Comparative Analysis of Machine Learning Methods with Chaotic AdaBoost and Logistic Mapping for Real-Time Sensor Fusion in Autonomous Vehicles: Enhancing Speed and Acceleration Prediction Under Uncertainty

Sensors · Haziran 2025

YÖKSİS Kayıtları

Sensors · 2025 SCI-Expanded

DOKTOR ÖĞRETİM ÜYESİ ONUR İNAN →

Makale Bilgileri

DergiSensors

Yayın TarihiHaziran 2025

Cilt / Sayfa25

DOI10.3390/s25113485

Scopus ID2-s2.0-105007843582

Erişim🔓 Açık Erişim

Özet CAB’s chaos-enhanced ensemble learning sets a new standard for AV sensor fusion, achieving unmatched prediction accuracy. The integration of Apache Kafka 2.13-3.4.0 and MongoDB 7.0.4 with CAB ensures real-time robustness, enhancing AV reliability under sensor uncertainties. Highlights: What are the main findings? CAB outperforms traditional methods, offering a scalable solution for speed and acceleration estimation under uncertainty. The simulated results demonstrate CAB’s potential, achieving superior safety (TTC: 3.2 s) and comfort (jerk: 0.15 m/s3) metrics, though real-world validation is needed. What is the implication of the main finding? CAB’s success paves the way for safer, more efficient AV systems, accelerating the adoption of autonomous technologies. The need for real-world testing highlights a pathway to refine CAB, potentially establishing it as a cornerstone in AV development beyond simulation constraints. This study presents a novel artificial intelligence-driven architecture for real-time sensor fusion in autonomous vehicles (AVs), leveraging Apache Kafka and MongoDB for synchronous and asynchronous data processing to enhance resilience against sensor failures and dynamic conditions. We introduce Chaotic AdaBoost (CAB), an advanced variant of AdaBoost that integrates a logistic chaotic map into its weight update process, overcoming the limitations of deterministic ensemble methods. CAB is evaluated alongside k-Nearest Neighbors (kNNs), Artificial Neural Networks (ANNs), standard AdaBoost (AB), Gradient Boosting (GBa), and Random Forest (RF) for speed and acceleration prediction using CARLA simulator data. CAB achieves a superior 99.3% accuracy (MSE: 0.018 for acceleration, 0.010 for speed; MAE: 0.020 for acceleration, 0.012 for speed; R2: 0.993 for acceleration, 0.997 for speed), a mean Time-To-Collision (TTC) of 3.2 s, and jerk of 0.15 m/s3, outperforming AB (98.5%, MSE: 0.15, TTC: 2.8 s, jerk: 0.22 m/s3), GB (99.1%), ANN (98.2%), RF (97.5%), and kNN (87.0%). This logistic map-enhanced adaptability, reducing MSE by 88% over AB, ensures robust anomaly detection and data fusion under uncertainty, critical for AV safety and comfort. Despite a 20% increase in training time (72 s vs. 60 s for AB), CAB’s integration with Kafka’s high-throughput streaming maintains real-time efficacy, offering a scalable framework that advances operational reliability and passenger experience in autonomous driving.

Yazarlar (2)

Mehmet Bilban

ORCID: 0000-0002-1524-031X

Onur Inan

Anahtar Kelimeler

AdaBoost Apache Kafka Artificial Neural Networks autonomous vehicles Chaotic AdaBoost Gradient Boosting k-Nearest Neighbors machine learning Random Forest