A5100697911- Axon Guidance and Neuronal Signaling
- Tunneling and Rock Mechanics
- Human Pose and Action Recognition
- Geological Modeling and Analysis
- Gait Recognition and Analysis
- Neurogenesis and neuroplasticity mechanisms
- Semantic Web and Ontologies
- Video Coding and Compression Technologies
- Graph Theory and Algorithms
- Advanced Data Compression Techniques
- Developmental Biology and Gene Regulation
- 3D Surveying and Cultural Heritage
- Zebrafish Biomedical Research Applications
- Anomaly Detection Techniques and Applications
- Advanced Image Fusion Techniques
- 3D Modeling in Geospatial Applications
- Income, Poverty, and Inequality
- Advanced Measurement and Detection Methods
- Hand Gesture Recognition Systems
- Rock Mechanics and Modeling
- Image and Signal Denoising Methods
- Geographic Information Systems Studies
- Infrared Target Detection Methodologies
Southwest Jiaotong University
2022-2024
Ministry of Natural Resources
2022-2023
Sichuan University
2022-2023
Chengdu University
2023
Dalhousie University
2015-2017
National Chung Hsing University
2010
Intelligent tunnel engineering requires accurate and comprehensive digital twin models to represent complex geological environments. The model of environment has multi-level diversified in-depth applications such as problem diagnosis, risk assessment, trend prediction, emergency response, etc. Since construction is a long-term continuous dynamic spatial–temporal progress, the face constantly advances during excavations. Thus, conditions surface surrounding areas are continuously revealed...
ABSTRACT V3 spinal interneurons (INs) are a group of excitatory INs that play crucial role in producing balanced and stable gaits vertebrate animals. In the developing mouse cord, arise from most ventral progenitor domain form anatomically distinctive subpopulations adult cords. They marked by expression transcription factor Sim1 postmitotically, but function development remains unknown. Here, we used Cre ;tdTomato mice to trace fate mutant versus control genetic background during...
Digital twin railway is a pivotal foundation for the intelligent construction and maintenance of engineering projects within extensive open spaces. Its essence integrated representation association management multi-granularity spatiotemporal data, executable analysis models, professional knowledge. These elements are characterized by prominent characteristics multi-source, heterogeneity, massive volume. However, current decentralized independent strategies often neglect dynamic coupling...
The real-time accurate description of all spatial features railway and their spatiotemporal relationships is a crucial factor in realizing comprehensive management related decision-making within the entire life cycle railways. Nevertheless, available data models mainly use static historical sequence data, which are insufficient to support multi-source heterogeneous sensed data; they lack systematic depiction interactive among multiple feature entities, limited low-level descriptive analysis....
Three-dimensional unfavourable geology models with complex structures and various attributes have become crucial for optimal design risk control during tunnel construction. In practical applications, it is necessary to integrate multi-source advanced prediction data, including seismic geological radar transient electromagnetic perform dynamic model However, due the implicit representation of spatial distribution single-source data heterogeneity existing methods mainly rely on manual...
Background : Humans with heterozygous mutations in the axon guidance receptor DCC display congenital mirror movements (MMs), which are involuntary of body parts, such as fingers, on one side that voluntary movement opposite side. In mice, homozygous Dcc kanga mutant allele causes synchronous MM‐like hindlimb during locomotion, resulting hopping. both human and neuroanatomical defect responsible for deficit lateralized motor control remains to be elucidated. Results Using HoxB8‐Cre line...
Human skeleton, as a compact representation of human action, has received increasing attention in recent years due to the easy accessibility skeleton data. Many previous works capture local physical dependencies among joints, which may miss implicit joint correlations. In this light, we propose novel motion scheme infer action categories, includes self-correlation transformation, feature extraction and fusion modules. Our network takes sequence 2D skeletal heat map input, captures...
In this paper, a multiband loss less compression system exploiting inter-band data correlation is presented. We develop an adaptive prediction scheme that can dynamically switch among smooth, intra and intra-band modes subject to the correlation. Specifically, we use context information determine between neighboring bands, then borrow wisdom of optimal formula from previous band if its matches current one. Prediction error feedback for bias cancellation. Experimental results show proposed...