Hard landing is a typical flight safety incident, and interpretability plays an important role in flight safety research. However, existing studies failed to provide good interpretability of the reasons for hard landing incidents and suffer from low prediction accuracy. To address the above problems, in this paper we propose CurveCluster+, a curve clustering method based on quick access recorder (QAR) data for hard landing risk evaluation. Specifically, we first conduct an in-depth analysis on hard landing flights by comparing key QAR parameter curves with the group behavior, based on which we establish a two-level hierarchical classification of hard landing incidents according to the hard landing patterns. Then we extract curve-level features from key QAR parameters through interpolation and resampling. After that we turn the classic K-means clustering into a semi-supervised algorithm by incorporating some expert experience and apply it on the curve-level features to automatically recognize the hard landing patterns. Finally, we propose a risk evaluation model based on the clustering results to discover high-risk flights from normal ones. We evaluate our method on a QAR dataset of 37,943 Airbus 320 aircraft flights. The results show that compared with other state-of-the-art data-driven methods, CurveCluster+ provides strong interpretability of hard landing incidents and exhibits good performance in recognizing hard landing patterns (the overall accuracy of our method reaches up to 92.99%). Moreover, it only requires a handful of hard landing samples to discover high-risk flights from tremendous normal landing flights, which is critical for flight safety warnings.

Flight safety is a key issue in the aviation industry. Recently, with the prevalence of flight data recording systems, some deep learning-based studies have been devoted to predicting safety incidents based on flight data. However, these studies, although they exhibit higher prediction accuracy, have largely neglected the interpretability analysis of safety incidents which is of great concern to airlines and pilots. To address this issue, we define flight safety prediction as a multiscale time series classification problem and propose an interpretable model named IMTCN to provide both accurate predictions and high interpretability of flight safety. First, multiple temporal convolutional networks (TCNs) are utilized to capture local representations and long effective histories from multivariate flight data. Because different flight parameters are collected with diverse sampling frequencies, multiple TCNs are used to handle these parameters separately. Then, we creatively adapt the class activation mapping (CAM) method, which has been used for interpretation in image classification, and combine it with the TCN to provide flight data interpretability. The established model can pinpoint key flight parameters and corresponding moments that contribute most to safety incidents. Experimental results on a real-world dataset with 37,943 Airbus A320 aircraft flights show that our model outperforms the baselines on the task of exceedance classification and prediction 2 seconds and 4 seconds in advance, and case studies demonstrate its superb interpretability for flight safety analysis.

The Vehicle-to-Everything (V2X) communication, as the fundamental part of intelligent transport system, has the potential to increase road safety and traffic efficiency. However, conventional static infrastructures like roadside units (RSUs) often encounter overload issues due to the uneven spatiotemporal distribution of vehicles. Although the line-of-sight (LoS) propagation characteristics and high mobility of unmanned aerial vehicles (UAVs) have brought about UAV-assisted vehicular communication. The scarce spectrum resources, complex interference, restricted energy budgets, and the mobility of automobiles still pose significant challenges. In this paper, we combine mean-field game (MFG) theory with multi-agent reinforcement learning (MARL) to allocate resources for RSUs and UAVs in non-orthogonal multiple access (NOMA) V2X communication networks. To find rational and reasonable global solutions for infrastructures under power and QoS constraints, a joint sub-band scheduling and transmit power allocation problem is addressed. The MARL technique is utilized to endow agents with the capability of self-learning. MFG theory is employed to tackle the tremendous overhead in agent interactions. The integration of MFG and MARL enables infrastructures to act as agents, engaging in mutual interactions and considering the impact of the surrounding environment, to achieve maximum global energy efficiency. Simulation results demonstrate the effectiveness of UAV-assisted V2X communication and prove that the proposed method outperforms a state-of-the-art resource allocation scheme in both average energy efficiency and probability of failure.

Urban mobility is enjoying much attention due to increasingly serious traffic and environment problems in cities. Private cars are the most important component of urban road traffic. However, current research on urban mobility seldom employs travel data from private cars due to the lack of access to corresponding data acquisition. This problem can be solved with the massive application of Electronic Registration Identification (ERI), which is an emerging technology to identify a unique vehicle based on Radio Frequency Identification (RFID). This paper proposes a framework for discovering the urban mobility of private cars based on ERI data. The main research content includes two parts: trajectory segmentation and attractive area mining. In the trajectory segmentation, stay segments in trajectories are identified by Bayes classification based on the link travel time distribution model. The model parameters of each link are trained by Expectation Maximization(EM) algorithm. In attractive area mining, a spatial clustering algorithm based on data field is introduced. Finally, we utilized real-world data into the proposed algorithms. The experimental results show that the proposed method can accurately segment the trajectory, and the visualization of attractive areas reveals the urban mobility characteristics of private cars.

Hard landing, as one of the most frequent flight safety incidents during the landing stage, is highly concerned by the aviation industry. Recently, the popularization of Quick Access Recorder (QAR), a modern flight data recording system, has made it possible to collect large volume of flight parameters and incorporate state-of-the-art AI technologies to improve flight safety. However, due to the complex, multivariate, and highly specialized nature of QAR data, most existing studies either suffer from information loss caused by rough feature extraction methods, or rely solely on black-box models with no interpretations, making themselves difficult to achieve satisfactory performance in terms of prediction and explainability. To address this issue, we propose a novel attention-driven model named SDTAN (Scalable Deep Time-Aware Attention Network), which can accurately predict hard landing events and provide interpretable insights to help reveal the possible reasons leading to the events. Specifically, SDTAN fully captures information to learn the local representations of parameters, and leverages the time-interval attention mechanism to focus on the entire temporal pattern of flight over the relevant time intervals. It further re-encodes the representations of parameters in a global view and learns the global effect of parameters on the predicted output to uncover the ones which strongly indicate the flight safety status, enabling both high prediction accuracy and qualitative interpretability. We conduct experiments on real-world QAR datasets of 37,920 Airbus A320 flight samples. Experimental results demonstrate that SDTAN outperforms other state-of-the-art baselines and provides effective interpretability by visualizing the importance of parameters.