Chenshu Wu

Chenshu Wu
University of Maryland, College Park | UMD, UMCP, University of Maryland College Park · Department of Electrical & Computer Engineering

Doctor of Philosophy

About

109
Publications
19,943
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
4,295
Citations

Publications

Publications (109)
Conference Paper
Full-text available
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...
Preprint
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...
Article
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,...
Article
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...
Article
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...
Article
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...
Article
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...
Preprint
Full-text available
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....
Article
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...
Article
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...
Article
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...
Article
Full-text available
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...
Article
Full-text available
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...
Article
Full-text available
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...
Article
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...
Article
Full-text available
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...
Article
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...
Article
Full-text available
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...
Article
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...
Article
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...
Article
Full-text available
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,...
Article
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...
Article
Full-text available
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...
Conference Paper
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...
Article
Full-text available
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...
Article
Full-text available
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...
Article
Full-text available
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...
Data
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...
Data
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...
Data
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...
Data
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)
Data
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...
Data
Columns of Mobile Flow Records (MFRs). Detailed description for some key columns of MFRs about human behavior. (PDF)
Data
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)
Conference Paper
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...
Chapter
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.
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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...
Chapter
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.
Chapter
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...
Chapter
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...
Chapter
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...
Conference Paper
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...
Article
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...
Book
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...
Article
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...
Article
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...
Conference Paper
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...
Article
Full-text available
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...
Conference Paper
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...
Conference Paper
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...
Article
Full-text available
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...