Yingying (Jennifer) Chen  
Fellow of National Academy of Inventors (NAI)
ACM Fellow, IEEE Fellow, AAIA Fellow
ACM Distinguished Scientist
Peter D. Cherasia Faculty Scholar
Department Chair, Electrical and Computer Engineering
 

Professor, Electrical and Computer Engineering
Associate Director, Wireless Information Network Laboratory (WINLAB)
Director, Data Analysis and Information Security (DAISY) Lab

Rutgers University - New Brunswick
Email: yingche at scarletmail.rutgers.edu

 

ECE Department
Office: Core 506
Phone: 848-445-9151
Address:
96 Frelinghuysen Rd
Piscataway, NJ 08854
WINLAB
Office: C-109
Phone: 848-932-0948
Address:
671 Route 1
North Brunswick, NJ 08902

News| Media Coverage| Teaching| Research| Publications
Books, Journals, & Magazine Articles Conference Papers
| DAISY Lab| Professional Activities| Collaborators & Students| Youtube Channel | Genealogy

Introduction

Yingying (Jennifer) Chen is the Department Chair and Professor of Electrical and Computer Engineering and the Peter D. Cherasia Faculty Scholar at Rutgers University. She is the Associate Director of the Wireless Information Network Laboratory (WINLAB). She also leads the Data Analysis and Information Security Laboratory (DAISY). She is a National Academy of Inventors (NAI) Fellow, an Institute of Electrical and Electronics Engineers (IEEE) Fellow, and an Asia-Pacific Artificial Intelligence Association (AAIA) Fellow. She is also named as an ACM Distinguished Scientist. Her background is a combination of Computer Science, Computer Engineering and Physics. She has co-authored five books: (1) Network Security Empowered by Artificial Intelligence (Springer 2024), (2) Mobile Technologies for Smart Healthcare System Design (Springer 2024), (3) Sensing Vehicle Conditions for Detecting Driving Behaviors (Springer 2018), (4) Pervasive Wireless Environments: Detecting and Localizing User Spoofing (Springer 2014), and (5) Securing Emerging Wireless Systems (Springer 2009), and published 300+ journal articles and referred conference papers. She obtained many patents with multiple of them being licensed and commercialized by industry. Her research has been reported in numerous media outlets including the Wall Street Journal, MIT Technology Review, CNN, Fox News Channel, IEEE Spectrum, Fortune, Inside Science, NPR, Tonight Show with Jay Leno and Voice of America.

Her research interests include: Applied Machine Learning in Mobile Computing and Sensing, Internet of Things (IoT), Security in AI/ML Systems, Smart Healthcare, and Deep Learning on Mobile Systems.

She is one of the pioneers to use machine learning techniques and data mining methods to classify and model the healthcare, security, system, network related problems since its infancy. Besides the algorithm development, her work has a strong emphasis on system implementation and validation in real-world scenarios. Her interdisciplinary research and education have been sponsored by multiple grants from various funding agencies:

nsf aro ardec dod afrl google

She is serving and served on prestigious journal editorial boards including IEEE/ACM Transactions on Networking (IEEE/ACM ToN), IEEE Transactions on Mobile Computing (IEEE TMC), IEEE Transactions on Wireless Communications (IEEE TWireless), ACM Transactions on Privacy and Security (ACM TOPS), IEEE Network Magazine, EURASIP Journal on Information Security, and International Journal of Parallel, Emergent and Distributes Systems (IJPEDS).

She is actively involving in community services. She is serving and served as Technical Program Co-chair of IEEE ICDCS 2024, IEEE INFOCOM 2022, IEEE MASS 2022, ACM MobiCom 2018, ACM WiSec 2019, IEEE CNS 2016, IEEE MASS 2013. She also serves as General Co-chair of IEEE DySPAN 2019 and ACM MobiCom 2016. All of these are top-tier conferences in wireless network, mobile computing, and network security. She regularly serves on the technical program committees (TPC) of ACM and IEEE conferences including ACM MobiCom, ACM MobiSys, ACM MobiHoc, ACM SenSys, ACM CCS, ACM ACSAC, ACM AsiaCCS, IEEE INFOCOM, IEEE ICDCS, IEEE CNS, IEEE MASS, IEEE SECON, IEEE ICC, IEEE Globecom.

Previously, she was a tenured professor in the Department of Electrical and Computer Engineering (ECE) at Stevens Institute of Technology. She received early promotion twice at Stevens: from Assistant to Associate Professor, and from Associate to Full Professor. She was also the Graduate Program Directors of Information and Data Engineering (IDE) and Networked Information Systems (NIS) in ECE Department at Stevens. She was a visiting professor at Princeton University. Prior to joining Stevens, she was with Alcatel - Lucent (now Nokia) at Holmdel & Murray Hill, New Jersey. Her work has involved a combination of research and development of new technologies and real systems, ranging from Network Management Systems for Lucent flagship optical and data products to voice/data integrated services.

Latest Update

Our community-based edge computing and sensing testbed is available here, a multi-million dollar project supported by the NSF CCRI Program. It provides practical multi-modal sensing experimental environments and shares various datasets and machine-learning-based algorithms.


Looking for self-motivated Ph.D. students in Applied Machine Learning, Mobile Sensing and Security, and Deep Learning in Mobile Systems.


Dr. Chen is the editor of the column, "Women in Networks", in IEEE Network Magazine. Please contact her if you would like to be featured in this column.


Honors & Awards

Editorial Boards

Associate Editor-in-Chief

Current: Associate Editor

Past: Associate Editor

Guest Editor

Research Grants:

Current Research Areas

AR/VR Security

Augmented Reality/Virtual Reality (AR/VR) technologies have been rapidly gaining popularity throughout the last decade, owing to their capability of creating an immersive cyber environment for all users, regardless of physical constraints. However, such a cyber environment brings risks to user's privacy and security. AR/VR device collects not only digital information of the user from network, but also their human physical characteristics from embedded sensors. This project aims to explore stealthily eavesdrop attacks via AR/VR sensor data and investigates to what extent will such information leakage expose the user’s privacy.

Snooping typed keys on virtual keyboards.

IEEE Symposium on Security and Privacy (IEEE S&P 2023)

Privacy Leakage via Unrestricted Motion-Position Sensors in the Age of Virtual Reality: A Study of Snooping Typed Input on Virtual Keyboards

We conduct a comprehensive study to assess the trustworthiness of the embedded sensors on VR, which embed various forms of sensitive data that may put users’ privacy at risk. We validate the vulnerability through developing malware programs and malicious websites and specifically explore to what extent it exposes the user’s information in the context of keystroke snooping.

ACM MobiCom 2021

Face-Mic: Inferring Live Speech and Speaker Identity via Subtle Facial Dynamics Captured by AR/VR Motion Sensors

We design an eavesdropping attack, Face-Mic, which leverages speech-associated subtle facial dynamics captured by zero-permission motion sensors in AR/VR headsets to infer highly sensitive information of live human speech, including speaker gender, identity, and speech content.


Adversarial Machine Learning

Voice-controllable systems have been widely integrated into smart and IoT devices (e.g., Google Home, Amazon Echo) and have provided great convenience. These systems rely heavily on learning-based techniques (i.e., Machine Learning, Deep Learning). However, recent studies show that they are vulnerable to well-crafted imperceptible audio perturbations which causes misclassification. In this project, we aim to develop audio adversary attacks that are: 1) applicable to streaming audio input (e.g., such as live human speech); 2) ignoring physical effect during over-the-air propagation; 3) able to be launched in real-time scenario.

Adversarial Attack to Speech Recognition System

ACM SenSys 2022

Push the Limit of Adversarial Example Attack on Speaker Recognition in Physical Domain

We design a physical audio adversarial attack, PhyTalker. Our attack generates real-time adversarial perturbations that can impact live-streaming audio samples. Our idea is to generate a sub-phoneme level perturbation dictionary to decouple the perturbation optimization and injection. We further introduce channel augmentation to compensate device and environmental distortions, as well as model ensemble to improve transferability.

ACM MobiCom 2022

Audio-domain Position-independent Backdoor Attack via Subsecond Triggers

In this project, we explore a stealthy training-phase (backdoor) attack in audio domain, targeting deep learning models in speech and speaker recognition systems. Particularly, we design synchronization-free and unnoticeable triggers mimicking environmental sounds are injected into any part of audio samples to cause misclassification of deep learning models. We further demonstrate that in practical scenarios, where the adversary replays the trigger over-the-air to launch the attack.

ECCV 2022

RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN

In this project, we propose and develop a Robust and Imperceptible Backdoor Attack against Compact DNN models (RIBAC). By performing systematic analysis and exploration on the important design knobs of model compression, we propose a framework that can dynamically learn the proper trigger patterns, model parameters and pruning masks. Our attack can achieve high trigger stealthiness, high attack success rate and high model efficiency simultaneously.

ACM CCS 2021

Robust Detection of Machine-induced Audio Attacks in Intelligent Audio Systems with Microphone Array

We build a holistic defense system for detecting machine-induced audio attacks that leverages multi-channel microphone arrays readily available on modern voice assistant devices, based on the spatial information extracted from the multi-channel audio.

AAAI 2021

Enabling Fast and Universal Audio Adversarial Attack Using Generative Model

We design a fast audio adversarial perturbation generator, which enables fast audio adversarial perturbation generation, and a universal audio adversarial perturbation generator that crafts input-agnostic adversarial perturbations.

ACM CCS 2020

AdvPulse: Universal, Synchronization-free, and Targeted Audio Adversarial Attacks via Subsecond Perturbations

We design AdvPulse, a practical audio adversarial attack against voice assistant systems. We generate input-agnostic universal sub-second audio adversarial perturbations that can be injected anywhere in the streaming audio input (e.g., live human speeches) for the attack

ICASSP 2020

Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systems

We propose the first real-time, universal, and robust adversarial attack against the state-of-the-art deep neural network (DNN) based speaker recognition system (X-Vector), through dynamically optimizing the perturbation based on speeches of different lengths and content.

HotMobile 2020

Practical Adversarial Attacks Against Speaker Recognition Systems

We study the vulnerability of speaker recognition systems by designing over-the-air adversarial attacks against speaker recognition systems, by leveraging room impulse response during the perturbation optimization.


Exploring Speech Privacy Attacks and Defenses

Voice-user interface (VUI) has been widely adopted in various mobile and IoT devices, enabling convenient interactions between humans and the devices. However, the frequent emerging usage of VUI could result in severe privacy leakage if malicious actors can listen onto this communication medium. We reveal speech privacy attacks that exploit zero-permission motion sensors (accelerometer and gyroscope) on smartphones, IoT devices, and AR/VR headsets, which could disclose people's gender, speaker, and speech content. Furthermore, we find that the phonatory vibrations picked up by the motion sensors can help to uniquely identify a user via voice signatures in the vibration domain, thereby preventing various acoustic attacks.

Leveraging built-in motion sensors to eavesdrop on speech generated by the built-in speaker.

ACM MobiCom 2021

Face-Mic: Inferring Live Speech and Speaker Identity via Subtle Facial Dynamics Captured by AR/VR Motion Sensors

We design an eavesdropping attack, Face-Mic, which leverages speech-associated subtle facial dynamics captured by zero-permission motion sensors in AR/VR headsets to infer highly sensitive information of live human speech, including speaker gender, identity, and speech content.

ACM WiSec 2021

Spearphone: A Lightweight Speech Privacy Exploit via Accelerometer-Sensed Reverberations from Smartphone Loudspeakers

We build a speech privacy attack that exploits speech reverberations from a smartphone’s inbuilt loudspeaker captured via zero-permission motion sensors. We demonstrate that speech reverberations from inbuilt loudspeakers, at an appropriate loudness, can impact the accelerometer, leaking sensitive speaker and speech information.

ACM AsiaCCS 2021

HVAC: Evading Classifier-based Defenses in Hidden Voice Attacks

Hidden Voice Attack uses the human-machine perception gap to generate obfuscated voice commands that are unintelligible to human listeners. We design an advanced hybrid Hidden Voice Attack, HVAC, which combines live human speech and hidden voice commands to bypass existing defense mechanisms against hidden voice attacks.

ACM AsiaCCS 2021

EchoVib: Exploring Voice Authentication via Unique Non-Linear Vibrations of Short Replayed Speech

We suggest a paradigm shift from the traditional voice authentication systems operating in the audio domain but susceptible to speech synthesis attacks. We leverage a motion sensor’s capability to pick up phonatory vibrations, that can help to uniquely identify a user via voice signatures in the vibration domain.

ACSAC 2019

Defeating Hidden Audio Channel Attacks on Voice Assistants via Audio-Induced Surface Vibrations

We employ low-cost motion sensors, in a novel way, to detect hidden voice attacks. We examine the unique audio signatures of the issued voice commands in the vibration domain, and show that the signatures of normal commands vs. synthetic hidden voice commands are distinctive, leading to the detection of the attacks.


Mobile Security

With the increasing prevalence of mobile and IoT devices (e.g., smartphones, tablets, smart-home appliances, and voice assistant devices), massive private and sensitive information are stored on these devices. To prevent unauthorized access on these devices, we combine various sensing modalities (e.g., physical vibrations, acoustic signals, visible light, and WiFi/mmWave) with machine learning/deep learning techniques to authenticate users.

Finger-input Authentication via Physical Vibration

Vibration-based Authentication
ACM MobiCom 2020

TouchPass: Towards Behavior-irrelevant on-touch User Authentication on Smartphones Leveraging Vibrations

We design a behavior-irrelevant on-touch user authentication system that leverages active vibration signals on smartphones to extract only physical characters of touching fingers for user identification.

ACSAC 2020

WearID: Low-Effort Wearable-Assisted Authentication of Voice Commands via Cross-Domain Comparison without Training

We develop WearID, a training-free voice authentication system leveraging the cross-domain speech similarity between the audio domain (recorded by voice assistant devices' microphone) and the vibration domain (recorded by wearables' accelerometer).

ACM CCS 2017

VibWrite: Towards Finger-input Authentication on Ubiquitous Surfaces via Physical Vibration

We design VibWrite that extends finger-input authentication beyond touch screens to any solid surface through a touch sensing technique based on vibration signals.

IEEE SECON 2017

VibSense: Sensing Touches on Ubiquitous Surfaces through Vibration

We design VibSense that pushes the limits of vibration-based sensing to determine the location of a touch on extended surface areas as well as identify the object touching the surface leveraging a single sensor, supporting a broad array of applications using only a single sensor.

Acoustic-based Authentication
ACM ASIACCS 2020

EchoLock: Towards Low-effort Mobile User Identification Leveraging Structure-borne Echos

We design EchoLock, a low-effort identification scheme that validates the user by sensing hand geometry via commodity microphones and speakers.

ACM UbiComp 2020

VocalLock: Sensing Vocal Tract for Passphrase-Independent User Authentication Leveraging Acoustic Signals on Smartphones

We develop a user authentication system, VocalLock, which senses the whole vocal tract during speaking to identify different individuals in a passphrase-independent manner on smartphones leveraging acoustic signals.

IEEE INFOCOM 2018

LipPass: Lip Reading-based User Authentication on Smartphones Leveraging Acoustic Signals

We propose a lip reading-based user authentication system, LipP ass, which extracts unique behavioral characteristics of users’ speaking lips leveraging build-in audio devices on smartphones for user authentication.

ACM CCS 2016

VoiceLive: A Phoneme Localization based Liveness Detection for Voice Authentication on Smartphones

We develop VoiceLive, a practical liveness detection system for voice authentication on smartphones, which detects a live user by leveraging the user’s unique vocal system and the stereo recording of smartphones.

WiFi/mmWave-based Authentication
ACM MobiHoc 2021

MultiAuth: Enable Multi-User Authentication with Single Commodity WiFi Device

We develop a multi-user authentication system that can authenticate multiple users with a single commodity WiFi device, through profiling multipath components from multiple users.

IEEE INFOCOM 2020

MU-ID: Multi-user Identification Through Gaits Using Millimeter Wave

We develop MU-ID, a gait-based multi-user identification system leveraging a single commercial off-the-shelf millimeter-wave radar.

IEEE INFOCOM 2020

Continuous User Verification via Respiratory Biometrics

We develop a continuous user verification system, which re-uses the widely deployed WiFi infrastructure to capture the unique physiological characteristics rooted in user’s respiratory motions.

ACM MobiHoc 2019

FingerPass: Finger Gesture-based Continuous User Authentication for Smart Homes Using Commodity WiFi

We design FingerPass which leverages channel state information of surrounding WiFi signals to continuously authenticate users through finger gestures in smart homes.

ACM MobiHoc 2017

Smart User Authentication through Actuation of Daily Activities Leveraging WiFi-enabled IoT

We explore using WiFi signals generated by IoT devices to capture unique human physiological and behavioral characteristics inherited from human daily activities for device-free user authentication.

Camera & PPG based Authentication
IEEE INFOCOM 2020

TrueHeart: Continuous Authentication on Wrist-worn Wearables Using PPG-based Biometrics

We devise a low-cost system exploiting a user’s pulsatile signals from the photoplethysmography (PPG) sensor in commercial wrist-worn wearables for continuous authentication, which is low-effort and practical.

IEEE INFOCOM 2020

LiveScreen: Video Chat Liveness Detection Leveraging Skin Reflection

We develop a novel video chat liveness detection system, LiveScreen, which can track the weak light changes reflected off the skin of a human face leveraging chromatic eigenspace differences.

ACM MobiSys 2019

CardioCam: Leveraging Camera on Mobile Devices to Verify Users While Their Heart is Pumping

We design, CardioCam, a low-cost, general, hard-to-forge user verification system leveraging the unique cardiac biometrics extracted from the readily available built-in cameras in mobile and IoT devices.


Wi-Fi Sensing and IoT

Contactless sensing has become increasingly important and has the potential to support a broad array of applications including communication, suspicious object detection, smart healthcare, and human dynamic monitoring. Traditional approaches involve wearable sensors and specialized hardware installations. To support emerging smart applications, We study using acoustic, WiFi, and vibration signals for contactless sensing.

BatComm (ACM SenSys 2020): RFID-based human body movements tracking

IEEE INFOCOM 2023

Universal Targeted Adversarial Attacks Against mmWave-based Human Activity Recognition

Vulnerability of human activity recognition (HAR) systems based on millimeter wave (mmWave) technology has been revealed in recent years. However, existing efforts in HAR adversarial attacks only focus on untargeted attacks. In this project, we propose the first targeted adversarial attacks against mmWave-based HAR through designed universal perturbation with.

USENIX Security 2023

Person Re-identification in 3D Space: A WiFi Vision-based Approach

Person re-identification (Re-ID) has become increasingly important as it supports a wide range of security applications. Traditional person Re-ID mainly relies on optical camera-based systems, which incur several limitations due to the changes in the appearance of people, occlusions, and human poses. In this work, we propose a WiFi vision-based system, 3D-ID, for person Re-ID in 3D space. Our system leverages the advances of WiFi and deep learning to help WiFi devices to discover, identify, and recognize people. In particular, we leverage multiple antennas on next-generation WiFi devices and 2D AoA estimation of the signal reflections to enable WiFi to visualize a person in the physical environment.

ACM Sensys 2022

Solving the WiFi Sensing Dilemma in Reality Leveraging Conformal Prediction

With the wide deployment of smart environments and IoT devices, WiFi sensing has demonstrated its great convenience and contactless sensing capabilities in supporting a broad array of applications. However, designing a ubiquitous WiFi sensing system for heterogeneous scenarios in practice is still a big dilemma as the system performs poorly when the testing data is significantly different from the training data caused by domain variations. In this work, we conduct a comprehensive study on the domain variation problem to make WiFi sensing robust and accurate in reality.

ACM SenSys 2020

BatComm: Enabling Inaudible Acoustic Communication with High-throughput for Mobile Devices

We redesign acoustic communication mechanism to push the boundary of potential throughput (throughput rates 12X higher than contemporary state-of-the-art methods) while keeping the inaudibility.

IEEE MASS 2020

Towards Environment-independent Behavior-based User Authentication Using WiFi

In this project, we design a device-free user authentication via daily human behavioral patterns captured by existing WiFi infrastructures. To disentangle the behavioral biometrics for practical environment-independent user authentication, we propose an end-to-end deep-learning based approach with domain adaptation techniques to remove the environmentand location-specific information contained in the collected WiFi measurements.

IEEE CNS 2018

Towards In-baggage Suspicious Object Detection Using Commodity WiFi

We develop a system that utilize thes fine-grained channel state information from off-the-shelf WiFi to detect suspicious objects that are suspected to be dangerous (i.e., defined as any metal and liquid object) without penetrating into the user’s privacy through physically opening the baggage

ACM UbiComp 2018

RF-Kinect: A Wearable RFID-based Approach Towards 3D Body Movement Tracking

We design RF-Kinect, a training-free system which tracks the body movement in 3D space by analyzing the phase information of wearable RFID tags attached on the limb.

IEEE INFOCOM 2018

Multi-Touch in the Air: Device-Free Finger Tracking and Gesture Recognition via COTS RFID

We develop RF-finger, a device-free system based on Commercial-Off-The-Shelf (COTS) RFID, which0 leverages a tag array on a letter-size paper to sense the finegrained finger movements performed in front of the paper.

ACM SenSys 2017

WiFi-Enabled Smart Human Dynamics Monitoring

We study using existing WiFi infrastructures to provide a fine-grained and comprehensive view of human dynamics through participant number estimation, human density estimation, and walking speed and direction derivation.

ACM MobiCom 2014

E-eyes: Device-free Location-oriented Activity Identification Using Fine-grained WiFi Signatures

Activity monitoring in home environments has become increasingly important and has the potential to support a broad array of applications including elder care, well-being management, and latchkey child safety. In this project, we demonstrate the first device-free location-oriented activity identification at home through the use of existing WiFi access points and WiFi devices (e.g., desktops, thermostats, refrigerators, smartTVs, laptops).


Smart Healthcare and Wellbeing Monitoring

Mobile devices and WiFi have become increasingly popular and are gradually woven into our social lives. Smartphones equipped with powerful embedded sensors (e.g., motion sensors, microphones, PPG) can be used to monitor multiple dimensions of human behaviors including physical, mental, and social behaviors of wellbeing. The collected sensing data can thus be comprehensive enough to be mined not only for the understanding of human behaviors or daily life activities but also for supporting a broad range of mobile healthcare applications. We are designing systems based on commodity WiFi, acoustic signals, wearable/PPG, and RFID, that can be easily integrated into current mobile devices to perform fine-grained healthcare monitoring.

Fine-grained Sleep Monitoring Leveraging Home Wi-Fi Networks

WiFi-based Approaches
ACM SenSys 2022

Solving the WiFi Sensing Dilemma in Reality Leveraging Conformal Prediction

We conduct a comprehensive study on the domain variation problem to enable robust WiFi sensing (activity recognition, gesture recognition, and user identification) under practical factors. We develop a novel cross-domain conformal prediction framework, which examines the conformity (similarity) of new testing samples to training data for robust prediction.

HealthyIoT 2019

WiFi-enabled Automatic Eating Moment Monitoring Using Smartphones

We design a WiFi-based eating moment monitoring system that can identify fine-grained food intake gestures (e.g., eating with fork, knife, spoon) and the corresponding eating episode.

ACM UbiComp 2019

Device-free Personalized Fitness Assistant Using WiFi

We develop a device-free fitness assistant system using existing WiFi infrastructure, which can provide personalized fitness assistance by differentiating individuals, automatically recording fine-grained workout statistics, and assessing workout dynamics.

ACM MobiHoc 2015

Tracking Vital Signs During Sleep Leveraging Off-the-shelf WiFi

We design a low-cost system leverages the Channel State Information (CSI) extracted from WiFi signals on mobile devices to monitor vital signs and perform fine-grained sleep monitoring in home environments.

ACM MobiCom 2014

E-eyes: Device-free Location-oriented Activity Identification Using Fine-grained WiFi Signatures

We investigate device-free location-oriented activity identification at home through the use of existing WiFi access points and WiFi devices (e.g., desktops, thermostats, refrigerators, smartTVs, laptops).

Acoustic-based Approaches
ACM MobiSys 2019

BreathListener: Fine-grained Breathing Monitoring in Driving Environments Utilizing Acoustic Signals

We develop a fine-grained breathing monitoring system, BreathListener, which leverages audio devices on smartphones to estimate the fine-grained breathing waveform in driving environments.

Wearable/PPG-based Approaches
IEEE INFOCOM 2018

PPG-based Finger-level Gesture Recognition Leveraging Wearables

We demonstrate that it is feasible to leverage the PPG sensors in wrist-worn wearable devices to enable finger-level gesture recognition, which could facilitate many emerging human-computer interactions (e.g., sign-language interpretation and virtual reality).

IEEE INFOCOM 2017

FitCoach: Virtual Fitness Coach Empowered by Wearable Mobile Devices

We design FitCoach, a virtual fitness coach leveraging the motion sensors on users’ wearable mobile devices to assess dynamic postures (movement patterns & positions) in workouts.

RFID-based Approaches
ACM UbiComp 2018

RF-ECG: Heart Rate Variability Assessment Based on COTS RFID Tag Array

We develop RF-ECG based on Commercial-Off-The-Shelf (COTS) RFID, a wireless approach to sense the human heartbeat through an RFID tag array attached on the chest area in the clothes.


Deep Learning on Mobile/Edge Devices (TinyLearning)

Deep learning models have achieved remarkable successes in a broad range of applications due to their performance scalability, and self adaptiveness. However, state-of-art mobile and edge devices still have limited memory size and computational capacity, which prevent them from running these models. We exploring using pruning, distributed learning, and optimization algorithms to improve the efficiency of deep learning, making powerful and large deep learning models that could be deployed on resources-limited mobile devices.

Use case scenarios for secure distributed learning in the mobile IoT

IJCNN 2021

MIXP: Efficient Deep Neural Networks Pruning for Further FLOPs Compression via Neuron Bond

We develop a novel mixture pruning mechanism, MIXP, which can effectively reduce the computational cost of CNNs while maintaining a high weight compression ratio and model accuracy.

IEEE SECON 2021

Secure Coded Computation for Efficient Distributed Learning in Mobile IoT

We investigate the performance of existing distribution schemes in terms of operational complexity and security and design scalable optimization algorithms to handle the unique constraints of mobile IoT.


Road Safty System

Connected vehicle technologies offer an unprecedented opportunity to transform the safety, efficiency, comfort, and economics of road travel. We study using mobile devices and existing car infrastructure to determine the driver inputs, road environments, and driver phone usage behaviors, which greatly facilitate advanced driver assistance and automated driving.

Scaling Road Data Acquisition for Dependable Self-Driving

Sensing Driver Phone Use to Reduce Driver Distraction Caused by Cell Phone Usage

ACM MobiSys 2017

BigRoad: Scaling Massive Road Data Acquisition for Dependable Self-Driving

We develop a low-cost yet reliable solution, BigRoad, that can derive internal driver inputs and external perceptions of road environments using a smartphone and an IMU mounted in a vehicle.

ACM MobiSys 2013

Sensing Vehicle Dynamics for Determining Driver Phone Use

We design a driver phone use detection based on readings of embedded sensors in smartphones, by differentiating centripetal acceleration due to vehicle dynamics.

ACM MobiCom 2011

Detecting Driver Phone Use Leveraging Car Speakers

We address the fundamental problem of distinguishing between a driver and passenger using a mobile phone, by leveraging the existing car stereo infrastructure (the speakers and Bluetooth network).


Selected Publications:

Books:

Yingying Chen, Wenyuan Xu, Wade Trappe, Yanyong Zhang,
Network Security Empowered by Artificial Intelligence,
ISBN: 978-3-319-89769-1, Springer, 2024.
   
Xiaonan Guo, Yan Wang, Jerry Cheng, Yingying Chen,
Mobile Technologies for Smart Healthcare System Design,
ISBN: 978-3-031-57344-6, Springer, 2024.
Yingying Chen, Wenyuan Xu, Wade Trappe, Yanyong Zhang,
Network Security Empowered by Artificial Intelligence,
ISBN: 978-3-319-89769-1, Springer, 2024.
   
Jiadi Yu, Yingying Chen, and Xiangyu Xu,
Sensing Vehicle Conditions for Detecting Driving Behaviors,
ISBN: 978-3-319-89769-1, Springer, 2018.
   
Jie Yang, Yingying Chen, Wade Trappe, and Jerry Cheng,
Pervasive Wireless Environments: Detecting and Localizing User Spoofing,
ISBN: 978-3-319-07355-2, Springer, 2014.
   

Yingying Chen, Jie Wu, Paul Yu, Xiaogang Wang,
Securing Emerging Wireless Systems,
ISBN:978-0-387-88490-5, Springer, 2009.

Selected Journal Papers:


Selected Conference Papers:

↑Top

   

Rutgers campus