Fi based sensing systems, although sound as being deployed almost everywhere there is Wi-Fi, are still practically difficult to be used without explicit adaptation efforts to new data domains. Various pioneering approaches have been proposed to resolve this contradiction by either translating features between domains or generating domain-indepen...

Ubiquitous connectivity among objects is the future of the coming Internet of Things era. Technologies are competing fiercely to fulfill this goal, but none of them can fit into all application scenarios. However, efforts are still made to expand application ranges of certain technologies. Shortly after the adoption of its newest version, Bluetooth...

Monitoring physical assault is critical for the prevention of juvenile delinquency and promotion of school harmony. A large portion of assault events, particularly school violence among teenagers, usually happen at indoor secluded places. Pioneering approaches employ always-on-body sensors or cameras in the limited surveillance area, which are priv...

The recent availability of digital traces generated by cellphone calls has significantly increased the scientific understanding of human mobility. Until now, however, based on low time resolution measurements, previous works have ignored to study human mobility under various time scales due to sparse and irregular calls, particularly in the era of...

Displacement of human mobility (D2). A, The distribution of displacement P(Δr) under time scales δ ≈ 7.5min(n = 7,567,233), 30min(n = 7,006,878), 2hour(n = 3,498,286), 8hour(n = 1,347,365), 32hour(n = 508,482). B-J, The distribution of displacement P(Δr) and its best fits under time scales δ ≈ 7.5min, 15min(n = 6,991,657), 30min, 1hour(n = 6,457,26...

Displacement of human mobility (D1). A-D, The distribution of displacement P(Δr) and its best fits under time scales δ ≈ 15min(n = 8,258,692), 1hour(n = 5,071,176), 4hour(n = 2,226,450), 16hour(n = 702,218), respectively. The solid lines (green and blue) indicate a truncated power law and a log-normal distribution with best fitting parameters. The...

Gyration radius of human mobility (D1). A, The distribution of gyration radius rg under time scales δ ≥ 7.5min, 30min, 2hour, 8hour, 32hour(n = 142,619). We further divide all users into 3 groups (n = 5,001, 3,198 and 2,217) according to their final gyration radius rg(T) during the whole observation period T. B-D, show the convergence speeds of rg...

KSW test for Fig 3 and S1 Fig. A-I, The KSW test result of the best power law fitting for the tail distribution of displacement under time scales δ ≈ 7.5min, 15min, 30min, 1hour, 2hour, 4hour, 8hour, 16hour and 32hour. The fits under all time scales passed the KSW test. (PDF)

Time related statistics of human mobility (D2). A, The distribution of waiting time Δt under time scales δmin(n = 66,821,244) and δ ≥ 7.5min(n = 38,617,952), 30min(n = 25,859,924), 2hour(n = 16,329,587), 8hour(n = 9,132,801) and 32hour(n = 3,882,266). B, The distribution of moving speed under time scales δ ≈ 7.5min(n = 5,249,717), 30min(n = 7,281,4...

Columns of Mobile Flow Records (MFRs). Detailed description for some key columns of MFRs about human behavior. (PDF)

KS test for Fig 3 and S1 Fig. A-I, The KS test result of the best power law fitting for the tail distribution of displacement under time scales δ ≈ 7.5min, 15min, 30min, 1hour, 2hour, 4hour, 8hour, 16hour and 32hour. The fits under all time scales passed the KS test except for 16hour due to the roughness at Δr ≈ 25km. (PDF)

Hidden screen-camera communication techniques emerge as a new paradigm that embeds data imperceptibly into regular videos while remaining unobtrusive to human viewers. Three key goals on imperceptible, high rate, and reliable communication are desirable but conflicting, and existing solutions usually made a trade-off among them. In this paper, we p...

Location acts as the most important information that bridges the physical world and the cyber space and thus a key enabler for Cyber-Physical Systems (CPS). In this chapter, we first introduce why indoor localization technology is particularly needed and then review the state-of-the-art approaches. In the end, we outline the book structure.

Current WiFi fingerprinting suffers from a pivotal problem of RSS fluctuations caused by unpredictable environmental dynamics. The RSS variations lead to severe spatial ambiguity and temporal instability in RSS fingerprinting, both impairing the location accuracy. In this chapter, we introduce fingerprint spatial gradient (FSG), a more stable and d...

Most radio-based indoor localization solutions require a process of site survey, in which radio signatures of an interested area are annotated with their real recorded locations. Site survey involves intensive costs on manpower and time, limiting the applicable buildings of wireless localization worldwide. In this chapter, we investigate, under a c...

A primary concern for WiFi fingerprint-based technologies to be fully practical is to combat harsh indoor environmental dynamics, especially for long-term deployment. Despite numerous research, the problem of radio map adaptation has not been sufficiently studied and remains open. In this chapter, we propose AcMu, an automatic and continuous radio...

Pioneer efforts to improve WiFi-based localization have resorted to motion-assisted or peer-assisted localization. They neither work in real time nor work without the help of peer users, which introduces extra costs and constraints, and thus degrades their practicality. To get over these limitations, an image-assisted localization system, named Arg...

Floor plan plays an essential role in many indoor pervasive and mobile applications, but its collection and on-site calibration are inconvenient and usually prohibitively costly for map providers. In this chapter, we explore the possibility of automatically generating floor plans. Based on the thoughts of human-centric sensing and crowdsourcing, th...

In this chapter, we summarize this book and, more importantly, present a vision on future directions. The research on wireless indoor localization continues growing and we foresee a prime time of indoor localization in the near future.

This chapter presents the preliminary background on mobile crowdsourcing and inertial sensing, which together have opened the new possibilities for wireless indoor localization, after more than a decade of development. In particular, we first introduce the basic concept of mobile crowdsourcing. Then we study how to measure human mobility using smar...

In this chapter, we reveal crucial observations, through real-world experience, that act as the root causes of localization errors, yet are surprisingly overlooked or not adequately addressed in previous works. Specifically, we recognize Access Points’ diverse discrimination for fingerprinting a specific location, observe the RSS inconsistency caus...

Most of existing indoor navigation systems work in a client/server manner, which needs to deploy comprehensive localization services together with precise indoor maps for a priori. In this chapter, we design and realize a Peer-to-Peer navigation system, named ppNav, on smartphones, which enables the fast-to-deploy navigation services, avoiding the...

This paper presents Widar2.0, the first WiFi-based system that enables passive human localization and tracking using a single link on commodity off-the-shelf devices. Previous works based on either specialized or commercial hardware all require multiple links, preventing their wide adoption in scenarios like homes where typically only one single AP...

Device-free passive detection is an emerging technology to detect whether there exist any moving entities in the areas of interest without attaching any device to them. It is an essential primitive for a broad range of applications including intrusion detection for safety precautions, patient monitoring in hospitals, child and elder care at home, a...

This book provides a comprehensive and in-depth understanding of wireless indoor localization for ubiquitous applications. The past decade has witnessed a flourishing of WiFi-based indoor localization, which has become one of the most popular localization solutions and has attracted considerable attention from both the academic and industrial commu...

Modern mobile devices are equipped with multiple antennas, which brings various wireless sensing applications such as accurate localization, contactless human detection and wireless human-device interaction. A key enabler for these applications is phased array signal processing, especially Angle of Arrival (AoA) estimation. However, accurate AoA es...

The proliferation of mobile computing has prompted WiFi-based indoor localization to be one of the most attractive and promising techniques for ubiquitous applications. A primary concern for these technologies to be fully practical is to combat harsh indoor environmental dynamics, especially for long-term deployment. Despite numerous research on Wi...

Various pioneering approaches have been proposed for Wi-Fi-based sensing, which usually employ learning-based techniques to seek appropriate statistical features, yet do not support precise tracking without prior training. Thus to advance passive sensing, the ability to track fine-grained human mobility information acts as a key enabler. In this pa...

Among numerous indoor localization systems proposed during the past decades, WiFi fingerprint-based localization has been one of the most attractive solutions, which is known to be free of extra infrastructure and specialized hardware. However, current WiFi fingerprinting suffers from a pivotal problem of RSS fluctuations caused by unpredictable en...

Monitoring school violence is critical for the prevention of juvenile delinquency and promotion of social harmony. Pioneering approaches employ always-on-body sensors or cameras with limited surveillance area, which cannot provide ubiquitous violence monitoring. In this paper, we present Wi-Dog, a non-invasive physical violence monitoring scheme ba...

In-air interaction acts as a key enabler for ambient intelligence and augmented reality. As an increasing popular example, exergames, and the alike gesture recognition applications, have attracted extensive research in designing accurate, pervasive and low-cost user interfaces. Recent advances in wireless sensing show promise for a ubiquitous gestu...

Most of existing indoor navigation systems work in a client/server manner, which needs to deploy comprehensive localization services together with precise indoor maps a prior. In this paper, we design and realize a Peer-to-Peer navigation system, named ppNav, on smartphones, which enables the fast-to-deploy navigation services, avoiding the require...

Although WiFi fingerprint-based indoor localization is attractive, its accuracy remains a primary challenge especially in mobile environments. Existing approaches either appeal to physical layer information or rely on extra wireless signals for high accuracy. In this paper, we revisit the RSS fingerprint-based localization scheme and reveal crucial...

Pioneer approaches for WiFi-based sensing usually employ learning-based techniques to seek appropriate statistical features, but do not support precise tracking without prior training. Thus to advance passive sensing, the ability to track fine-grained human mobility information acts as a key enabler. In this paper, we proposed Widar, a WiFi-based t...

Non-invasive human sensing based on radio signals has attracted numerous research interests and fostered a broad range of innovative applications of localization, gesture recognition, smart health-care, etc, for which a primary primitive is to detect human presence. Previous works have studied to detect moving humans via signal variations caused by...

Wireless LANs, particularly WiFi, have been pervasively deployed and have fostered myriad wireless communication services and ubiquitous computing applications. A primary concern in designing these applications is to combat harsh indoor propagation environments, particularly Non-Line-Of-Sight (NLOS) propagation. The ability to identify the existenc...

Indoor localization on smartphones is an enabler for a number of ubiquitous and mobile computing applications attracting worldwide attentions. Many location-based services rely on WiFi fingerprinting approaches to achieve a reasonable accuracy. However, there is still room for improvement due to the prevalent-existing errors (e.g., 8∼12 m). In this...

Wireless-based device-free human sensing has raised increasing research interest and stimulated a range of novel location-based services and human-computer interaction applications for recreation, asset security and elderly care. A primary functionality of these applications is to first detect the presence of humans before extracting higher-level c...

WiFi technology has fostered numerous mobile computing applications, such as adaptive communication, fine-grained localization, gesture recognition, etc., which often achieve better performance or rely on the availability of Line-Of-Sight (LOS) signal propagation. Thus the awareness of LOS and NonLine-Of-Sight (NLOS) plays as a key enabler for them...