A5070836917- Speech and Audio Processing
- Advanced Neural Network Applications
- Occupational Health and Safety Research
- Music and Audio Processing
- Advanced Data Compression Techniques
- Impact of Technology on Adolescents
- Photonic and Optical Devices
- Domain Adaptation and Few-Shot Learning
- Child and Adolescent Psychosocial and Emotional Development
- Image and Signal Denoising Methods
- Digital Mental Health Interventions
- Advanced Memory and Neural Computing
- Neural Networks and Reservoir Computing
- Human Pose and Action Recognition
- Infection Control in Healthcare
- Hearing Loss and Rehabilitation
- Infection Control and Ventilation
- Quality and Safety in Healthcare
Rutgers, The State University of New Jersey
2024-2025
Rutgers Sexual and Reproductive Health and Rights
2022
Lehigh University
2020
Wuhan University
2018-2019
Proper personal protective equipment (PPE) use is critical to prevent disease transmission healthcare providers, especially those treating patients with a high infection risk. To address the challenge of monitoring PPE usage in healthcare, computer vision has been evaluated for tracking adherence. Existing datasets this purpose, however, lack diversity and nonadherence classes, represent single not multiple do depict dynamic provider movement during patient care. We introduce Resuscitation...
High-order decomposition is a widely used model compression approach towards compact convolutional neural networks (CNNs). However, many of the existing solutions, though can efficiently reduce CNN sizes, are very difficult to bring considerable saving for computational costs, especially when ratio not huge, thereby causing severe computation inefficiency problem. To overcome this challenge, in paper we propose efficient High-Order DEcomposed Convolution (HODEC). By performing systematic...
Conventional methods in semi-supervised learning (SSL) often face challenges related to limited data utilization, mainly due their reliance on threshold-based techniques for selecting high-confidence unlabeled during training. Various efforts (e.g., FreeMatch) have been made enhance utilization by tweaking the thresholds, yet none managed use 100% of available data. To overcome this limitation and improve SSL performance, we introduce \algo, a novel algorithm that fully utilizes boost...
Abstract Objectives Human monitoring of personal protective equipment (PPE) adherence among healthcare providers has several limitations, including the need for additional personnel during staff shortages and decreased vigilance prolonged tasks. To address these challenges, we developed an automated computer vision system PPE in settings. We assessed performance against human observers detecting nonadherence a video surveillance experiment. Materials Methods The was trained to detect 15...
College students are experiencing increasing rates of depression, anxiety and other mental health disorders. However, traditional face-to-face consultations not always accessible, the current digital interventions cannot provide richness an in-person consultation. To address such problems, we developed a smartphone application called Mental Mentor (M&M) to help college cope with their anxieties especially those related academic performance. M&M applies retrieval-based model mentoring advice...
On silicon photonic platform, we demonstrate a spatial-spectral pattern classifier and three-channel wavelength demultiplexer in few-layer metasystems.