Cross-city Point of interest (POI) recommendation aims to recommend locations for users who move from a source city to a target city. Most existing cross-city POI recommendation methods consider users’ check-in records from their source city to analyze user preferences, while neglecting the crucial information in the reviews, which is of importance for modeling user preferences. Additionally, users often have different travel intentions when traveling to other cities, how to accurately mine users’ travel intention in the target city is still challenging. To address above issues, a cross-city POI recommendation method called IARSA is proposed, which integrates user intention aware and review sentiment analysis. Firstly, gated graph neural network (GGNN) is employed to obtain user preferences for the source city, and variational deep embedding is employed to mine users’ different travel intensions in the target city. Then the user drift preference representation is generated with user intentions and inherent preference. Next, we analyze the sentiment information of POI reviews, and utilize the Gaussian Mixture Model (GMM) to model reviews in POIs and generate sentiment vectors for POI. The comprehensive representation of the POIs is a combination of the sentiment vector and the geographic vector generated by Graph Convolutional Network (GCN). Finally, relevance scores for POIs in the target city are computed with user drift preference embedding and POI representations. Extensive experiments conducted on three real-world datasets demonstrate that our approach significantly outperforms state-of-the-art baseline methods, achieving superior results in both precision and recall metrics.
Xu Zhou, Fu-Liang Zhou, Ming-Yi Xin et al.· IEEE Transactions on Big Dat...· 0 citations
The rapid expansion of real-time Internet of Things (IoT) applications has positioned uncrewed aerial vehicles (UAVs) as a promising solution for flexible and timely data collection in areas lacking robust infrastructure. This paper investigates a UAV-assisted secure status updating system, where a UAV serves as a mobile relay to forward status updating packets from ground devices (GDs) under the threat of a potential eavesdropper. To ensure information freshness and operational sustainability, we formulate a long-term stochastic optimization problem to minimize the cumulative average age-of-information (AoI) of all GDs and energy consumption of the UAV. The formulated optimization problem is an online mixed-integer non-linear programming problem, which involves the joint optimization of the flight speed, direction, and transmission power of the UAV as well as the binary scheduling indicator of GDs. To tackle the inherent non-convexity and complex spatial-temporal coupling, we propose an agentic artificial intelligence (AI)-enabled deep reinforcement learning (DRL) approach, named adaptive truncated quantile critics with large language models (LLM)-enabled state representation and reward function design (ATQC-L). Specifically, an adaptive truncated quantile mechanism is incorporated to mitigate distributional overestimation in dynamic environments. Furthermore, we leverage the reasoning capability of LLMs as an offline design-time agent to generate task-aware state representation and intrinsic reward functions. Simulation results demonstrate that the proposed ATQC-L algorithm outperforms representative DRL baselines in balancing information freshness and energy consumption of the UAV, while maintaining stable performance under different network scales, LLM backbones, truncation-parameter settings, imperfect eavesdropping channel state information, and mobile eavesdropping scenarios.
Chuang Zhang, Geng Sun, Jiahui Li et al.· IEEE Transactions on Cogniti...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
