Search

Infrastructure along the highway refers to various facilities and equipment: bridges, culverts, traffic signs, guardrails, etc. New technologies such as artificial intelligence, big data, and the Internet of Things are driving the digital transformation of highway infrastructure towards the future goal of intelligent roads. Drones have emerged as a promising application area of intelligent technology in this field. They can help achieve fast and precise detection, classification, and localization of infrastructure along highways, which can significantly enhance efficiency and ease the burden on road management staff. As the infrastructure along the road is exposed to the outdoors for a long time, it is easily damaged and obscured by objects such as sand and rocks; on the other hand, based on the high resolution of the images taken by Unmanned Aerial Vehicles (UAVs), the variable shooting angles, complex backgrounds, and high percentage of small targets mean the direct use of existing target detection models cannot meet the requirements of practical applications in industry. In addition, there is a lack of large and comprehensive image datasets of infrastructure along highways from UAVs. Based on this, a multi-classification infrastructure detection model combining multi-scale feature fusion and an attention mechanism is proposed. In this paper, the backbone network of the CenterNet model is replaced with ResNet50, and the improved feature fusion part enables the model to generate fine-grained features to improve the detection of small targets; furthermore, the attention mechanism is added to make the network focus more on valuable regions with higher attention weights. As there is no publicly available dataset of infrastructure along highways captured by UAVs, we filter and manually annotate the laboratory-captured highway dataset to generate a highway infrastructure dataset. The experimental results show that the model has a mean Average Precision (mAP) of 86.7%, an improvement of 3.1 percentage points over the baseline model, and the new model performs significantly better than other detection models overall. [ABSTRACT FROM AUTHOR]

The deployment density and computational power of small base stations (BSs) are expected to increase significantly in the next generation mobile communication networks. These BSs form the mobile edge network, which is a pervasive and distributed infrastructure that can empower a variety of edge/fog computing applications. This paper proposes a novel edge-computing application called explicit caching, which stores selective contents at BSs and exposes such contents to local users for interactive browsing and download. We formulate the explicit caching problem as a joint content recommendation, caching, and delivery problem, which aims to maximize the expected user quality-of-experience (QoE) with varying degrees of cross-layer sensing capability. Optimal and effective heuristic algorithms are presented to solve the problem. The theoretical performance bounds of the explicit caching system are derived in simplified scenarios. The impacts of cache storage space, BS backhaul capacity, cross-layer information, and user mobility on the system performance are simulated and discussed in realistic scenarios. Results suggest that, compared with conventional implicit caching schemes, explicit caching can better exploit the mobile edge network infrastructure for personalized content dissemination. [ABSTRACT FROM AUTHOR]

Research shows that various contextual factors can have an impact on learning. Some of these factors can originate from the physical learning environment (PLE) in this regard. When learning from home, learners have to organize their PLE by themselves. This paper is concerned with identifying, measuring, and collecting factors from the PLE that may affect learning using mobile sensing. More specifically, this paper first investigates which factors from the PLE can affect distance learning. The results identify nine types of factors from the PLE associated with cognitive, physiological, and affective effects on learning. Subsequently, this paper examines which instruments can be used to measure the investigated factors. The results highlight several methods involving smart wearables (SWs) to measure these factors from PLEs successfully. Third, this paper explores how software infrastructure can be designed to measure, collect, and process the identified multimodal data from and about the PLE by utilizing mobile sensing. The design and implementation of the Edutex software infrastructure described in this paper will enable learning analytics stakeholders to use data from and about the learners' physical contexts. Edutex achieves this by utilizing sensor data from smartphones and smartwatches, in addition to response data from experience samples and questionnaires from learners' smartwatches. Finally, this paper evaluates to what extent the developed infrastructure can provide relevant information about the learning context in a field study with 10 participants. The evaluation demonstrates how the software infrastructure can contextualize multimodal sensor data, such as lighting, ambient noise, and location, with user responses in a reliable, efficient, and protected manner. [ABSTRACT FROM AUTHOR]

Safe autonomous vehicle (AV) operations depend on an accurate perception of the driving environment, which necessitates the use of a variety of sensors. Computational algorithms must then process all of this sensor data, which typically results in a high on-vehicle computational load. For example, existing lane markings are designed for human drivers, can fade over time, and can be contradictory in construction zones, which require specialized sensing and computational processing in an AV. But, this standard process can be avoided if the lane information is simply transmitted directly to the AV. High definition maps and road side units (RSUs) can be used for direct data transmission to the AV, but can be prohibitively expensive to establish and maintain. Additionally, to ensure robust and safe AV operations, more redundancy is beneficial. A cost-effective and passive solution is essential to address this need effectively. In this research, we propose a new infrastructure information source (IIS), chip-enabled raised pavement markers (CERPMs), which provide environmental data to the AV while also decreasing the AV compute load and the associated increase in vehicle energy use. CERPMs are installed in place of traditional ubiquitous raised pavement markers along road lane lines to transmit geospatial information along with the speed limit using long range wide area network (LoRaWAN) protocol directly to nearby vehicles. This information is then compared to the Mobileye commercial off-the-shelf traditional system that uses computer vision processing of lane markings. Our perception subsystem processes the raw data from both CEPRMs and Mobileye to generate a viable path required for a lane centering (LC) application. To evaluate the detection performance of both systems, we consider three test routes with varying conditions. Our results show that the Mobileye system failed to detect lane markings when the road curvature exceeded ± 0.016 m−1. For the steep curvature test scenario, it could only detect lane markings on both sides of the road for just 6.7% of the given test route. On the other hand, the CERPMs transmit the programmed geospatial information to the perception subsystem on the vehicle to generate a reference trajectory required for vehicle control. The CERPMs successfully generated the reference trajectory for vehicle control in all test scenarios. Moreover, the CERPMs can be detected up to 340 m from the vehicle's position. Our overall conclusion is that CERPM technology is viable and that it has the potential to address the operational robustness and energy efficiency concerns plaguing the current generation of AVs. [ABSTRACT FROM AUTHOR]

Multi-step traffic forecasting has always been extremely challenging due to constantly changing traffic conditions. Advanced Graph Convolutional Networks (GCNs) are widely used to extract spatial information from traffic networks. Existing GCNs for traffic forecasting are usually shallow networks that only aggregate two- or three-order node neighbor information. Because of aggregating deeper neighborhood information, an over-smoothing phenomenon occurs, thus leading to the degradation of model forecast performance. In addition, most existing traffic forecasting graph networks are based on fixed nodes and therefore need more flexibility. Based on the current problem, we propose Dynamic Adaptive Deeper Spatio-Temporal Graph Convolutional Networks (ADSTGCN), a new traffic forecasting model. The model addresses over-smoothing due to network deepening by using dynamic hidden layer connections and adaptively adjusting the hidden layer weights to reduce model degradation. Furthermore, the model can adaptively learn the spatial dependencies in the traffic graph by building the parameter-sharing adaptive matrix, and it can also adaptively adjust the network structure to discover the unknown dynamic changes in the traffic network. We evaluated ADSTGCN using real-world traffic data from the highway and urban road networks, and it shows good performance. [ABSTRACT FROM AUTHOR]

Traffic flow prediction is one of the most important tasks of the Intelligent Transportation Systems (ITSs) for traffic management, and it is also a challenging task affected by many complex factors, such as weather and time. Many cities adopt efficient traffic prediction methods to control traffic congestion. However, most of the existing methods of traffic prediction focus on urban road scenarios, neglecting the complexity of multivariate auxiliary information in highways. Moreover, these methods have difficulty explaining the prediction results based only on the historical traffic flow sequence. To tackle these problems, we propose a novel traffic prediction model, namely Multi-variate and Multi-horizon prediction based on Long Short-Term Memory (MMLSTM). MMLSTM can effectively incorporate auxiliary information, such as weather and time, based on a strategy of multi-horizon time spans to improve the prediction performance. Specifically, we first exploit a multi-horizon bidirectional LSTM model for fusing the multivariate auxiliary information in different time spans. Then, we combine an attention mechanism and multi-layer perceptron to conduct the traffic prediction. Furthermore, we can use the information of multivariate (weather and time) to provide interpretability to manage the model. Comprehensive experiments are conducted on Hangst and Metr-la datasets, and MMLSTM achieves better performance than baselines on traffic prediction tasks. [ABSTRACT FROM AUTHOR]

High-speed railway administrations are particularly concerned about safety and comfort issues, which are sometimes threatened by the differential deformation of substructures. Existing deformation-monitoring techniques are impractical for covering the whole range of a railway line at acceptable costs. Fortunately, the information about differential substructure deformation is contained in the dynamic inspection data of longitudinal level from comprehensive inspections trains. In order to detect potential differential deformations, an identification method, combining digital filtering, a convolutional neural network and infrastructure base information, is proposed. In this method, a low-pass filter is designed to remove short-waveband components of the longitudinal level. Then, a one-dimensional convolutional neural network is constructed to serve as a feature extractor from local longitudinal-level waveforms, and a binary classifier of potential differential deformations in place of the visual judgement of humans with profound expertise. Finally, the infrastructure base information is utilized to further classify the differential deformations into several types, according to the positional distribution of the substructures. The inspection data of four typical high-speed railways are selected to train and test the method. The results show that the convolutional neural network can identify differential substructure-deformations, with the precision, recall, accuracy and F1 score all exceeding 98% on the test data. In addition, four types of deformation can be further classified with the support of infrastructure base information. The proposed method can be used for directly locating adverse substructure deformations, and is also becoming a promising addition to existing deformation monitoring methods. [ABSTRACT FROM AUTHOR]

Vehicular Ad hoc NETworks (VANET) has been well studied for a long time as a means to exchange information among moving vehicles. As vehicular networks do not always have connected paths, vehicular networks can be regarded as a kind of delay-tolerant networks (DTNs) when the density of vehicles is not high enough. In this case, packet delivery ratio degrades significantly so that reliability of networks as an information infrastructure is hardly held. Past studies such as SADV (Static-node Assisted Data dissemination protocol for Vehicular networks) and RDV (Reliable Distance-Vector routing) showed that the assistance of low-cost unwired static nodes located at intersections, which work as routers to provide distance-vector or link-state routing functions, significantly improves the communication performance. However, they still have problems: SADV does not provide high-enough delivery ratio and RDV suffers from traffic concentration on the shortest paths. In this paper, we propose MP-RDV (Multi-Path RDV) by extending RDV with multiple paths utilization to improve performance against both of those problems. In addition, we apply a delay routing metric, which is one of the major metrics in this field, to RDV to compare performance with the traffic-volume metric, which is a built-in metric of RDV. Evaluation results show that MP-RDV achieves high load-balancing performance, larger network capacity, lower delivery delay, and higher fault tolerance against topology changes compared to RDV. As for routing metrics, we showed that the traffic-volume metric is better than the delay one in RDV because delay measurement is less stable against traffic fluctuation. [ABSTRACT FROM AUTHOR]

Platooning strategy is an important component of autonomous driving technology. Autonomous vehicles in platoons are often equipped with a variety of on-board sensors to detect the surrounding environment. The abundant data collected by autonomous vehicles in platoons can be transmitted to the infrastructure through vehicle-to-infrastructure (V2I) communications using the IEEE 802.11 distributed coordination function (DCF) mechanism and then uploaded to the cloud platform through the Internet. The cloud platform extracts useful information and then sends it back to the autonomous vehicles respectively. In this way, autonomous vehicles in platoons can detect emergency conditions and make a decision in time. The characteristics of platoons would cause a fair-access problem in the V2I communications, i.e., vehicles in the platoons moving on different lanes with different velocities would have different resident time within the infrastructure's coverage and thus successfully send different amounts of data to the infrastructure. In this case, the vehicles with different velocities will receive different amounts of useful information from the cloud. As a result, vehicles with a higher velocity are more likely to suffer from a traffic accident as compared to the vehicles with a lower velocity. Hence, this paper considers the fair-access problem and proposes a fair-access scheme to ensure that vehicles with different velocities successfully transmit the same amount of data by adaptively adjusting the minimum contention window of each vehicle according to its velocity. Moreover, the normalized throughput of the proposed scheme is derived. The validity of the fair-access scheme is demonstrated by simulation. [ABSTRACT FROM AUTHOR]

With the recent development of artificial intelligence along with information and communications infrastructure, a new paradigm of online services is being developed. Whereas in the past a service system could only exchange information of the service provider at the request of the user, information can now be provided by automatically analyzing a particular need, even without a direct user request. This also holds for online platforms of used-vehicle sales. In the past, consumers needed to inconveniently determine and classify the quality of information through static data provided by service and information providers. As a result, this service field has been harmful to consumers owing to such problems as false sales, fraud, and exaggerated advertising. Despite significant efforts of platform providers, there are limited human resources for censoring the vast amounts of data uploaded by sellers. Therefore, in this study, an algorithm called YOLOv3+MSSIM Type 2 for automatically censoring the data of used-vehicle sales on an online platform was developed. To this end, an artificial intelligence system that can automatically analyze an object in a vehicle video uploaded by a seller, and an artificial intelligence system that can filter the vehicle-specific terms and profanity from the seller's video presentation, were also developed. As a result of evaluating the developed system, the average execution speed of the proposed YOLOv3+MSSIM Type 2 algorithm was 78.6 ms faster than that of the pure YOLOv3 algorithm, and the average frame rate per second was improved by 40.22 fps. In addition, the average GPU utilization rate was improved by 23.05%, proving the efficiency. [ABSTRACT FROM AUTHOR]

Seaports are genuine, intermodal hubs connecting seaways to inland transport links, such as roads and railways. Seaports are located at the focal point of institutional, industrial, and control activities in a jungle of interconnected information systems. System integration is setting considerable challenges when a group of independent providers are asked to implement complementary software functionalities. For this reason, seaports are the ideal playground where software is highly composite and tailored to a large variety of final users (from the so-called port communities). Although the target would be that of shaping the Port Authorities to be providers of (digital) innovation services, the state-of-the-art is still that of considering them as final users, or proxies of them. For this reason, we show how a canonical cloud, virtualizing a distributed architecture, can be structured to host different, possibly overlapped, tenants, slicing the information system at the infrastructure, platform, and software layers. Resources at the infrastructure and platform layers are shared so that a variety of independent applications can make use of the local calculus and access the data stored in a Data Lake. Such a cloud is adopted by the Port of Livorno as a rapid prototyping framework for the development and deployment of ICT innovation services. In order to demonstrate the versatility of this framework, three case studies relating to as many prototype ICT services (Navigation Safety, e-Freight, and Logistics) released within three industrial tenants are here presented and discussed. [ABSTRACT FROM AUTHOR]

With the steadily growing of global transportation market, the traffic load has increased dramatically over the past decades, which may develop into a risk source for existing bridges. The simultaneous presence of heavy trucks that are random in nature governs the serviceability limit for large bridges. This study investigated probabilistic traffic load effects on large bridges under actual heavy traffic load. Initially, critical stochastic traffic loading scenarios were simulated based on millions of traffic monitoring data in a highway bridge in China. A methodology of extrapolating maximum traffic load effects was presented based on the level-crossing theory. The effectiveness of the proposed method was demonstrated by probabilistic deflection investigation of a suspension bridge. Influence of traffic density variation and overloading control on the maximum deflection was investigated as recommendations for designers and managers. The numerical results show that the congested traffic mostly governs the critical traffic load effects on large bridges. Traffic growth results in higher maximum deformations and probabilities of failure of the bridge in its lifetime. Since the critical loading scenario contains multi-types of overloaded trucks, an effective overloading control measure has a remarkable influence on the lifetime maximum deflection. The stochastic traffic model and corresponding computational framework is expected to be developed to more types of bridges. [ABSTRACT FROM AUTHOR]

Lane marking detection and localization are crucial for autonomous driving and lane-based pavement surveys. Numerous studies have been done to detect and locate lane markings with the purpose of advanced driver assistance systems, in which image data are usually captured by vision-based cameras. However, a limited number of studies have been done to identify lane markings using high-resolution laser images for road condition evaluation. In this study, the laser images are acquired with a digital highway data vehicle (DHDV). Subsequently, a novel methodology is presented for the automated lane marking identification and reconstruction, and is implemented in four phases: (1) binarization of the laser images with a new threshold method (multi-box segmentation based threshold method); (2) determination of candidate lane markings with closing operations and a marching square algorithm; (3) identification of true lane marking by eliminating false positives (FPs) using a linear support vector machine method; and (4) reconstruction of the damaged and dash lane marking segments to form a continuous lane marking based on the geometry features such as adjacent lane marking location and lane width. Finally, a case study is given to validate effects of the novel methodology. The findings indicate the new strategy is robust in image binarization and lane marking localization. This study would be beneficial in road lane-based pavement condition evaluation such as lane-based rutting measurement and crack classification. [ABSTRACT FROM AUTHOR]