A5048164195- Video Surveillance and Tracking Methods
- Smart Grid Energy Management
- Engineering Diagnostics and Reliability
- Medical Imaging Techniques and Applications
- Advanced Vision and Imaging
- Gear and Bearing Dynamics Analysis
- Advanced Neural Network Applications
- Advanced Bandit Algorithms Research
- Structural Health Monitoring Techniques
- Fire Detection and Safety Systems
- Blind Source Separation Techniques
- Vehicle Noise and Vibration Control
- Single-cell and spatial transcriptomics
- Remote-Sensing Image Classification
- Machine Fault Diagnosis Techniques
- Robotics and Sensor-Based Localization
- Gene Regulatory Network Analysis
- Data Stream Mining Techniques
- Automated Road and Building Extraction
- Image and Object Detection Techniques
University of Jinan
2024-2025
Yantai University
2023
Nanjing University
2023
Karlsruhe Institute of Technology
2020
Forest fires are a vulnerable and devastating disaster that pose major threat to human property life. Smoke is easier detect than flames due the vastness of wildland scene obscuring vegetation. However, shape wind-blown smoke constantly changing, color varies greatly from one combustion chamber another. Therefore, widely used sensor-based fire detection systems have disadvantages untimely high false rate in middle an open environment. Deep learning-based object can recognize objects form...
In this work, we present a visual pose regression network: ViPNet. It is robust and real-time capable on mobile platforms such as self-driving vehicles. We train convolutional neural network to estimate the six degrees of freedom camera from single monocular image in an end-to-end manner. order poses with uncertainty, use Bayesian version ResNet-50 our basic network. SEBlocks are applied residual units increase model's sensitivity informative features. Our ViPNet trained using geometric loss...
We introduce a novel gene regulatory network (GRN) inference method that integrates optimal transport (OT) with deep-learning structural model. Advances in next-generation sequencing enable detailed yet destructive expression assays at the single-cell level, resulting loss of cell evolutionary trajectories. Due to technological and cost constraints, experiments often feature cells sampled irregular sparse time points small sample size. Although trajectory-based models can accurately reveal...
Feature selection (FS) is a crucial procedure in machine learning pipelines for its significant benefits removing data redundancy and mitigating model overfitting. Since concept drift widespread phenomenon streaming could severely affect performance, effective FS on drifting streams imminent. However, existing state-of-the-art algorithms fail to adjust their strategy adaptively when the feature subset changes, making them unsuitable streams. In this paper, we propose dynamic method that...