A5103232609- Traffic and Road Safety
- Autonomous Vehicle Technology and Safety
- Traffic Prediction and Management Techniques
- Industrial Vision Systems and Defect Detection
- Human-Automation Interaction and Safety
- Geological and Geophysical Studies
- Traffic control and management
- Anomaly Detection Techniques and Applications
- Seismic Imaging and Inversion Techniques
- Evacuation and Crowd Dynamics
- Geological and Geochemical Analysis
- Integrated Circuits and Semiconductor Failure Analysis
- earthquake and tectonic studies
- Hydrocarbon exploration and reservoir analysis
- Advancements in Photolithography Techniques
- Embedded Systems Design Techniques
- Air Traffic Management and Optimization
- Cloud Computing and Resource Management
- Manufacturing Process and Optimization
- Advanced Neural Network Applications
- Text Readability and Simplification
- Aerospace and Aviation Technology
- Topic Modeling
- UAV Applications and Optimization
- CCD and CMOS Imaging Sensors
Shanghai University
2023-2024
Nanyang Technological University
2016-2022
Institute for Infocomm Research
2020-2022
Agency for Science, Technology and Research
2020-2022
Alibaba Group (China)
2021-2022
Sinopec (China)
2013
Beijing Jiaotong University
2010
China University of Petroleum, Beijing
2010
China University of Petroleum, East China
2008-2009
Road accidents wreck lives. Could technology stop them from happening? Driving better road safety with and artificial intelligence are the key elements considered by several carmakers. The aspect of transportation in future is to build an ecosystem comprising autonomous, connected, electric shared mobility. evolution autonomous vehicles (AVs) can potentially aid people be deployed resolve mobility-related pain for drivers on roads while changing lanes. Thus, intelligent assistance system...
This study presents a domain-specific automated machine learning (AutoML) for risk prediction and behaviour assessment, which can be used in the behavioural decision-making motion trajectory planning of autonomous vehicles (AVs). The AutoML enables end-to-end from vehicle movement sensing data to detailed levels corresponding characteristics, integrates three main components of: unsupervised identification by surrogate indicators big clustering, feature based on XGBoost, model auto-tuning...
With the enrichment of smartphones, driving distractions caused by phone usages have become a threat to safety. A promising way mitigate is detect them and give real-time safety warnings. However, existing detection algorithms face two major challenges, low user acceptance in-vehicle camera sensors, uncertain accuracy pre-trained models due drivers individual differences. Therefore, this study proposes domain-specific automated machine learning (AutoML) self-learn optimal distraction based...
Objective This study aims to investigate the causes of take-over failures in conditional automated driving with spatial-temporal analysis brain zone activation. Background Take-over requires a human driver resume control vehicle when its automation system disengages. Existing studies have found that occur frequently on some drivers, but not been thoroughly studied. Method In simulator experiment, 40 drivers took over critical freeway cut-in situations. Functional near-infrared spectroscopy...
Abstract Data from seismic reflection profiles, drilling, stratigraphy, structural deformation studies and physical rock properties reveal the existence of decol1ement structures in both shallow deep levels western Shandong, China. The most outstanding occur along regional unconformity surface between Cambrian Archean, disconformity Carboniferous Ordovician. structure manifests as a fault zone with cataclastic rocks asymmetrical folds. Some underwent dynamic metamorphism hydrothermal...
Early risk diagnosis and driving anomaly detection from vehicle stream are of great benefits in a range advanced solutions towards Smart Road crash prevention, although there intrinsic challenges, especially lack ground truth, definition multiple exposures. This study proposes domain-specific automatic clustering (termed AutoCluster) to self-learn the optimal models for unsupervised assessment, which integrates key steps into an auto-optimisable pipeline, including feature algorithm...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Enhancing yield is recognized as a paramount driver to reducing production costs in semiconductor smart manufacturing. However, optimizing and ensuring high rates highly complex technical challenge, especially while maintaining reliable diagnosis prognosis, this shall require understanding all the confounding factors condition. This study proposes domain-specific explainable automated machine learning technique (termed xAutoML), which autonomously self-learns optimal models for prediction,...