A5101837783- Energy Efficient Wireless Sensor Networks
- Security in Wireless Sensor Networks
- Explainable Artificial Intelligence (XAI)
- Optical Coherence Tomography Applications
- Medical Image Segmentation Techniques
- Optical Polarization and Ellipsometry
- Water Quality Monitoring Technologies
- Advanced Sensor and Control Systems
- Neural Networks and Reservoir Computing
- AI in cancer detection
- Mobile Ad Hoc Networks
- Bayesian Modeling and Causal Inference
- Decision-Making and Behavioral Economics
- Industrial Technology and Control Systems
- Advanced Algorithms and Applications
- Advanced Neural Network Applications
University of Electronic Science and Technology of China
2024
University of Science and Technology Beijing
2024
Sun Yat-sen University
2010-2011
Low-light image enhancement (LLIE) investigates how to improve the brightness of an captured in illumination-insufficient environments. The majority existing methods enhance low-light images a global and uniform manner, without taking into account semantic information different regions. Consequently, network may easily deviate from original color local To address this issue, we propose semantic-aware knowledge-guided framework (SKF) that can assist model learning rich diverse priors...
In wireless sensor networks (WSNs) how to judiciously utilize the limited energy capacity of nodes is very important, especially in multi-user application scenarios. this paper data query processing strategies are discussed and scenario defined. scenario, there a large-scale monitored region with large number original queries requested from thousands users. Such huge requests sensornets heavy load for traditional methods. To mitigate problem, novel strategy, NER-MQ (Network Event Report...
An application scenario, the multi-users scenario in wireless sensor networks (WSNs), was defined this article, where a large number of queries were generally sent from thousands users large-scale monitored region and they would be very heavy load for query processing. To deal with
In this work, we address the challenging problem of long-horizon goal-reaching policy learning from non-expert, action-free observation data. Unlike fully labeled expert data, our data is more accessible and avoids costly process action labeling. Additionally, compared to online learning, which often involves aimless exploration, provides useful guidance for efficient exploration. To achieve goal, propose a novel subgoal strategy. The motivation behind strategy that goals offer limited...