Deep Fuzzy Interpretive Modeling for Capability Exploration in Autonomous Vehicle Communication Architectures

Abstract

Autonomous vehicular communication systems are essential for intelligent transportation, enabling continuous data exchange among vehicles, infrastructure, and centralized networks. These systems rely on key parameters such as Random Access Memory (RAM), storage capacity, transmission rate, and trust factor to ensure efficient and reliable communication. In dynamic environments, accurately evaluating communication unit capability is crucial for maintaining system performance, safety, and optimal resource utilization. Traditional assessment methods depend on manual configuration checks and threshold-based monitoring, treating parameters independently and failing to capture complex interdependencies. This limitation results in unreliable capability estimation in real-time scenarios. To improve automation and prediction accuracy, machine learning models including Decision Tree Regressor (DTR), Orthogonal Matching Pursuit Regressor (OMPR), and K-Nearest Neighbors Regressor (KNNR) are utilized. However, these models struggle with nonlinear relationships, noisy data, and generalization in complex datasets. To address these issues, this study proposes a hybrid Deep Fuzzy Regression (DFR) model that integrates Deep Fuzzy Encoding (DFE) with Random Forest Regressor (RFR) and Linear Regression (LR) through an ensemble approach. The DFE component effectively handles uncertainty and gradual feature variations, while the hybrid model enhances robustness and predictive performance. The system follows a structured pipeline including data preprocessing, feature engineering, model training, and evaluation. Performance is measured using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²). Results indicate that the proposed DFR model achieves reliable and consistent capability assessment, making it suitable for real-time vehicular communication systems and improving overall efficiency and decision-making.