Semantic Web-Enhanced Reinforcement Learning Model for Urban Planning Optimization DOI Open Access

Yimeng Liang,

Jun Zhang

International Journal on Semantic Web and Information Systems, Journal Year: 2025, Volume and Issue: 21(1), P. 1 - 20

Published: March 22, 2025

As urbanization accelerates, urban planning is essential for enhancing quality of life and sustainability. Current methods struggle with complex spatiotemporal data, limiting real-time feature capture strategy adjustments. To address this, we propose the Semantic Web-Enhanced Reinforcement Learning-based Urban Planning Optimization Model (SWRL-UPOM). Integrating Web technologies Spatio-Temporal Adaptive Multimodal Graph Convolutional Network (STAMFGCN) Gated Hierarchical Attention LSTM (STGHALSTM), SWRL-UPOM uses reinforcement learning to optimize strategies dynamically. STAMFGCN extracts inter-regional relationships from multimodal while STGHALSTM models predicts pollution evolution. Leveraging structured data reasoning, RL framework iteratively updates based on predicted trends. Experiments show outperforms traditional in prediction, optimization, adaptability dynamic changes.

Language: Английский

A Neuromarketing Approach to Consumer Behavior on Web Platforms DOI Open Access
Coral Cenizo

International Journal of Consumer Studies, Journal Year: 2025, Volume and Issue: 49(2)

Published: March 1, 2025

ABSTRACT In recent years, neuromarketing has gained prominence as a strategic research tool. However, despite the proliferation of studies leveraging neuroscience to analyze cognitive and emotional processes, advancements in this field within website environment remain fragmented, revealing significant scientific gap. The primary objective study is conduct systematic literature review (SLR) consolidate knowledge on application analyzing consumer behavior web platforms. To achieve this, SPAR‐4‐SLR protocol TCCM framework were employed retrieved from Web Science Scopus, enabling identification key gaps area. findings indicate that techniques, such eye tracking brain activity analysis, have shown great potential for optimizing interface design enhancing user experience. also highlights critical shortcomings areas integration factors, consideration multicultural variables, inclusion users with disabilities. These limitations underscore need multidimensional approaches account both conscious subconscious responses visual navigational stimuli. Given growing importance neuroscientific techniques studying behavior, addresses gap provides new insights academic business practice.

Language: Английский

Citations

0
Semantic Web-Enhanced Reinforcement Learning Model for Urban Planning Optimization DOI Open Access

Yimeng Liang,

Jun Zhang

International Journal on Semantic Web and Information Systems, Journal Year: 2025, Volume and Issue: 21(1), P. 1 - 20

Published: March 22, 2025

As urbanization accelerates, urban planning is essential for enhancing quality of life and sustainability. Current methods struggle with complex spatiotemporal data, limiting real-time feature capture strategy adjustments. To address this, we propose the Semantic Web-Enhanced Reinforcement Learning-based Urban Planning Optimization Model (SWRL-UPOM). Integrating Web technologies Spatio-Temporal Adaptive Multimodal Graph Convolutional Network (STAMFGCN) Gated Hierarchical Attention LSTM (STGHALSTM), SWRL-UPOM uses reinforcement learning to optimize strategies dynamically. STAMFGCN extracts inter-regional relationships from multimodal while STGHALSTM models predicts pollution evolution. Leveraging structured data reasoning, RL framework iteratively updates based on predicted trends. Experiments show outperforms traditional in prediction, optimization, adaptability dynamic changes.

Language: Английский

Citations

0