•  
  •  
 

Article Type

Research Article

Abstract

Uncertainty remains a critical challenge in dynamic spatiotemporal forecasting. This study proposes the Neutrosophic Deep Q-Network (N-DQN), a framework that integrates neutrosophic logic with deep reinforcement learning to enhance decision optimization under uncertainty. Features are modeled through truth, indeterminacy, and falsity membership functions, enabling robust handling of ambiguous data. The framework incorporates attention-guided preprocessing and horizon-aware optimization to adapt predictions across short- and long-term intervals. Experiments on benchmark traffic datasets (METR-LA and PEMS-BAY) demonstrate improved forecasting accuracy and reduced error rates compared with established baselines. The results highlight the scalability and resilience of N-DQN, positioning it as a promising approach for real-world applications in intelligent transportation, healthcare, and other dynamic AI systems.

Keywords

Neutrosophic logic, Deep reinforcement learning, Spatiotemporal forecasting, Uncertainty modeling, Decision optimization, Intelligent systems

Share

COinS