A5100458226- EEG and Brain-Computer Interfaces
- Neural dynamics and brain function
- Functional Brain Connectivity Studies
- Heart Rate Variability and Autonomic Control
- Flood Risk Assessment and Management
- Visual Attention and Saliency Detection
- Metallurgy and Material Forming
- Hydrology and Watershed Management Studies
- Face Recognition and Perception
- Blind Source Separation Techniques
- Sleep and Work-Related Fatigue
- Infrastructure Maintenance and Monitoring
- Microstructure and Mechanical Properties of Steels
- Visual perception and processing mechanisms
- Hydrological Forecasting Using AI
- ECG Monitoring and Analysis
- Advanced Memory and Neural Computing
- Neural Networks and Applications
- Microstructure and mechanical properties
- Advanced Neuroimaging Techniques and Applications
- Cell Image Analysis Techniques
- Structural Health Monitoring Techniques
- Soft Robotics and Applications
- Neural and Behavioral Psychology Studies
- CCD and CMOS Imaging Sensors
Dalian University of Technology
2016-2025
University of Manchester
2025
Tianjin University
2019-2025
Beijing General Research Institute of Mining and Metallurgy
2024
Nanjing University of Information Science and Technology
2024
Northeastern University
2013-2023
Dalian University
2014-2023
PLA Information Engineering University
2010-2023
Third Affiliated Hospital of Sun Yat-sen University
2023
Sun Yat-sen University
2023
Manual visual inspection is customarily used to identify and evaluate service status of bridges. However, current procedures followed by human inspectors demand long time access Also, highly relying on subjective or empirical knowledge may induce false evaluation. To overcome these challenges, a vision-based method presented for bridge defects detection using transfer learning convolutional neural networks (CNNs), which could automatically analyze large volume collected images. Firstly,...
Flash floods in mountainous catchments are often caused by the rainstorm, which may result more severe consequences than plain area due to less timescale and a fast-flowing front of water debris. flood forecasting is huge challenge for hydrologists managers its instantaneity, nonlinearity, dependency. Among different methods forecasting, data-driven models have become increasingly popular recent years their strong ability simulate nonlinear hydrological processes. This study proposed Support...
Abstract Nature‐based solutions have been promoted as a sustainable solution for urban stormwater management and they are currently adopted at an unprecedented speed scale to build sponge cities in China, with primary aim solving flood problems. However, there limits how much rainfall can absorb, hence, unlikely be panacea flooding problems cities. We argue that bottom‐up community‐based measures essential part of the intervention development framework is required transform into resilient...
Driver distraction diverting drivers' attention to unrelated tasks and decreasing the ability control vehicles, has aroused widespread concern about driving safety. Previous studies have found that performance decreases after used vehicle behavioral features detect distraction. But how brain activity changes while remains unknown. Electroencephalography (EEG), a reliable indicator of activities been widely employed in many fields. However, challenges still exist mining information EEG...
Driving fatigue is one of the main causes traffic accidents. Generally, single-modal driving detection methods have low accuracy and weak anti-interference capability in real environment. In this paper, we propose an optimized method for that fuses EEG vehicle motion information. The correlation between signal information analyzed. extracts frequency band energy ratio four rhythm waves α, β, θ δ from EEG. sample entropy standard deviation steering wheel angle, acceleration speed calculated....
This paper proposes a real-time electroencephalogram (EEG)-based detection method of the potential danger during fatigue driving. To determine driver in real time, wavelet entropy with sliding window and pulse coupled neural network (PCNN) were used to process EEG signals visual area (the main information input route). detect danger, mechanism was analyzed. The functional brain networks employed track impact on processing capacity brain. results show overall connectivity subjects is weakened...
The assessment of flood risk and resilience has become increasingly important in recent years for effective urban management. While are two distinct concepts with unique metrics, there is lack quantitative analysis understanding the relationship between them. This study aims to investigate this at grid cell level areas. To assess high-resolution cells, proposes a performance-based metric, which calculated using system performance curve based on duration magnitude. Flood as product maximum...
Abstract Background Neural stem cells (NSCs) are believed to have the most therapeutic potential for neurological disorders because they can differentiate into various neurons and glial cells. This research evaluated safety efficacy of intranasal administration NSCs in children with cerebral palsy (CP). The functional brain network (FBN) analysis based on electroencephalogram (EEG) voxel-based morphometry (VBM) T1-weighted images were performed evaluate structural changes brain. Methods A...
The UT-A1 urea transporter plays an important role in maintaining the hyperosmolar milieu of inner medulla. Vasopressin increases permeability rat terminal medullary collecting ducts (IMCDs) within 5–10 min. To elucidate mechanism, IMCD suspensions were radiolabeled with [ 32 P]orthophosphate. was immunoprecipitated and analyzed by autoradiogram Western blot. Both 97- 117-kDa proteins phosphorylated. treatment increased phosphorylation both at 2 min, which peaked min remained elevated for up...
With Docker gaining widespread popularity in the recent years, container scheduler becomes a crucial role for exploding containerized applications and services. In this work, host energy conservation, image pulling costs from registry to hosts workload network transition clients are evaluated combination. By modeling scheduling problem as an integer linear programming, effective adaptive is proposed. Impressive cost savings were achieved compared Swarm scheduler. Moreover, it can be easily...
Information on dynamic displacement is an effective indicator for structures condition evaluation and provides a quantised insight into the structural analysis. This paper proposes low-cost system based computer vision using smartphone to measure displacement, then identify properties of structures. Conventional sensors like linear variable differential transformers (LVDT), GPS, accelerometer in monitoring systems have limitations high price, inaccessibility, accuracy. However, some new...
Abstract Real‐time foot pressure monitoring using wearable smart systems, with comprehensive health and analysis, can enhance quality of life prevent foot‐related diseases. However, traditional insole solutions that rely on basic data analysis methods manual feature extraction are limited to real‐time plantar mapping gait failing meet the diverse needs users for healthcare. To address this, we propose a deep learning‐enabled system comprising sensing insole, portable circuit board, learning...
Pluvial floods are destructive natural disasters in cities. With high computational efficiency, machine learning models increasingly used for flood susceptibility mapping. However, limited flooded or nonflooded samples constrain models' predictive capability and introduce uncertainty feature engineering. This study introduces a semi-supervised graph-structured model, Graph Attention Network (GAT), to address data scarcity enable the use of only basic conditioning factors as inputs. GAT uses...
Physiological responses derived from audiovisual perception during assisted driving are associated with the regulation of autonomic nervous system (ANS), especially in emergencies. However, interaction event-related brain activity and ANS regulating peripheral physiological indicators (i.e., heart rate variability (HRV) respiratory rate) is unknown, making it difficult to study neural mechanism takeover assistance system. In this paper, we established a mapping between activations events...