Problem
Research questions and friction points this paper is trying to address.
traffic accident risk prediction
spatio-temporal fusion
global spatial correlation
temporal feature noise
spatial semantics
MambaLSTM: A Spatio-Temporal Framework for Enhanced Traffic Accident Risk Prediction
🤖 AI Summary
This study addresses the limitations of existing traffic accident risk prediction methods, which are susceptible to noise in spatiotemporal feature fusion and struggle to model global spatial dependencies across regions. To overcome these challenges, this work proposes the MambaLSTM framework, which enhances temporal feature integration through a squeeze-and-excitation module and captures semantic relationships among neighboring areas via a block embedding module. Innovatively combining the state space model Mamba with a refined LSTM unit, the framework jointly captures global spatial dependencies and long- and short-term temporal dynamics. Experimental results on real-world datasets demonstrate that the proposed method significantly outperforms current state-of-the-art models, achieving higher accuracy in accident risk prediction.
📝 Abstract
In traffic accident risk prediction, most studies overlook the extra noise that could be incorporated when fusing temporal features into spatial features, and some models struggle to capture global correlations among spatial regions. To address these challenges, we propose a novel traffic accident risk prediction framework named MambaLSTM. First, we develop a squeeze-and-excitation temporal feature fusion module to integrate temporal information without compromising spatio-temporal integrity. Second, we introduce a new patch embedding module for effectively capturing semantic relationships among spatially adjacent regions. Additionally, we introduce a Mamba block based on state-space models to model global spatial semantics in urban regions. Finally, we propose a MambaLSTM unit to efficiently capture long- and short-term temporal dependencies for identifying dynamic risk patterns. Extensive experiments on real-world datasets demonstrate the proposed model's superiority over state-of-the-art methods. The code is released at https://github.com/Zhenzovo/MambaLSTM.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Mamba
Spatio-Temporal Modeling
Traffic Accident Risk Prediction
State-Space Model
Temporal Feature Fusion
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
