A5101713329- Topic Modeling
- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Caching and Content Delivery
- Robotics and Automated Systems
- Vehicle Routing Optimization Methods
- Digital Transformation in Industry
- Indoor and Outdoor Localization Technologies
- Expert finding and Q&A systems
- Urban and Freight Transport Logistics
- Transportation and Mobility Innovations
- Radio Wave Propagation Studies
- GNSS positioning and interference
- Technology and Security Systems
- Metaheuristic Optimization Algorithms Research
Communication University of China
2023
Anhui University
2022
Jinan University
2020
Beihang University
2011
Existing news recommendation methods suffer from sparse and weak interaction data, leading to reduced effectiveness explainability. Knowledge reasoning, which explores inferential trajectories in the knowledge graph, can alleviate data sparsity provide explicitly recommended explanations. However, brute-force pre-processing approaches used conventional are not suitable for fast-changing recommendation. Therefore, we propose an explainable model: Reinforced Contrastive Heterogeneous Network...
Personalised news recommendation comprises two crucial components: understanding and user modelling. Previous studies have attempted to model interests using various internal information external knowledge graphs (KG). However, they overlooked the collaborative function of KG among diverse behaviours, resulting in serious cold-start problems poor interpretability interests. To address these issues, this article proposes a novel approach called Relation-Aware Approach based on Multi-view News...
Nowadays, news spreads faster than it is consumed. This, alongside the rapid cycle and delayed updates, has led to a challenging cold-start issue. Likewise, user problem, due limited engagement, long hindered recommendations. To tackle both of them, we introduce Symmetric Few-shot Learning framework for Cold-start News Recommendation (SFCNR), built upon self-supervised contrastive enhancement. Our approach employs symmetric few-shot learning towers (SFTs) transform warm user/news attributes...
In view of the ambiguity solution is technical difficulty in relative position carrier phase differential. This paper introduces principle differential positioning and process integer detail. The solved by LAMBDA (the least-square decorrelation adjustment) method a short baseline, float fixed baseline are compared. result show that can reach accuracy centimeter level. KEYWORD: positioning; phase; ambiguity;
The genetic algorithm and the adaptive mechanism are adopted to tackle inefficiency of optimization convergence difficulty collaborative (CO). Based on further analysis process, constraint conditions converged into part function. system model CO has been reconstructed according penalty function which is based information different disciplines transformation system-level constraints. Therefore, global local search capabilities searching efficiency have improved. Meanwhile, caused by internal...