Aircraft landing time (ALT) prediction is crucial for air traffic management, especially for arrival aircraft sequencing on the runway. In this study, a trajectory image-based deep learning method is proposed to predict ALTs for the aircraft entering the research airspace that covers the Terminal Maneuvering Area (TMA). Specifically, the trajectories of all airborne arrival aircraft within the temporal capture window are used to generate an image with the target aircraft trajectory labeled as red and all background aircraft trajectory labeled as blue. The trajectory images contain various information, including the aircraft position, speed, heading, relative distances, and arrival traffic flows. It enables us to use state-of-the-art deep convolution neural networks for ALT modeling. We also use real-time runway usage obtained from the trajectory data and the external information such as aircraft types and weather conditions as additional inputs. Moreover, a convolution neural network (CNN) based module is designed for automatic holding-related featurizing, which takes the trajectory images, the leading aircraft holding status, and their time and speed gap at the research airspace boundary as its inputs. Its output is further fed into the final end-to-end ALT prediction. The proposed ALT prediction approach is applied to Singapore Changi Airport (ICAO Code: WSSS) using one-month Automatic Dependent Surveillance-Broadcast (ADS-B) data from November 1 to November 30, 2022. Experimental results show that by integrating the holding featurization, we can reduce the mean absolute error (MAE) from 82.23 seconds to 43.96 seconds, and achieve an average accuracy of 96.1\%, with 79.4\% of the predictions errors being less than 60 seconds.

Electric Vehicle (EV) charging demand and charging station availability forecasting is one of the challenges in the intelligent transportation system. With accurate EV station availability prediction, suitable charging behaviors can be scheduled in advance to relieve range anxiety. Many existing deep learning methods have been proposed to address this issue; however, due to the complex road network structure and complex external factors, such as points of interest (POIs) and weather effects, many commonly used algorithms can only extract the historical usage information and do not consider the comprehensive influence of external factors. To enhance the prediction accuracy and interpretability, the Attribute-Augmented Spatiotemporal Graph Informer (AST-GIN) structure is proposed in this study by combining the Graph Convolutional Network (GCN) layer and the Informer layer to extract both the external and internal spatiotemporal dependence of relevant transportation data. The external factors are modeled as dynamic attributes by the attributeaugmented encoder for training. The AST-GIN model was tested on the data collected in Dundee City, and the experimental results showed the effectiveness of our model considering external factors' influence on various horizon settings compared with other baselines.

Urban road travel time estimation and prediction on a citywide scale is a necessary and important task for recommending optimal travel paths. However, this problem has not yet been well addressed: most existing approaches face serious data sparsity issues, e.g., lack of sensor data on several road segments; and it is a difficult task to capture context patterns around the road and incorporate context-aware information into travel time estimation models. Because of this, we propose to utilize trajectory data to model road travel times as this type of data covers more urban road segments than data from traditional traffic monitoring systems. Moreover, the trajectory itself has involved both travel times and the context of road congestion. A general framework for context-aware road travel time estimation (CARTE) is then put forward. Specifically, we adopt a third-order tensor to model spatiotemporal road travel times by setting the congestion level as a third dimension. By incorporating another context-aware information, namely points of interest (POI), a coupled tensor decomposition algorithm is proposed to fill in missing data. Eventually, we propose an algorithm to calculate an ultimate two-dimensional (spatial and temporal) travel time matrix by weighting the congestion probabilities of each congestion level. The effectiveness of the CARTE was validated on two real-world datasets and it was compared to the state-of-the-art methods. The experimental results demonstrate that the proposed travel time prediction approach always achieves the best performance in terms of accuracy with different data sparsity and prediction horizons.

Accurate long series forecasting of traffic information is critical for the development of intelligent traffic systems. We may benefit from the rapid growth of neural network analysis technology to better understand the underlying functioning patterns of traffic networks as a result of this progress. Due to the fact that traffic data and facility utilization circumstances are sequentially dependent on past and present situations, several related neural network techniques based on temporal dependency extraction models have been developed to solve the problem. The complicated topological road structure, on the other hand, amplifies the effect of spatial interdependence, which cannot be captured by pure temporal extraction approaches. Additionally, the typical Deep Recurrent Neural Network (RNN) topology has a constraint on global information extraction, which is required for comprehensive long-term prediction. This study proposes a new spatial-temporal neural network architecture, called Spatial-Temporal Graph-Informer (STGIN), to handle the long-term traffic parameters forecasting issue by merging the Informer and Graph Attention Network (GAT) layers for spatial and temporal relationships extraction. The attention mechanism potentially guarantees long-term prediction performance without significant information loss from distant inputs. On two real-world traffic datasets with varying horizons, experimental findings validate the long sequence prediction abilities, and further interpretation is provided.

Electric Vehicle (EV) charging demand and charging station availability forecasting is one of the challenges in the intelligent transportation system. With the accurate EV station situation prediction, suitable charging behaviors could be scheduled in advance to relieve range anxiety. Many existing deep learning methods are proposed to address this issue, however, due to the complex road network structure and comprehensive external factors, such as point of interests (POIs) and weather effects, many commonly used algorithms could just extract the historical usage information without considering comprehensive influence of external factors. To enhance the prediction accuracy and interpretability, the Attribute-Augmented Spatial-Temporal Graph Informer (AST-GIN) structure is proposed in this study by combining the Graph Convolutional Network (GCN) layer and the Informer layer to extract both external and internal spatial-temporal dependence of relevant transportation data. And the external factors are modeled as dynamic attributes by the attribute-augmented encoder for training. AST-GIN model is tested on the data collected in Dundee City and experimental results show the effectiveness of our model considering external factors influence over various horizon settings compared with other baselines.

Map matching of vehicle trajectories is to identify the correct link in the road network for each positioning point of a trajectory. A sampling period of fewer than 10 seconds for each position point is typically regarded as a high sampling rate trajectory. Existing algorithms are mainly targeted to the low-sampling-rate trajectories, which may ignore much useful information from high-sampling-rate trajectories. Till now, no studies explore the validity of such algorithms when we feed them the high-sampling-rate trajectories, which is the target of this paper. For alleviating the positioning error influence and speeding up the matching process for high sampling rate trajectories, a batch matching strategy is studied to simultaneously match a subsequence of a trajectory. Specifically, we first estimate the mean and median speeds of a trajectory and the current speed of the GPS point. To make sure that the upcoming subsequence to be matched is on the same road segment, we utilize the speed estimations as constraints for determining the subsequence size together with the local features of a road network. Accordingly, an incremental map matching algorithm is further in this study. Experimental results on real-world datasets of high sampling rate vehicle trajectories demonstrate that the proposed algorithm outperforms the algorithm that is designed for the low-sampling-rate trajectory.

A novel time-resolved fluorescence blocking lateral flow immunoassay (TRF-BLFIA) was developed for on-site differential diagnosis of pseudorabies virus (PRV)-infected and vaccinated pigs using europium nanoparticles (EuNPs)-labeled virion antigens and high titer PRV gE monoclonal antibodies (PRV gE-mAb). Upon application of a positive serum sample, the specific epitopes of gE protein on the EuNPs-PRV probe were blocked, inhibiting binding to the PRV gE-mAb on the T line, resulting in low or negligible fluorescence signal, whereas when a negative sample was applied, EuNPs-PRV probes would be able to bind the antibody at the T line, leading to high fluorescence signal. Under optimized conditions, TRF-BLFIA provided excellent sensitivity and selectivity. When testing swine clinical samples (n = 356), there was 96.1% agreement between this method and a most widely used commercial gE-ELISA kit. Moreover, our method was rapid (15 min), cost-efficient and easy to operate with simple training, allowing for on-site detection. Thus, TRF-BLFIA could be a practical tool to differentially diagnose PRV-infected and vaccinated pigs.

AbstractBackgroundA great concern around the globe now is to mitigate the COVID-19 pandemic via contact tracing. Analyzing the control strategies during the first five months of 2020 in Singapore is important to estimate the effectiveness of contacting tracing measures.MethodsWe developed a mathematical model to simulate the COVID-19 epidemic in Singapore, with local cases stratified into 5 categories according to the conditions of contact tracing and self-awareness. Key parameters of each category were estimated from local surveillance data. We also simulated a set of possible scenarios to predict the effects of contact tracing and self-awareness for the following month.FindingsDuring January 23 - March 16, 2020, the success probabilities of contact tracing and self-awareness were estimated to be 31% (95% CI 28%-33%) and 54% (95% CI 51%-57%), respectively. During March 17 - April 7, 2020, several social distancing measures (e.g., limiting mass gathering) were introduced in Singapore, which, however, were estimated with minor contribution to reduce the non-tracing reproduction number per local case (Rι,2). If contact tracing and self-awareness cannot be further improved, we predict that the COVID-19 epidemic will continue to spread in Singapore ifRι,2≥ 1.5.ConclusionContact tracing and self-awareness can mitigate the COVID-19 transmission, and can be one of the key strategies to ensure a sustainable reopening after lifting the lockdown.SummaryWe evaluate the efficiency of contact tracing and self-awareness in Singapore’s early-stage control of COVID-19. Then use a branching model to simulate and evaluate the possible prospective outcomes of Singapore’s COVID-19 control in different scenarios.

Ubiquitous trajectory data enables an amount of mobility-based analysis, such as target advertising, which also threatens personal position privacy. In this paper, we endeavor to solve the trajectory privacy preserving problem. We apply point-based protection method to preserve the trajectory's internal points, and we further propose a Bayesian inference based method to protect the destination location privacy involved in trajectories. The proposed methods consider the temporal information of a travel. Proved by the Bayesian inference process, we certify that the destination location of a trajectory can be amized by shearing the initial endpoint and the most current point before the destination point of a trajectory. To further improve the destination protection performance, we partition the hours of a day into different time spans, then the anonymizing process shears the first trajectory point that is sampled at the same time span of the most current trajectory point (the last point in the query trajectory and before the destination). The privacy protection is effective if the destination is anonymized by destination prediction algorithms. By evaluating on two real trajectory datasets with two referenced destination prediction algorithms, it demonstrates that our proposed destination privacy protection algorithm is more effective than baselines.

Pseudorabies virus (PRV) is a pathogen that causes an acute infectious disease in pigs, which could lead to huge losses to the farming industry. The Bartha-K61 strain of PRV, commonly used as a gE-deleted vaccine, does not always protect against the wild-type virus infection effectively. Therefore, the prompt detection of viral infection in gE-deleted vaccine vaccinated pigs is crucial for in-time measures to prevent the spread of diseases. In this study, we developed a Surface-enhanced Raman spectroscopy(SERS) based lateral flow assay based on antigen-antibody reaction to meet the demand. Our method was rapid (15 min), sensitive (LOD: 5 ng mL(-1)), selective for wild-type PRV detection, and quantitatively or semi-quantitatively (DLR: 41-650 ng mL(-1)) compatible. The detection results from this method were consistent with results from the gE-specific PCR, indicating that this SERS-based lateral flow assay could be used as a new tool to differentially diagnose wild-type PRV and gE-deleted vaccine.

Traffic congestion has gradually become a focal issue in people’s daily life. When the traffic flow on a road segment exceeds its actual capacity, congestion takes place. During rush hours, a congested road segment must carry heavy loads for a long time and is very likely to spread traffic congestion to this road’s adjacent segments via the spatial structure of the road. The new infected road segments continue propagating congestion in the same way. In this paper, we attempt to model the congestion propagation phenomenon with a space-temporal congestion subgraph (STCS). To this end, we detect each segment regardless of whether it is congested during consecutive time intervals and build the connection of two segments in terms of their spatio-temporal properties. Due to the sparseness of the trajectory data, two strategies of filling missing congestion edges from both temporal and spatial viewpoints are also proposed. Since STCSes are constructed from the same time interval over different days, we design a specific algorithm to discover the frequent congestion subgraphs. Finally, we evaluate the solution on Shanghai taxicab data and the corresponding road network. The experiment shows that the frequent congestion subgraph can reveal an urban congestion propagation pattern.

Pseudorabies virus (PRV) is an acute and thermal infectious disease in domestic animals. Pigs are a main source of PRV infection, which causes high mortality rates for newborn infected piglets and high miscarriage rates for infected adults. Therefore, early control of PRV is necessary to avoid significant economic loss. We have developed a novel fluorescent immunochromatographic strip (F-ICS) for rapid, sensitive, and specific detection of PRV with a limit of detection (LOD) of 0.13 ng mL−1 and a detection linear range (DLR) between 0.13 and 2.13 ng mL−1. The detection limit was about 10 times lower than the colloidal gold strip. In tests of clinical samples, the F-ICS was largely consistent with PCR results, indicating its practical clinical application. In addition, for easy observation of the F-ICS signal by eye, we present a matching 3D-printed pocket fluorescence observation instrument (PFOI) that allows for use of the F-ICS in the field as easily as conventional colloidal gold strips.

To meet the wireless network congestion control problem, we give a definition of congestion degree classification and propose a mechanism of directed cooperative path net, guided by the wireless network's cross-layer design methods and node cooperation principles. Considering the virtual collision and "starved" phenomenon in congested networks, the QRD mechanism and channel competition mechanism QPCG are proposed, with introducing the game theory into the cross-layer design. Simulation results showed that directed cooperative path nets could effectively improve network resource utilization and network transmission performance in congested network. And the QRD and QPCG mechanism could effectively reduce the probability of "starved" phenomenon and increased the wireless network throughput with reducing the packet loss rate.

A FCM-based segmentation algorithm is proposed in this paper to improve the accuracy and efficiency of liver parenchyma segmentation. The proposed segmentation method consists of four steps as follows:First,we characterized the gray distribution of the unfiltered image. Second, combined with the Otsu algorithm and associated with a cropped liver image, we defined a gray interval as the liver's intersity range. Third, The fuzzy c-means clustering algorithm was applied to define the confidence interval of traditional confidence connectivity method. Finally, we employed the improved confidence connected algorithm to extract the liver parenchyma from a large cross-section liver image. Experimental results show that the proposed segmentation method is feasible even for diseased liver images.

Ray casting algorithm is a kind of widely used volume rendering algorithm in the field of medical 3D reconstruction. One of the greatest advantages of it is the high rendering quality, while the rendering speed is rather low. In order to accelerate the rendering speed, in this paper, it proposed an accelerated ray casting algorithm which is based on the proximate cloud algorithm, combined with empty voxel leaping and fast interpolation. Meanwhile, it also analyzed the complexity of computing to significantly enhance the speed of the algorithm on volume rendering.