A5101436242- Advanced Computational Techniques and Applications
- Target Tracking and Data Fusion in Sensor Networks
- Family Caregiving in Mental Illness
- Schizophrenia research and treatment
- Mental Health Treatment and Access
- Advanced Neural Network Applications
- COVID-19 and Mental Health
- Mental Health and Patient Involvement
- Chaos control and synchronization
- Advanced Measurement and Detection Methods
- COVID-19 Digital Contact Tracing
- Image and Signal Denoising Methods
- Risk and Safety Analysis
- Occupational Health and Safety Research
- Time Series Analysis and Forecasting
- Long-Term Effects of COVID-19
- Advanced Wireless Communication Techniques
- Multimodal Machine Learning Applications
- Inertial Sensor and Navigation
- Child and Animal Learning Development
- Data-Driven Disease Surveillance
- Blind Source Separation Techniques
- Image Processing Techniques and Applications
- Memory and Neural Mechanisms
- Error Correcting Code Techniques
Purdue University West Lafayette
2025
Guangzhou Medical University
2020-2024
Beijing Jiaotong University
2023
University of Toronto
2023
Center for Excellence in Brain Science and Intelligence Technology
2021
Fujian University of Traditional Chinese Medicine
2021
University of Chinese Academy of Sciences
2021
Chinese Academy of Sciences
2021
National University of Defense Technology
2020
Harbin Institute of Technology
2011
This paper presents modeling random gyro drift rate by traditional time series method , and makes compensation for Kalman filter, proposes the forecasting neural networks strapdown based on analysis, a research of applied inertial navigation systems, comparison between results filter is presented.
The recent outbreak of a novel coronavirus pneumonia (COVID-19) may have acute psychological consequences, both in relation to the impact virus itself and restrictions imposed tackle its spread. We conducted an online survey 403 residents Guangzhou, China. found prevalence anxiety (defined as Generalized Anxiety Disorder-7 score ≥5) was 37.7%, significantly moderately correlated with worry about COVID-19. Higher levels community associated presence individuals COVID-19 same building; longer...
In order to improve the resistance of communication systems jamming signals from multiple sources without any prior information, based on conventional fast independent component analysis algorithm (FastICA), we propose a Pade-FastICA algorithm. The main idea proposed is utilize Pade approximation theory approximate cost function. Simulations are conducted in frequency domain show effects algorithm, which demonstrates its feasibility. Furthermore, numerical experiments performed, superiority...
Purpose This study aims to report on the feasibility, acceptability and outcomes of a peer support program designed promote social participation for adults with serious mental illness (SMI) in China. Design/methodology/approach The authors used community-based participatory research approach adapt test six-month, culturally responsive 68 participants. Peer supporters were trained supervised Guangzhou, workers hired via competitive process completed both classroom field training. Study...
The success of Computer Vision (CV) relies heavily on manually annotated data. However, it is prohibitively expensive to annotate images in key domains such as healthcare, where data labeling requires significant domain expertise and cannot be easily delegated crowd workers. To address this challenge, we propose a neuro-symbolic approach called Rapid, which infers image rules from small amount labeled provided by experts automatically labels unannotated using the rules. Specifically, Rapid...
The analysis and prediction of the risks causes railway freight accidents can help to formulate accident prevention measures, thereby ensuring safety operations. In order achieve evolution results reduce probability from source, this paper proposes a method for based on K2 scoring algorithm graph convolutional neural network (GCN) model. First, data Federal Railroad Administration (FRA) railroad equipment database, classifies into five major categories perspectives human, machine,...
Smoothing processing is one of the common methods in image enhancement that clears up noise, and its theories are all aimed at monochrome image. Using color space transformation can not only gain more useful information, but also use for a based on L-H-S, experiment smoothing made. The experimental results show method availably cleans noise infection improve imaging quality.
Abstract Humans can often handle daunting tasks with ease by developing a set of strategies to reduce decision making into simpler problems. The ability use heuristic demands an advanced level intelligence and has not been demonstrated in animals. Here, we trained macaque monkeys play the classic video game Pac-Man. monkeys’ decision-making may be described strategy-based hierarchical model over 90% accuracy. reveals that adopted take-the-best using one dominating strategy for their at time...
In responding to Covid-19 pandemic, countries around the world implemented various policies impede virus. But effect of these polices among East Asian and European are Utterly different. This paper chose South Korea United Kingdom conduct a case study explore whether what extent did digital track trace make an in curbing mainly utilizes government websites data peer-reviewed research articles from PubMed Google Scholar support research. illustrates three critical factors why contact tracing...