Search

Advances in automotive technology require networks to support a variety of communication requirements, such as reliability, real-time performance, low jitter, and strict delay limits. Time-Sensitive Network (TSN) is a keyframe transmission delay-guaranteed solution based on the IEEE 802 architecture of the automotive Ethernet. However, most of the existing studies on automotive TSN performance are based on a single mechanism, lacking a complete and systematic research tool. At the same time, the design method should be considered from a global perspective when designing an automotive TSN system, rather than only considering a single mechanism that TSN applies to. This paper discusses the correspondence between traffic types and automotive scenarios and proposes a methodology to target the delay constraint of traffic types as the design goal of automotive TSN networks. To study the performance of automotive TSN under different mechanisms such as time-aware shaper (TAS), credit-based shaper (CBS), cyclic queuing and forwarding (CQF), etc., this paper also develops a systematic automotive TSN simulation system based on OMNeT++. The simulation system plays a crucial role in the whole methodology, including all applicable TSN standards for the automotive field. Lastly, a complex automotive scenario based on zonal architecture provided by a major motor company in Shanghai is analyzed in the simulated system; verifying TSN can guarantee real-time performance and reliability of the in-vehicle network. [ABSTRACT FROM AUTHOR]

Dynamic traffic flow, which can facilitate the efficient operation of traffic road networks, is an important prerequisite for the application of reasonable assignment of traffic demands in an urban road network. In order to improve the accuracy of dynamic traffic flow assignment, this paper proposes a dynamic traffic flow assignment model based on GPS trajectory data and the influence of POI. First, this paper explores the impact patterns of POI on regional road network congestion during peak hours through qualitative and quantitative analysis. Then, based on the user equilibrium theory, a dynamic traffic flow assignment model, in which the effect of POI on links is reflected using the link-node impedance function, is proposed. Finally, the accuracy of the model is validated by the GPS trajectory data and origin–destination (OD) traffic data of motor vehicles in Xuhui District, Shanghai, China. The results show that the model can be used to coordinate and optimize the traffic assignment of the regional road network under the influence of POI during peak hours and alleviate the congestion of the road network. The findings can provide a powerful reference for developing scientific and rational traffic assignment decisions and management strategies for urban road network traffic. [ABSTRACT FROM AUTHOR]

The traditional weighing and selling process of non-barcode items requires manual service, which not only consumes manpower and material resources but is also more prone to errors or omissions of data. This paper proposes an intelligent self-service vending system embedded with a single camera to detect multiple products in real-time performance without any labels, and the system realizes the integration of weighing, identification, and online settlement in the process of non-barcode items. The system includes a self-service vending device and a multi-device data management platform. The flexible configuration of the structure gives the system the possibility of identifying fruits from multiple angles. The height of the system can be adjusted to provide self-service for people of different heights; then, deep learning skill is applied implementing product detection, and real-time multi-object detection technology is utilized in the image-based checkout system. In addition, on the multi-device data management platform, the information docking between embedded devices, WeChat applets, Alipay, and the database platform can be implemented. We conducted experiments to verify the accuracy of the measurement. The experimental results demonstrate that the correlation coefficient R 2 between the measured value of the weight and the actual value is 0.99, and the accuracy of non-barcode item prediction is 93.73%. In Yangpu District, Shanghai, a comprehensive application scenario experiment was also conducted, proving that our system can effectively deal with the challenges of various sales situations. [ABSTRACT FROM AUTHOR]

The train-induced vibration response provides a flexible solution for the real-time monitoring deformation of high-speed railway track slab in actual operation. This paper proposes a long-term real-time monitoring method for track slab deformation based on wavelet packet energy (WPE) using fiber optic accelerometers to record train-induced vibration. We found that the vibration response law of track slab deformation could be established by using the WPE of the frequency band covering the first- and second-order frequencies induced by the adjacent carriages. A field test was carried out for more than one year on the Beijing–Shanghai high-speed railway to investigate the train-induced vibration response law of track slab that was continuously deformed under a long-term temperature load. The maximum values of the WPE characteristic index appeared in winter and summer, and they were positively correlated with the temperature difference between the air environment and the track slab under the daily temperature load. These results were demonstrated to be consistent with the track slab deformation law for long-term and daily temperature loads. The novel method based on fiber optic accelerometers and WPE provides a new method for the long-term and real-time monitoring of track slab deformation. [ABSTRACT FROM AUTHOR]

Sensor data are gaining increasing global attention due to the advent of Internet of Things (IoT). Reasoning is applied on such sensor data in order to compute prediction. Generating a health warning that is based on prediction of atmospheric pollution, planning timely evacuation of people from vulnerable areas with respect to prediction of natural disasters, etc., are the use cases of sensor data stream where prediction is vital to protect people and assets. Thus, prediction accuracy is of paramount importance to take preventive steps and avert any untoward situation. Uncertainties of sensor data is a severe factor which hampers prediction accuracy. Belief Rule Based Expert System (BRBES), a knowledge-driven approach, is a widely employed prediction algorithm to deal with such uncertainties based on knowledge base and inference engine. In connection with handling uncertainties, it offers higher accuracy than other such knowledge-driven techniques, e.g., fuzzy logic and Bayesian probability theory. Contrarily, Deep Learning is a data-driven technique, which constitutes a part of Artificial Intelligence (AI). By applying analytics on huge amount of data, Deep Learning learns the hidden representation of data. Thus, Deep Learning can infer prediction by reasoning over available data, such as historical data and sensor data streams. Combined application of BRBES and Deep Learning can compute prediction with improved accuracy by addressing sensor data uncertainties while utilizing its discovered data pattern. Hence, this paper proposes a novel predictive model that is based on the integrated approach of BRBES and Deep Learning. The uniqueness of this model lies in the development of a mathematical model to combine Deep Learning with BRBES and capture the nonlinear dependencies among the relevant variables. We optimized BRBES further by applying parameter and structure optimization on it. Air pollution prediction has been taken as use case of our proposed combined approach. This model has been evaluated against two different datasets. One dataset contains synthetic images with a corresponding label of PM2.5 concentrations. The other one contains real images, PM2.5 concentrations, and numerical weather data of Shanghai, China. We also distinguished a hazy image between polluted air and fog through our proposed model. Our approach has outperformed only BRBES and only Deep Learning in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]