A5023706427- EEG and Brain-Computer Interfaces
- Muscle activation and electromyography studies
- Building Energy and Comfort Optimization
- Neuroscience and Neural Engineering
- Stroke Rehabilitation and Recovery
- Wind and Air Flow Studies
- Urban Heat Island Mitigation
- Energy Efficiency and Management
- Structural Load-Bearing Analysis
- Facilities and Workplace Management
- Railway Engineering and Dynamics
- Structural Engineering and Vibration Analysis
- Blind Source Separation Techniques
- Structural Behavior of Reinforced Concrete
- Sustainable Building Design and Assessment
- Geochemistry and Geologic Mapping
- Mechanical stress and fatigue analysis
- Smart Grid Energy Management
- Hydrocarbon exploration and reservoir analysis
- Hand Gesture Recognition Systems
- Mineral Processing and Grinding
- Air Quality Monitoring and Forecasting
- Energy Load and Power Forecasting
- Advanced Neural Network Applications
- Noise Effects and Management
Xi'an Jiaotong University
2015-2025
Zhejiang University
2011-2025
South China University of Technology
2013-2024
Central South University
2022-2024
Tsinghua University
2024
Shandong University
2023
Beijing University of Civil Engineering and Architecture
2021-2022
Chaozhou Central Hospital
2022
Institute of Engineering
2021
Stanford University
2016-2021
Lane detection is one of the most important tasks in self-driving. Due to various complex scenarios (e.g., severe occlusion, ambiguous lanes, etc.) and sparse supervisory signals inherent lane annotations, task still challenging. Thus, it difficult for ordinary convolutional neural network (CNN) train general scenes catch subtle feature from raw image. In this paper, we present a novel module named REcurrent Feature-Shift Aggregator (RESA) enrich after preliminary extraction with an CNN....
With ever-rising energy demand and diminishing sources of inexpensive resources, conservation has become an increasingly important topic. Building heating, ventilation, air conditioning (HVAC) systems are considered to be a prime target for due their significant contribution commercial buildings’ consumption in the US. Knowing building’s occupancy plays crucial role implementing demand-response HVAC controls, with corresponding potential reduction consumption, especially office buildings....
Semantic segmentation is a fundamental problem in computer vision. It considered as pixel-wise classification practice, and most models use loss their optimization riterion. However, the ignores dependencies between pixels an image. Several ways to exploit relationship have been investigated, \eg, conditional random fields (CRF) pixel affinity based methods. Nevertheless, these methods usually require additional model branches, large extra memories, or more inference time. In this paper, we...
A novel artificial bee colony (ABC) algorithm to detect structural damage via modal and frequency analyses is proposed (named as TCABC algorithm). Compared the standard ABC algorithm, tabu search method chaotic are adopted in enhance exploration exploitation ability. The uses a memory function avoid solution being trapped local minimum, which increases Chaotic generates more searching points for finding global Additionally, first roulette wheel selection replaced by tournament ability of...
The goal of this study was to perform real-time estimation isometric finger extension force using the discharge information motor units (MUs).A electromyogram (EMG) decomposition method based on fast independent component analysis (FastICA) algorithm developed extract MU events from high-density (HD) EMG recordings. first performed offline during an initialization period, and obtained separation matrix then applied new data samples in real-time. Since pool probability reflects neural drive...
Proper monitoring of anesthesia stages can guarantee the safe performance clinical surgeries. In this study, different were classified using near-infrared spectroscopy (NIRS) signals with machine learning. The cerebral hemodynamic variables right proximal oxyhemoglobin (HbO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> ) in maintenance (MNT), emergence (EM) and consciousness (CON) stage collected then differences between three compared...
Heating, ventilation, and air conditioning (HVAC) is a major energy consumer in buildings, implementing demand driven HVAC operations way to reduce related consumption. This relies on the availability of occupancy information, which determines peak/off-hour modes that impact cooling/heating loads systems. research proposes an estimation model built combination non-intrusive sensors can detect indoor temperature, humidity, CO2 concentration, light, sound motion. Sensor data processed real...
Hand gesture has become a powerful means for human-computer interaction. Traditional recognition just consider hand trajectory. For some specific applications, such as virtual reality, more natural gestures are needed, which complex and contain movement in 3-D space. In this paper, we introduce an HMM-based method to recognize single gestures. Gesture images gained by common web camera. Skin color is used segment area from the image form sequence. Then put forward state-based spotting...
The monosynaptic cortico-motoneuronal connections suggest the possibility of individual motor units (MUs) receiving independent commands from cortex. However, previous studies that used corticomuscular coherence (CMC) between electroencephalogram (EEG) signals and electromyogram (EMG) have not directly explored corticospinal functionality at single motoneuron level. objective this study is to find out whether synchronous activities exist cortex MUs. Corticomuscular was calculated EEG MU...
The current research investigates the effect of residual stresses from welding on stability steel structures, particularly herringbone column undulating cross-truss structure in Zhengzhou New International Exhibition Center project. Residual at 30 key points were measured using blind hole method, and temperature stress fields under thermal coupling analyzed numerical simulation techniques. welded columns are generally higher than theoretical calculated values, with relative error most...
Lane is critical in the vision navigation system of intelligent vehicles. Naturally, lane a traffic sign with high-level semantics, whereas it owns specific local pattern which needs detailed low-level features to localize accurately. Using different feature levels great importance for accurate detection, but still under-explored. On other hand, current detection methods struggle detect complex dense lanes, such as Y-shape or fork-shape. In this work, we present Cross Layer Refinement...
A closed-loop Functional Electrical Stimulation (FES) system that incorporates electromyogram (EMG) signal feedback provides more effective assistance to paralytic patients in maintaining and recovering their motor abilities. However, the FES with real-time adjustment of stimulation parameters tends introduce time-varying artifacts EMG signals, challenging removal aims at accurate monitoring muscle contraction status. Therefore, an acquisition embeds a artifact generation (SAG) circuit...