A5072170851- Non-Invasive Vital Sign Monitoring
- Hand Gesture Recognition Systems
- User Authentication and Security Systems
- Music and Audio Processing
- Gaze Tracking and Assistive Technology
- Context-Aware Activity Recognition Systems
- Hearing Impairment and Communication
- Advanced Decision-Making Techniques
- Image and Signal Denoising Methods
- Digital Media and Visual Art
- Speech and Audio Processing
- Biometric Identification and Security
- Heart Rate Variability and Autonomic Control
- Tactile and Sensory Interactions
- Cultural and Communication Design Research
- Video Surveillance and Tracking Methods
- EEG and Brain-Computer Interfaces
- Image Retrieval and Classification Techniques
- Advanced Chemical Sensor Technologies
- ECG Monitoring and Analysis
- Complex Network Analysis Techniques
- Machine Fault Diagnosis Techniques
- Aesthetic Perception and Analysis
- Cultural Industries and Urban Development
- Advanced Image Fusion Techniques
East China Normal University
2023-2025
Liaoning Provincial People's Hospital
2025
China Medical University
2025
Beijing Institute of Graphic Communication
2024
RELX Group (United Kingdom)
2024
Northwestern University
2021-2024
RELX Group (United States)
2024
Xi'an Jiaotong University
2024
All India Institute of Medical Sciences
2024
University at Buffalo, State University of New York
2018-2023
Smart wearable devices have recently become one of the major technological trends and been widely adopted by general public. Wireless earphones, in particular, seen a skyrocketing growth due to its great usability convenience. With goal seeking more unobtrusive authentication method that users can easily use conveniently access, this study we present EarEcho as novel, affordable, user-friendly biometric solution. takes advantages unique physical geometrical characteristics human ear canal...
Noninvasive sensors capable of measuring weak biopotential signals, such as electrocardiogram (ECG) and EEG, communicating results wirelessly to a host computer are developing rapidly. Some them utilize capacitively coupled electrodes in an attempt place the sensor at distance from skin. This article demonstrated fabrication development ECG electrode prototype using custom high specific capacitance high-performance electronics. Two ultrathin capacitive were fabricated on flexible polyimide...
Monitoring a person's dietary behavior has many health applications (e.g. weight management). Existing approaches for automatic eating detection using wearable sensors often require custom hardware that may not be practical as their usability and energy efficiency have been validated. In this paper, we propose to use off-the-shelf Bluetooth headsets unobtrusively monitor detect users' episodes by analyzing the chewing sound. The challenges of commodity acoustic include limited sampling rate...
The unique climate and topography of the Tibetan Plateau produce an abundant distribution lakes. These lakes are important indicators change, changes in lake area have critical implications for water resources ecological conditions. Lake change can be monitored using huge sets high-resolution remote sensing data available, but this demands automatic classification system. This study develops algorithm Chinese <small>GF</small>-1 (or Gaofen-1) wide-field-of-view...
The increasing adoption of 3D printing in many safety and mission critical applications exposes printers to a variety cyber attacks that may result catastrophic consequences if the process is compromised. For example, mechanical properties (e.g., physical strength, thermal resistance, dimensional stability) printed objects could be significantly affected degraded simple setting maliciously changed. To address this challenge, study proposes model-free real-time online monitoring approach...
We propose SonicASL, a real-time gesture recognition system that can recognize sign language gestures on the fly, leveraging front-facing microphones and speakers added to commodity earphones worn by someone facing person making gestures. In user study (N=8), we evaluate performance of various at both word sentence levels. Given 42 frequently used individual words 30 meaningful sentences, SonicASL achieve an accuracy 93.8% 90.6% for word-level sentence-level recognition, respectively. The...
With the rapid growth of wearable computing and increasing demand for mobile authentication scenarios, voiceprint-based has become one prevalent technologies already presented tremendous potentials to public. However, it is vulnerable voice spoofing attacks (e.g., replay synthetic attacks). To address this threat, we propose a new biometric approach, named EarPrint, which aims extend voiceprint build hidden secure user scheme on earphones. EarPrint builds speaking-induced body sound...
Complex wavelet structural similarity (CW-SSIM) index has been proposed as a promising image measure that is robust to small geometric distortions such translation, scaling and rotation of images, but how make the best use it in classification problems not deeply investigated. In this paper, we propose novel "feature-extraction free" algorithm based on CW-SSIM handwritten digit recognition an example demonstrate it. First, unsupervised clustering method used divide training images into...
In this work we study the feasibility and usability of an assistive food journaling system that sends users just-in-time reminders when unique hand gestures during consumption are detected using a smartwatch. Our shows participants were able to sustain logging throughout 2-week period with help our eating detection system, as number correlate well logs. Despite fact required wear watch on their dominant hand, it was still quite usable did not interfere normal activities. Participant feedback...
With the rapid growth of artificial intelligence and mobile computing, intelligent speech interface has recently become one prevalent trends already presented huge potentials to public. To address privacy leakage issue during interaction or accommodate some special demands, silent interfaces have been proposed enable people's communication without vocalizing their sound (e.g., lip reading, tongue tracking). However, most existing mechanisms require either background illuminations additional...
Recognition of facial expressions has been widely explored to represent people's emotional states. Existing expression recognition systems primarily rely on external cameras which make it less accessible and efficient in many real-life scenarios monitor an individual's a convenient unobtrusive manner. To this end, we propose PPGface, ubiquitous, easy-to-use, user-friendly platform that leverages earable devices with built-in PPG sensor. PPGface understands the through dynamic patterns...
With the aging of population and long-time wearing earphones, hearing health has gradually emerged as a worldwide issue. Early detection conditions would greatly reduce potential risks with timely medical intervention. This study proposes an earphone-based ear condition monitoring system, named EarHealth, which is low-cost, non-invasive, easily usable in daily life. It can detect three major conditions: ruptured eardrum, earwax buildup blockage, otitis media. By analyzing recorded echoes...
Intelligent speech interfaces have been developing vastly to support the growing demands for convenient control and interaction with wearable/earable portable devices. To avoid privacy leakage during interactions strengthen resistance ambient noise, silent widely explored enable people's mobile/wearable devices without audible sounds. However, most existing solutions require either restricted background illuminations or hand involvement hold device perform gestures. In this study, we propose...
Seronegative Hashimoto's thyroiditis is often underdiagnosed due to the lack of antibody markers. Combining ultrasound radiomics with machine learning offers potential for early detection in patients normal thyroid function. Data from 164 single lesions and function, treated surgically between 2016 2024, were retrospectively collected four hospitals. Radiomics features extracted images non-tumorous hypoechoic areas. Pathological lymphocytic infiltration ratios evaluated by senior...
Sign language builds up an important bridge between the d/Deaf and hard-of-hearing (DHH) hearing people. Regrettably, most people face challenges in comprehending sign language, necessitating translation. However, state-of-the-art wearable-based techniques mainly concentrate on recognizing manual markers (e.g., hand gestures), while frequently overlooking non-manual markers, such as negative head shaking, question mouthing. This oversight results loss of substantial grammatical semantic...
To address the increasing challenges of counterfeit detection and IP protection for 3D printing, we propose that every printer holds unique fingerprinting features characterized by thermodynamic properties extruder hot-end can be used as a new way watermarking. We prove these physical fingerprints resulting from manufacturing imperfections system variations exhibit distinct heating responses, namely "ThermoTag," which represented distinguishable processes and, ultimately, temperature...
Wearable devices have become indispensable gadgets in people's daily lives nowadays; especially wireless earphones experienced unprecedented growth recent years, which lead to increasing interest and explorations of user authentication techniques. Conventional methods embedded that use microphones or other modalities are vulnerable environmental factors, such as loud noises occlusions. To address this limitation, we introduce EarPPG, a new biometric modality takes advantage the unique in-ear...