Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Bayesian-Symbolic Integration for Uncertainty-Aware Parking Prediction

Alireza Nezhadettehad, Arkady Zaslavsky, Abdur Rakib, Seng W. Loke

Abstract

Accurate parking availability prediction is critical for intelligent transportation systems, but real-world deployments often face data sparsity, noise, and unpredictable changes. Addressing these challenges requires models that are not only accurate but also uncertainty-aware. In this work, we propose a loosely coupled neuro-symbolic framework that integrates Bayesian Neural Networks (BNNs) with symbolic reasoning to enhance robustness in uncertain environments. BNNs quantify predictive uncertainty, while symbolic knowledge extracted via decision trees and encoded using probabilistic logic programming is leveraged in two hybrid strategies: (1) using symbolic reasoning as a fallback when BNN confidence is low, and (2) refining output classes based on symbolic constraints before reapplying the BNN. We evaluate both strategies on real-world parking data under full, sparse, and noisy conditions. Results demonstrate that both hybrid methods outperform symbolic reasoning alone, and the context-refinement strategy consistently exceeds the performance of Long Short-Term Memory (LSTM) networks and BNN baselines across all prediction windows. Our findings highlight the potential of modular neuro-symbolic integration in real-world, uncertainty-prone prediction tasks.

Bayesian-Symbolic Integration for Uncertainty-Aware Parking Prediction

Abstract

Accurate parking availability prediction is critical for intelligent transportation systems, but real-world deployments often face data sparsity, noise, and unpredictable changes. Addressing these challenges requires models that are not only accurate but also uncertainty-aware. In this work, we propose a loosely coupled neuro-symbolic framework that integrates Bayesian Neural Networks (BNNs) with symbolic reasoning to enhance robustness in uncertain environments. BNNs quantify predictive uncertainty, while symbolic knowledge extracted via decision trees and encoded using probabilistic logic programming is leveraged in two hybrid strategies: (1) using symbolic reasoning as a fallback when BNN confidence is low, and (2) refining output classes based on symbolic constraints before reapplying the BNN. We evaluate both strategies on real-world parking data under full, sparse, and noisy conditions. Results demonstrate that both hybrid methods outperform symbolic reasoning alone, and the context-refinement strategy consistently exceeds the performance of Long Short-Term Memory (LSTM) networks and BNN baselines across all prediction windows. Our findings highlight the potential of modular neuro-symbolic integration in real-world, uncertainty-prone prediction tasks.

Paper Structure

This paper contains 14 sections, 3 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Methodology
  4. Utilised Dataset and Preprocessing
  5. Bayesian Neural Network with Confidence Thresholding
  6. Hybrid Neuro-Symbolic Framework
  7. Handling Data Scarcity and Noise
  8. Evaluation Metrics
  9. Results and Discussion
  10. Experimental Setup
  11. Baseline
  12. Impact of Data Scarcity
  13. Impact of Noise on Model Robustness
  14. Conclusion and Future Work

Figures (4)

  • Figure 1: Overview of the hybrid neuro-symbolic decision process. Method 1 uses symbolic reasoning as a fallback when BNN confidence is low. Method 2 applies symbolic constraints to refine the output space before re-evaluating BNN predictions.
  • Figure 2: Accuracy under full data (baseline) condition.
  • Figure 3: Accuracy under data scarcity conditions (90%, 50%, and 10%).
  • Figure 4: Accuracy under noisy input conditions.