Key technologies for wireless network digital twin towards smart railways

An emerging railway technology called smart railway promises to deliver higher transportation efficiency,enhanced comfort in services,and greater eco-friendliness.The smart railway is expected to integrate fifth-generation mobile communication(5G),Artificial Intelligence(AI),and other technologies,which poses new problems in the construction,operation and maintenance of railway wireless networks.Wireless Digital Twins(DTs),which have recently emerged as a new paradigm for the design of wireless networks,can address these problems and enable the whole lifecycle management of railway wireless networks.However,there are still many scientific issues and challenges for railway-oriented wireless DT.Relevant key technologies to solve these problems are introduced and described,including characterization of materials'physical-EM properties,autonomous reconstruction of Three-dimensional(3D)environment model,AI-empowered environmental cognition,Ray-Tracing(RT),model-based and AIbased RT acceleration,and generation of multi-spectra sensing data.Moreover,this paper presents our research results for each key technology and describes the wireless network planning and optimization system based on highperformance RT developed by our laboratory.This paper outlines the framework for realizing the wireless DT of smart railways,providing the direction for future research.

STRASS Dehazing:Spatio-Temporal Retinex-Inspired Dehazing by an Averaging of Stochastic Samples

In this paper,we propose a neoteric and high-efficiency single image dehazing algorithm via contrast enhancement which is called STRASS(Spatio-Temporal Retinex-Inspired by an Averaging of Stochastic Samples)dehazing,it is realized by constructing an efficient high-pass filter to process haze images and taking the influence of human vision system into account in image dehazing principles.The novel high-pass filter works by getting each pixel using RSR and computes the average of the samples.Then the low-pass filter resulting from the minimum envelope in STRESS framework has been replaced by the average of the samples.The final dehazed image is yielded after iterations of the high-pass filter.STRASS can be run directly without any machine learning.Extensive experimental results on datasets prove that STRASS surpass the state-of-the-arts.Image dehazing can be applied in the field of printing and packaging,our method is of great significance for image pre-processing before printing.

Property estimation of free-field sand in 1-g shaking table tests

Experimental data taken from free-field soil in 1-g shaking table tests are valuable for seismic studies on soil-structure interaction.But the available data from medium-to large-scale shaking table tests were not abundant enough to cover a large variety of types and conditions of the soil.In the study,1-g shaking table tests of a 3-m-height sand column were conducted to provide seismic experimental data about sand.The sand was directly collected in-situ,with the largest grain diameter being 2 cm and containing a water content of 6.3%.Properties of the sand were estimated under the influence of white noise plus pulse and earthquake motions,including the settlement,the dynamic properties of the sand column,and the three soil layers′shear modulus degradation relationships.The estimated properties were then indirectly verified by means of finite element analysis.Results show that the estimated parameters were effective and could be used in numerical modeling to reproduce approximate seismic responses of the sand column.

Determining osmotic suction through electrical conductivity for unsaturated low-plasticity soils

Determining osmotic suction from the electrical conductivity(EC)of soil pore water was widely reported in the literature.However,while dealing with unsaturated soils,they do not have enough soil pore water to be extracted for a reliable measurement of EC.In this paper,the chilled-mirror dew-point hygrometer and contact filter paper method were used to determine the total and matric suctions for low-plasticity soils with different salinities(0.05‰,2.1‰,and 6.76‰).A new piecewise function was proposed to calculate the osmotic suction,with the piecewise point corresponding to the first occurrence of precipitated salt in mixed salt solutions(synthetic seawater).EC,ion and salt concentrations used for osmotic suction calculation were transformed from the established relationships of mixed salt solution instead of experimental measurement.The calculated osmotic suction by the proposed equation and the equations in the literature was compared with the indirectly measured one(the difference between the measured total and matric suctions).Results showed that the calculated osmotic suction,especially the one calculated using the proposed function,was in fair agreement with the indirectly measured data(especially for specimens with higher salinity of 6.76‰),suggesting that the transformation of EC and concentrations from the established relationship is a good alternative to direct measurement for lowplasticity soil.In particular,the proposed method could be applied to unsaturated low-plasticity soils which do not have enough soil pore water for a proper EC measurement.

Leveraging reinforcement learning for dynamic traffic control:A survey and challenges for field implementation

In recent years,the advancement of artificial intelligence techniques has led to significant interest in reinforcement learning(RL)within the traffic and transportation community.Dynamic traffic control has emerged as a prominent application field for RL in traffic systems.This paper presents a comprehensive survey of RL studies in dynamic traffic control,addressing the challenges associated with implementing RL-based traffic control strategies in practice,and identifying promising directions for future research.The first part of this paper provides a comprehensive overview of existing studies on RL-based traffic control strategies,encompassing their model designs,training algorithms,and evaluation methods.It is found that only a few studies have isolated the training and testing environments while evaluating their RL controllers.Subsequently,we examine the challenges involved in implementing existing RL-based traffic control strategies.We investigate the learning costs associated with online RL methods and the transferability of offline RL methods through simulation experiments.The simulation results reveal that online training methods with random exploration suffer from high exploration and learning costs.Additionally,the performance of offline RL methods is highly reliant on the accuracy of the training simulator.These limitations hinder the practical implementation of existing RL-based traffic control strategies.The final part of this paper summarizes and discusses a few existing efforts which attempt to overcome these challenges.This review highlights a rising volume of studies dedicated to mitigating the limitations of RL strategies,with the specific aim of enhancing their practical implementation in recent years.

Light People:Tarik Bourouina

In 2015,195 countries of the United Nations proposed Sustainable Development Goals so as to alleviate the problems of climate change and global pollution.In France,there is a scientist dedicated to contribute providing solutions for above issues by virtue of MEMS,Lab-On-Chip and metamaterials.This expert is Prof.Tarik Bourouina,a Professor of Physics at ESIEE Paris,UniversitéGustave Eiffel.He devoted himself to the investigations on micro sensors and metamaterials,and kept seeking their applications in the future blueprint of“Sustainable”and“Smart”cities.

Effects of cobalt doping on the reactivity of hausmannite for As(Ⅲ)oxidation and As(Ⅴ)adsorption

Hausmannite is a common low valence Mn oxide mineral,with a distorted spinel structure,in surficial sediments.Although natural Mn oxides often contain various impurities of transitional metals(TMs),few studies have addressed the effect and related mechanism of TM doping on the reactivity of hausmannite with metal pollutants.Here,the reactivity of cobalt(Co)doped hausmannite with aqueous As(Ⅲ)and As(Ⅴ)was studied.Co doping decreased the point of zero charge of hausmannite and its adsorption capacity for As(Ⅴ).Despite a reduction of the initial As(Ⅲ)oxidation rate,Co-doped hausmannite could effectively oxidize As(Ⅲ)to As(Ⅴ),followed by the adsorption and fixation of a large amount of As(Ⅴ)on the mineral surface.Arsenic K-edge EXAFS analysis of the samples after As(Ⅴ)adsorption and As(Ⅲ)oxidation revealed that only As(Ⅴ)was adsorbed on the mineral surface,with an average As-Mn distance of 3.25–3.30 A,indicating the formation of bidentate binuclear complexes.These results provide new insights into the interaction mechanism between TMs and low valence Mn oxides and their effect on the geochemical behaviors of metal pollutants.