Improving driver safety and trip quality through real-time anomaly detection with multi-model learning in taxi services

Vehicle and driver detection in real-world traffic scenarios with an improved YOLO model

IYOLO, an enhanced YOLOv8-based framework for simultaneous detection and classification of vehicles, drivers, and passengers on highways, aiming to distinguish drivers from passengers and establish one-to-one vehicle-driver associations is proposed.

Improving road safety through optimized and interpretable ensemble models of driver behavior

These findings demonstrate that RF–Bayesian provides a stable, interpretable, and computationally efficient framework for smartphone-based driver behavior classification, with practical relevance for telematics, fleet safety management, driver feedback systems, and intelligent transportation safety applications.

QAR Data-Driven Flight Anomaly Detection and Risk Warning: A Review of Statistical Learning and Machine Learning Methods in Aviation Safety

Quick Access Recorder (QAR) data provide high-dimensional onboard flight records that are increasingly used for data-driven aviation safety analysis. As flight operations become more complex, conventional manual monitoring and threshold-based exceedance detection are often insufficient for identifying evolving risks in a timely and interpretable manner. This paper reviews QAR data-driven methods for flight anomaly detection and risk warning from the perspective of statistical learning and aviation data science. First, the main characteristics of QAR data are summarized, including multi-source heterogeneity, temporal dependence, missing values, noise, and severe class imbalance. Common preprocessing techniques, such as missing-value imputation, trajectory correction, feature engineering, downsampling, and imbalanced-data handling, are then reviewed. Second, existing methods are organized into four groups: statistical monitoring and rule-based methods, clustering and unsupervised anomaly detection, Bayesian and probabilistic risk reasoning, and hybrid machine learning with explainable AI. Representative approaches include statistical process control, association rules, Gaussian mixture models, CurveCluster, Fast-DTW, Bayesian networks, dynamic Bayesian networks, VAE-LSTM, MAD-XFP, and XGBoost with SHAP interpretation. The review further discusses typical applications in landing risk warning, takeoff risk assessment, flight operation pattern recognition, and aviation noise prediction. Finally, key challenges are summarized, including model interpretability, real-time deployment, cross-aircraft and cross-airport generalization, data quality, causal reasoning, and privacy-preserving collaboration. This review provides a structured reference for using QAR data to support aviation safety assessment, risk warning, and operational decision-making.

Driver behavior monitoring: an embedded and incremental hybrid machine learning approach

This research establishes a statistically robust and deployable foundation for next-generation intelligent transportation systems by coupling Bayesian learning theory with edge computing design.

A Smart City Framework for Real-Time Traffic Monitoring and Accident Detection

Smart city transport networks must be highly adaptive, meaning they can quickly adjust to new road conditions. This research aims to provide a smart city architecture that can detect accidents and track traffic in realtime using edge-cloud computing, deep learning-based video analytics, and IoT sensing. In order to correctly analyse traffic and detect accidents, the platform continuously gathers heterogeneous data from roadside cameras and automobile sensors, performs essential analytics at the edge to decrease latency, and runs robust cloud analytics. The software is able to do precise traffic analyses and detect accidents because of this. Abnormal traffic event spatial and temporal patterns are captured using a mixed deep learning architecture employing recurrent neural networks and convolutional neural networks. Also, for proactive traffic management, a module that forecasts traffic patterns can be used. The proposed system exhibits low response time, robustness under varying traffic and lighting conditions, and outstanding detection accuracy, according to the experimental results. The system is both scalable and inexpensive, and it improves urban mobility, response times to emergencies, and road safety.

Real-time traffic congestion detection using smartphone multi-sensor data and stacked ensemble learning