Recent studies have revealed the significant potential of spatiotemporal graph neural networks for multivariate time series forecasting with missing values. These methods typically represent interactions between time series as graph structures, where each time step is encoded as a graph node. Existing methods largely rely on self-learned or predefined graph structures to capture spatial dependencies within temporal data. However, in real-world applications, interactions between nodes are often directional and may span long temporal distances. Moreover, at high missing rates, interpolation across time scales often produces varied results in reconstructing missing time series. To address these challenges, this paper investigates the directed interactions of missing values in time series an d their multi-scale interpolation process. We propose the Multi-scale Temporal Interpolation Patch Graph Neural Network (MTIPG), which enables precise spatiotemporal modeling with limited data. Specifically, we first design a hierarchical structure combined with dilated convolutions to capture feature interpolation of missing sequences at specific time scales. Then, we quantify the positional relationships between patches using the dot product similarity between the head and tail embeddings of missing sequences, facilitating implicit modeling of missing variables and directional information propagation. Finally, we integrate these modules to generate accurate prediction results. Extensive experiments on four real-world datasets demonstrate that MTIPG consistently outperforms state-of-the-art baselines across various missing rates, achieving accurate predictions for all variables' future values, even with up to 60% missing data.

Flight safety remains a central concern in civil aviation. Recently, increasing attention has been given to leveraging high-dimensional temporal flight data, typically collected by Quick Access Recorders (QAR), to predict safety events. However, most existing studies focus on individual events, overlooking the latent correlations among multiple events. For instance, during landing, a maneuver that reduces the risk of one event may inadvertently increase the risk of another. Predicting multiple events introduces three main challenges: 1)handling parameters recorded at inconsistent sampling rates, 2) learning task-specific parameter importance for interpretability, and 3) modeling complex temporal dependencies for accuracy. To address these, we propose MultiSafe, a deep multi-task learning model for predicting and interpreting multiple flight safety events. First, to process parameters with heterogeneous frequencies, we introduce a Multi-Scale Shared Encoder with adaptive convolutional kernels to unify representations across tasks. Next, a gating-based Parameter Selector learns task-specific parameter importance, enabling interpretable predictions. Finally, a Temporal Decoder with fine-grained attention captures intricate temporal dependencies among parameters. Experiments on a dataset of 37,518 A320 flight records demonstrate that MultiSafe outperforms state-of-the-art baselines in prediction accuracy, while its interpretability offers actionable insights to assist pilots in enhancing flight safety.

Graph neural network (GNN)-based approaches have achieved remarkable success in temporal knowledge graph (TKG) reasoning. Despite these advances, two critical challenges remain: 1) inadequate modeling of local contextual dynamics, which limits the adaptability of entity and relation representations to specific queries and 2) inadequate mechanisms for handling emerging patterns, that is, novel interactions absent from historical data, which reduces predictive performance in dynamic environments. To address these limitations, we propose TCDR-PD, a temporal and contextual dynamic representation network with pattern decomposition. TCDR-PD introduces a temporal and contextual dynamic representation learning (TCDR) module to capture both global temporal trends and query-specific contextual dynamics, enabling more precise embeddings. Additionally, the pattern decomposition (PD) prediction module explicitly disentangles the prediction of recurring and emerging patterns, enabling tailored strategies to improve reasoning performance. Experiments on four benchmark datasets demonstrate that TCDR-PD outperforms state-of-the-art methods, effectively supporting stable reasoning over evolving TKGs.

Space-air-ground integrated vehicular networks (SAGIVNs) can provide long-distance communication service with wide coverage for ground users such as vehicles. However, scarce spectrum resources and long-distance transmission result in high path loss as well as latency. As relay stations, unmanned aerial vehicles (UAVs) play key roles in improving transmission quality between space and ground, i.e., satellites and vehicles, whose configuration of resources highly influences network performance. In this paper, we focus on joint resource allocation for UAVs in SAGIVNs. Specifically, the joint optimization problem in user association, trajectory design, and power control is addressed. By considering the trade-off between transmission rate and energy consumption in SAGIVNs, we propose an energy-efficient joint resource allocation approach named ERDM. Firstly, vehicles are assigned to UAVs based on their positions. hen, we formulate the optimization problem to maximize energy efficiency, the sum rate with unit power cost, with consideration of service quality constraints. To reduce the complexity of the problem, we employ multi-agent deep reinforcement learning framework to obtain optimal solutions. By incorporating the behavior of other agents, UAVs learn to allocate resources for themselves and update Q-networks using gained experiences in distinctive observations and feedback rewards. Simulations reveal ERDM outperforms other benchmarks by up to 24.72% in energy efficiency under different circumstances.

Hard landings, as a common type of aviation incident, have consistently attracted the attention of airlines and aviation authorities. In recent years, the widespread adoption of Quick Access Recorder (QAR) systems has led numerous researchers to focus on predicting hard landing events through the analysis of QAR data. However, most studies treat QAR data as standard time series without fully accounting for its unique characteristics. Unlike typical time series, QAR data exhibits limited periodicity and trends, making it challenging for traditional modeling approaches to capture its complex patterns. Furthermore, model interpretability, as an essential aspect for practical deployment and decision-making, remains insufficiently explored. To address these issues, we propose a Fine-Grained Time and Hidden Feature Learning model for Interpretable Hard Landing Prediction based on QAR Data (TF-QAR). Specifically, we introduce a novel fine-grained temporal aggregation module, which dynamically extracts the importance of each time step through learnable parameters, to efficiently model the temporal dependencies in QAR data. Additionally, we develop a feature aggregation module that introduces a learnable adjacency matrix to model the significance of flight features and their interrelationships, revealing not only key parameters that directly influence hard landings, but also hidden parameters that are indirectly related. We conducted extensive experiments using a dataset of 37,929 real A320 flight segments in China. The results demonstrate that our model outperforms existing state-of-the-art baselines. Moreover, by visualizing the learnable parameters, TF-QAR provides interpretable insights valuable for pilot decision-making, offering practical support for the prevention and management of hard landing events.

Flight safety incidents, such as hard landings and tail strike risks, represent critical concerns during the landing phase. Although Quick Access Recorder (QAR) systems collect extensive multivariate flight data, previous studies have faced challenges in effectively modeling the complex interdependencies between flight parameters, which has limited their ability to predict multiple safety incidents simultaneously. To address this issue, we propose a novel model, named MDGNN, to capture hidden spatio-temporal dependencies and predict both hard landing and tail strike risk incidents. Specifically, we employ temporal convolutional networks (TCNs) to extract both localized representations and long-term temporal trends from multivariate flight data, ensuring the standardization of flight parameters across varying frequencies. Additionally, we are the first to construct a dynamic graph to model temporal relationships, applying a dynamic graph neural network and a temporal convolution module to accurately capture intricate spatial and temporal dependencies. Extensive experiments conducted on 37,904 Airbus A320 flight samples demonstrate that the MDGNN model surpasses state-of-the-art baselines with high prediction accuracy. Furthermore, a case study visualizing key flight parameters highlights the model’s ability to reveal the root causes of safety exceedances, offering valuable insights for flight safety analysis.

Robustness is paramount for ensuring the reliability of knowledge graph models in safety-sensitive applications. While recent research has delved into adversarial attacks on static knowledge graph models, the exploration of more practical temporal knowledge graphs has been largely overlooked. To fill this gap, we present the Adaptive Temporal Perturbation Framework (ATPF), a novel adversarial attack framework aimed at probing the robustness of temporal knowledge graph (TKG) models. The general idea of ATPF is to inject perturbations into the victim model input to undermine the prediction. First, we propose the Temporal Perturbation Prioritization (TPP) algorithm, which identifies the optimal time sequence for perturbation injection before initiating attacks. Subsequently, we design the Rank-Based Edge Manipulation (RBEM) algorithm, enabling the generation of both edge addition and removal perturbations under black-box setting. With ATPF, we present two adversarial attack methods: the stringent ATPF-hard and the more lenient ATPF-soft, each imposing different perturbation constraints. Our experimental evaluations on the link prediction task for TKGs demonstrate the superior attack performance of our methods compared to baseline methods. Furthermore, we find that strategically placing a single perturbation often suffices to successfully compromise a target link.

The high mobility of automobiles causes channel estimation uncertainties in vehicle-to-vehicle (V2V) communications. Moreover, scarce spectrum resources further bottlenecked the Quality of Service (QoS) in vehicular communication networks. Nonorthogonal multiple access (NOMA) technique is introduced to solve these problems, which reuses resource blocks (RBs) to improve the network’s throughput and reduce latency with exploiting the power domain. In this article, we devise a multiagent reinforcement learning (MARL)-based resource allocation method for roadside units (RSUs) in vehicular communication networks. A joint sub-band scheduling and transmit power allocation problem is investigated, aiming to find rational and reasonable solutions at each RSU, under QoS constraints and power limits, from a global perspective. Due to the complicated structure of this high-dimensional optimization, it is extremely challenging to accomplish in polynomial time. The proposed method adopts MARL technique in RSUs to actualize collaboration and self-learning. RSUs act as agents, collectively interacting with the environment to maximize global energy efficiency, the ratio of the sum rate received at vehicles to the total power consumption of relevant RSUs, by trading-off between transmission rate and link interference. With distinctive observations and relevant feedback rewards, each agent learns to improve spectrum and power allocation by updating Q-networks using the gained experiences. The proposed method has much less complexity compared to the centralized implemented method, but still provides approximate performances. Simulation results demonstrate that the proposed method outperforms two existing baselines and a state-of-the-art power allocation scheme in terms of both average energy efficiency and probability of failure.

Accurate long sequence time series forecasting (LSTF) remains a key challenge due to its complex time-dependent nature. Multivariate time series forecasting methods inherently assume that variables are interrelated and that the future state of each variable depends not only on its history but also on other variables. However, most existing methods, such as Transformer, cannot effectively exploit the potential spatial correlation between variables. To cope with the above problems, we propose a Transformer-based LSTF model, called Graphformer, which can efficiently learn complex temporal patterns and dependencies between multiple variables. First, in the encoder’s self-attentive downsampling layer, Graphformer replaces the standard convolutional layer with an dilated convolutional layer to efficiently capture long-term dependencies between time series at different granularity levels. Meanwhile, Graphformer replaces the self-attention mechanism with a graph self-attention mechanism that can automatically infer the implicit sparse graph structure from the data, showing better generality for time series without explicit graph structure and learning implicit spatial dependencies between sequences. In addition, Graphformer uses a temporal inertia module to enhance the sensitivity of future time steps to recent inputs, and a multi-scale feature fusion operation to extract temporal correlations at different granularity levels by slicing and fusing feature maps to improve model accuracy and efficiency. Our proposed Graphformer can improve the long sequence time series forecasting accuracy significantly when compared with that of SOTA Transformer-based models.

Active learning alleviates labeling costs by selecting and labeling the most informative examples from an unlabeled pool. However, most existing active learning approaches estimate informativeness with uncalibrated confidence, resulting in unreliable informativeness estimation. These approaches generally ignored two significant issues caused by uncalibrated confidence methods. Firstly, the average uncalibrated confidence generated by modern neural networks is usually higher than the accuracy. Secondly, examples located near the decision boundaries are unstable during prediction when the target model updates parameters in the last several epochs, even throughout the training process. This phenomenon, caused by the forgetting characteristic of neural networks , has a significant impact on some specific models that estimate the informativeness by predicted probability vectors or pseudo labels. To address these issues, in this paper, we propose a novel active learning approach to reliably estimate informativeness with calibrated confidence. Specifically, we integrate the intermediate predictions for each unlabeled example , generated by the target model during the training process, to generate calibrated confidence. The calibrated confidence can capture a tendentious label from an indecisive subset of the class space. We show that the calibrated confidence with tendentiousness can maintain the ability of correct predictions. The empirical results demonstrate that our approach outperforms the state-of-the-art active learning methods on image classification tasks.

The demand-responsive customized bus has been operated in real life, which is a crucial way to improve the service quality and efficiency of the urban public transportation system. Reasonable station and line planning can enhance customized bus competitiveness in residents’ travel mode. Most previous studies on optimizing customized bus lines rely on historical passenger volume and travel time to generate static schemes, but the actual operation process of customized bus is often in uncertain circumstances, such as road congestion. The static strategy will occur deviations in this situation. This study proposes a novel planning method to address the above issue. First, a spatiotemporal clustering algorithm is proposed to generate joint stations based on the passenger travel demand. Second, the method models the multiline customized bus optimization problem as a Markov decision process and uses a multiagent deep reinforcement learning algorithm to ensure effective training and response to incomplete information scenarios. Finally, the rationality of the proposed planning method is verified in a case study of customized bus area in Chongqing, China. Compared with the latest heuristic optimization algorithm, our method can effectively reduce the operating and passenger costs in complex environments.

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.

Customized bus is considered an effective means to alleviate traffic congestion and reduce traffic-related environmental pollution caused by the increasing number of private cars. Exploring potential passenger information as the first stage of customized bus service has become a popular topic. Unlike manual investigation and passenger request methods, current studies utilize data mining methods to actively explore potential passengers from various historical travel data. However, the existing data mining methods only consider the spatiotemporal features of potential passengers and neglect the semantic features related to customized bus services, which play an important role in determining whether passengers are willing to use services. In this paper, we treated the exploration of potential customized bus passengers as a binary classification problem based on private car trajectory data. Then, we propose a novel data mining method, named iTrAdaboost-DTCN, which combines the strengths of deep learning and transfer learning. In detail, it integrates state-of-the-art deep neural networks by constructing a deep trajectory classification network (DTCN), which can automatically extract semantic feature representations to help improve classification accuracy. Due to the lack of city-wide labeled customized bus passenger information in practice, it also integrates instance-based transfer learning through improved TrAdaboost, which solves the learning problem of the target classification domain with limited labeled samples. Experimental results demonstrate that our method can explore potential passengers more effectively than other baseline methods. Furthermore, we apply our method to real-world scenarios and compare three travel characteristics of identified customized and non-customized bus passengers.

Intelligent logistics empowered by artificial intelligence (AI) has become an inevitable trend in the development of modern logistics, thus, a convenient and efficient logistics system has attracted widespread attention. However, how to use AI to execute computation-intensive applications on resource-constrained logistics vehicles (LVs) still faces enormous challenges. For the dependent applications in intelligent logistics, this article investigates a task dynamic offloading strategy for LVs-edge collaboration with multiple dependent tasks, considering the intertask dependency, to guarantee the Quality-of-Service (QoS) requirements of LVs. First, the dependent application ARCore is modeled and transformed into a model with a linear execution sequence. Then, based on this task model, the joint task offloading and resource allocation problem is formulated. The goal is to minimize the weighted sum cost of the execution delay and energy consumption while guaranteeing the delay tolerance and computing resource constraints of the tasks. Furthermore, we propose a federated LVs-edge collaborative computation (FECC) offloading framework to solve the optimization problem, which only requires each agent to share its model parameters without sharing local training data, thereby reducing the computation complexity and signaling overhead of the multiagent training process. Numerical results show that the proposed strategy has significant advantages in terms of total system cost compared to the baseline strategy.

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.

Information popularity prediction on social media platforms is a valuable and challenging issue.However, existing studies either neglect the correlation among different cascades, or lack a comprehensive consideration of user behavioral proximity and preference with respect to different messages.In this paper we propose a graph neural network-based framework named HeDAN (heterogeneous diffusion attention network), which comprehensively considers various factors affecting the information diffusion to predict the information popularity more accurately.Specifically, we first construct a heterogeneous diffusion graph with two types of nodes (user and message) and three types of relations (Friendship, Interaction, and Interest).Among them, Friendship reflects the strength of social relationship between users, Interaction reflects the behavioral proximity between users, and Interest reflects user preference to messages.Next, a graph neural network model with hierarchical attention mechanism is proposed to learn from these relations.Specifically, at the nodelevel, we utilize the graph attention network to learn the subgraph structure and generate the representations of nodes under each specific relationship.At the semantic-level, we distinguish the importance of different nodes in different relations via multihead self-attention mechanism.Extensive experimental results on three datasets show the superior performance of our proposed model over the state-of-the-arts.

Accurate traffic prediction is critical to the effectiveness of intelligent transportation systems. However, traffic data are highly nonlinear with complicated dynamic spatio-temporal correlations, accurate traffic forecasting, particularly long-term forecasting, remains a difficulty. Existing models generally learn a fixed graph to capture spatial correlations, which makes them difficult to effectively capture changing spatial dynamics over time, resulting in poor prediction outcomes. To tackle these challenges, we propose a new spatio-temporal graph convolution network model, named Spatio-Temporal Attention-based Graph Convolution Network (STAGCN), which jointly fuses dynamic evolving spatial correlations and long-term temporal correlations to improve the performance. First, we design a spatio-temporal multi-head self-attention module to capture both spatial heterogeneity and temporal correlations. Second, we propose an adaptive evolving graph convolution module that can learn a new graph at each time step and make STAGCN evolve dynamically. Meanwhile, self-attention is used to construct a dynamic adjacency matrix to further capture spatial correlations. In addition, we optimize the original Transformer by employing relation-aware attention mechanism to make it better suitable for time series prediction, thereby improving the long-term prediction performance of the model. Extensive experiments are conducted on two real-world datasets, demonstrating that our proposed model achieves state-of-the-art performance and consistently outperforms other baselines.

A large volume of commuting private cars cause serious traffic congestion, especially during morning and evening rush hours, and the low occupancy rate of commuting private cars bring a huge waste of resources. Carpooling among commuting private cars can reduce vehicle volume and alleviate traffic congestion. Moreover, commuters matching is the key issue to solve for realizing stable carpooling. This paper designs a commuting trajectory based stable carpooling model (CT-CSC) for commuting private cars, and proposes a particle swarm-based commuter matching approach for stable carpooling (PSCMA). The objective of CT-CSC model is minimizing carpooling cost. In the proposed PSCMA, the particle swarm and fitness calculation rules are redesigned to make it suitable for the CT-CSC model. The real-world RFID electronic identification data in Chongqing is used for experimental verification. Experimental results show the effect of the parameter inertia factor ω for the PSCMA. In addition, compared with genetic algorithm, hill climbing algorithm and simulation annealing algorithm, the performance of the PSCMA is outstanding. Furthermore, 1,003 commuters passing through the Huanghuayuan Bridge in Chongqing are selected to carpool, and we analyzed the reduction of the number of commuters, mileages and gasoline

Ride-sharing cars are private vehicles held by individuals or provided by ride-hailing companies for designated drivers to offer taxi-like services. Recently, various ride-sharing cars have emerged around the city with the popularity of online ride-hailing services. Identifying them is the critical task of transportation management. However, less work focuses on this issue due to the lack of city-wide private vehicles’ trajectory data and labeled ride-sharing cars. Fortunately, data collected by advanced sensing technology, such as electronic registration identification (ERI) of the motor vehicle data collected by radio-frequency identification (RFID) technology, provide us with an opportunity to detect ride-sharing cars from a data-driven aspect. This article proposes detecting ride-sharing cars via self-taught learning (STL) using ERI data, named STL-detector, which is accurate with very little labeled information. In detail, STL-detector consists of two components. In theunsupervised feature learningcomponent, we construct a 3-D convolutional neural networks (3-D-CNN) autoencoder trained with an amount of unlabeled data, which forms a succinct high-level input representation and significantly improve detection performance. In thesupervised classificationcomponent, we utilize the random forest (RF) as the classifier, which is trained on very little labeled data, to detect ride-sharing cars/others. The experimental results demonstrate that our STL-detector model can detect ride-sharing cars with better performance compared with other baselines on a set of train and test samples. Furthermore, we apply our model to a real-world scenario to detect ride-sharing cars and conduct a comparative analysis on the behavior of detected ride-sharing cars and taxis.

With the deepening of the urbanization process, the ownership of urban private cars continues to increase, resulting in severe urban traffic congestion and environmental problems. The customized bus, as an emerging public transportation mode, is considered an effective means to alleviate the above problems. This article employs electronic registration identification (ERI) data of vehicles to design customized buses for private cars, consisting of two components: 1) discovering private car commuters and 2) designing customized bus schemes. First, based on the spatial–temporal similarity and high-frequency characteristics of commuting trips, we mined the urban private car commuters and their corresponding commuting trips as the demand for customized buses. Then, we constructed the customized bus model, which targets the number of served passengers with the constraints, such as the trip time window, bus capacity, passenger load rate, etc. In the model, intermediate stops are not set to ensure bus punctuality and passenger experience, and buses of various capacities are employed to ensure effectiveness and efficiency. The differential evolution algorithm was utilized to find the optimal solution for the model. In the experiments, we carried out relevant verification based on Chongqing’s one-week ERI data. The experimental results showed customized bus schemes for various cases and verified the superior performance of our algorithm by comparing it with general optimization algorithms. Besides, through numerical calculation and traffic simulation, the excellent potential for customized buses in reducing urban transportation energy consumption and urban road congestion is illustrated.

Private cars’ travel has been one of the main factors causing urban traffic congestion. Especially during morning and evening rush hours, private car commuters bring a significant burden to traffic. However, there is very little literature on them due to the lack of access to relevant data. A real-world dataset containing vehicle passing records of Electronic Registration Identification (ERI) of vehicles provides us with an opportunity to research private car commuters. We propose a regular behavior-based model to recognize private car commuters. In the model, a regular behavior-based definition of private car commuters is firstly proposed. Then, TDSP(Time dependent shortest path)-based distance measurement and a hierarchical clustering method are designed to extract regular behaviors. Furthermore, we utilize a regular threshold$p $to help determine regular behaviors. The experiment, which is conducted on a real-world dataset containing one-week vehicle passing records in Chongqing of China, validates the effectiveness and accuracy of the proposed model. Moreover, we analyze the mobility pattern of private car commuters, and some typical mobility patterns of them are successfully found.

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.

The influence maximization (IM) problem, which aims to find$k$most influential individuals from a social network to maximize the influence spread, has been extensively studied. Existing works all rely on the assumption that influenced individuals will definitely try to propagate the information to their neighbors through social trust. However, in real-world this assumption can be over-simplistic since trust-levels among different individuals usually exhibit high diversity. As a result, an influenced individual may choose not to further propagate the information to his neighbors. Motivated by the observation, in this paper we propose a new accepted influence maximization (AIM) problem where the influenced individuals are further divided into two subgroups, i.e., accepted and active, where only active individuals will continue to propagate the information. We prove this problem is NP-hard and the objective function is submodular, based on which a greedy algorithm is proposed with ($1-1/e-\epsilon$) approximation guarantee. Considering the low computational efficiency of the greedy algorithm, we further propose a scalable path-based algorithm ALDAG. We conduct experiments on real datasets and the results demonstrate the effectiveness and efficiency of our method.

Timestamps are often problematic in Internet-of-Things (IoT) systems due to time synchronization problems of distributed radio-frequency identification (RFID) readers or sensors. This issue may seriously affect the data quality in some fields, such as transportation. A typical IoT application in transportation is electronic registration identification of the motor vehicle (ERI), an emerging traffic data acquisition technology based on RFID. ERI data play a vital role in intelligent transportation. However, the data quality is often affected seriously by the inaccurate timestamps, which arise from the time-unsynchronized distributed ERI readers. To solve this issue, we propose a novel framework, data repairing of time synchronization problems (DR-TSP), which can detect the time-unsynchronized ERI readers and correct timestamp-deviated ERI data. Precisely, DR-TSP consists of three components. Problem reader discovery component employs a statistics-based method to detect the time-unsynchronized ERI readers and discovers the clock leaps of the problematic ERI reader through a smoothing-based method. Travel-time estimation component constructs a spatial correlative travel-time estimation model based on the neural network to infer timestamp deviation. The influence of clock deviation is considered in the model training. Data correction component utilizes the above results to correct the timestamp-deviated data. Experiments over large-scale ERI data collected from a big China city, Chongqing, show that our method can significantly improve data quality.

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.