A5071841109- Hydraulic and Pneumatic Systems
- Indoor and Outdoor Localization Technologies
- Underwater Vehicles and Communication Systems
- Text and Document Classification Technologies
- Machine Learning and Data Classification
- Advanced Image Processing Techniques
- Evacuation and Crowd Dynamics
- Image Processing Techniques and Applications
- Remote Sensing and Land Use
- Inertial Sensor and Navigation
- Human Mobility and Location-Based Analysis
- Machine Learning and Algorithms
- Optical Systems and Laser Technology
Southern University of Science and Technology
2025
Chongqing University of Posts and Telecommunications
2024
Shandong University of Technology
2017
Most natural language processing tasks rely on massive labeled data to train an outstanding neural network model. However, the label noise (i.e., wrong label) is inevitably introduced when annotating large-scale text datasets, which significantly degrades performance of models. To overcome this dilemma, we propose a novel <u>G</u>ranular-<u>B</u> all based t<u>RAIN</u>ing framework, named GBRAIN, realize robust coarse-grained representation learning, thus combating noises in diverse tasks....
Abstract. In this paper, we proposed an indoor pedestrian positioning method which is probabilistic constrained by "multi-target encounter" when the initial position known. The based on Pedestrian Dead Reckoning (PDR) method. According to PDR of error size and road network structure, buffer distance determined reasonably centering location generated. At same time, key nodes are selected network. premise knowing between multiple nodes, forward pedestrians entered from different can be...