Privacy-Preserving Large-Scale AI Models for Intelligent Railway Transportation Systems:Hierarchical Poisoning Attacks and Defenses in Federated Learning

The development of Intelligent Railway Transportation Systems necessitates incorporating privacy-preserving mechanisms into AI models to protect sensitive information and enhance system efficiency.Federated learning offers a promising solution by allowing multiple clients to train models collaboratively without sharing private data.However,despite its privacy benefits,federated learning systems are vulnerable to poisoning attacks,where adversaries alter local model parameters on compromised clients and send malicious updates to the server,potentially compromising the global model’s accuracy.In this study,we introduce PMM(Perturbation coefficient Multiplied by Maximum value),a new poisoning attack method that perturbs model updates layer by layer,demonstrating the threat of poisoning attacks faced by federated learning.Extensive experiments across three distinct datasets have demonstrated PMM’s ability to significantly reduce the global model’s accuracy.Additionally,we propose an effective defense method,namely CLBL(Cluster Layer By Layer).Experiment results on three datasets have confirmed CLBL’s effectiveness.

Dynamic response of mountain tunnel,bridge,and embankment along the Sichuan-Tibet transportation corridor to active fault based on model tests

The Sichuan-Tibet transportation corridor is prone to numerous active faults and frequent strong earthquakes.While extensive studies have individually explored the effect of active faults and strong earthquakes on different engineering structures,their combined effect remains unclear.This research employed multiple physical model tests to investigate the dynamic response of various engineering structures,including tunnels,bridges,and embankments,under the simultaneous influence of cumulative earthquakes and stick-slip misalignment of an active fault.The prototype selected for this study was the Kanding No.2 tunnel,which crosses the Yunongxi fault zone within the Sichuan-Tibet transportation corridor.The results demonstrated that the tunnel,bridge,and embankment exhibited amplification in response to the input seismic wave,with the amplification effect gradually decreasing as the input peak ground acceleration(PGA)increased.The PGAs of different engineering structures were weakened by the fault rupture zone.Nevertheless,the misalignment of the active fault may decrease the overall stiffness of the engineering structure,leading to more severe damage,with a small contribution from seismic vibration.Additionally,the seismic vibration effect might be enlarged with the height of the engineering structure,and the tunnel is supposed to have a smaller PGA and lower dynamic earth pressure compared to bridges and embankments in strong earthquake zones crossing active faults.The findings contribute valuable insights for evaluating the dynamic response of various engineering structures crossing an active fault and provide an experimental reference for secure engineering design in the challenging conditions of the Sichuan-Tibet transportation corridor.

Influence of Transportation Accessibility on Urban-rural Income Disparity and Its Spatial Heterogeneity

Transportation accessibility has been treated as an important means of reducing the urban-rural income disparity.However,only a few studies have examined the effects of different types of transportation accessibility on urban-rural income disparity and their spatial heterogeneity.Based on data from 285 prefecture-level(and above)Chinese cities in 2000,2005,2010,2015,and 2020,this study uses spatial econometric models to examine how highway accessibility and railway accessibility influence the urban-rural income disparity and to identify their spatial heterogeneity.The result reveals that highway accessibility and railway accessibility have‘coreperiphery’ring-like circle structures.The urban-rural income disparity exhibits strong spatial clustering effects.Both highway accessibility and railway accessibility are negatively associated with urban-rural income disparity,and the former having a greater effect size.Moreover,there is a substitution effect between highway accessibility and railway accessibility in the whole sample.Furthermore,these associations differ in geographic regions.In the central region,highway accessibility is more important in reducing the urban-rural income disparity,but its effect is weakened with the increase of railway accessibility.In the western region,railway accessibility has a larger effect on narrowing the urban-rural income disparity,and this effect is strengthened by the increase of highway accessibility.We conclude that improving transportation accessibility is conducive to reducing the urban-rural income disparity but its effect is spatial heterogenetic.Highways and railways should be developed in a coordinated manner to promote an integrated transport network system.

Factors Influencing Proppant Transportation and Hydraulic Fracture Conductivity in Deep Coal Methane Reservoirs

The gas production of deep coalbed methane wells in Linxing-Shenfu block decreases rapidly,the water output is high,the supporting effect is poor,the effective supporting fracture size is limited,and the migration mechanism of proppant in deep coal reservoir is not clear at present.To investigate the migration behavior of proppants in complex fractures during the volume reconstruction of deep coal and rock reservoirs,an optimization test on the conductivity of low-density proppants and simulations of proppant migration in complex fractures of deep coal reservoirs were conducted.The study systematically analyzed the impact of various fracture geometries,proppant types and fracturingfluid viscosities on proppant distribution.Furthermore,the study compared the outcomes of dynamic proppant transport experiments with simulation results.The results show that the numerical simulation is consistent with the results of the proppant dynamic sand-carrying experiment.Under the conditions of low viscosity and large pumping-rate,a high ratio of 40/70 mesh proppant can facilitate the movement of the proppant to the depths of fractures at all levels.The technical goal is to create comprehensive fracture support within intricate trapezoidal fractures in deep coal and rock reservoirs without inducing sand plugging.The sand ratio is controlled at 15%–20%,with a proppant combination ratio of 40/70:30/50:20/40=6:3:1.Proppant pumping operations can effectively address the issue of poor support in complex fractures in deep coal formations.The research results have been successfully applied to the development of deep coalbed methane in the Linxing-Shenfu block,Ordos Basin.

Analyzing the transportation infrastructure-rural industry integration relationship in China

Transportation infrastructure is crucial to China’s economic growth because it substantially contributes to the holistic development of rural primary,secondary,and tertiary industries.This study innovatively examines transportation infrastructure and urbanization levels to explore,both theoretically and empirically,their relationship with the holistic development of primary,secondary,and tertiary industries in rural China,and the mediating role of urbanization on this relationship.We employed fixed-effects models,the entropy weight approach,mixed regression,and generalized method of moments to analyze the data of 30 provinces across China from 2013 to 2020.The results indicate that the construction of transportation infrastructure directly fosters the collective advancement of such industries in rural areas and that urbanization partially mediates the transportation infrastructure-rural industry integration relationship.However,the western region shows disparities in the integrated development of these sectors.Further analysis reveals that foreign investments amplify the positive influence of transportation infrastructure on rural industry integration.Essentially,the enhancement of rural transportation infrastructure,promotion of urbanization,implementation of strategic planning,and strengthening of support mechanisms are crucial aspects in the comprehensive development of rural industries and the achievement of rural revitalization in China.

A Study on Integrated Construction of Luzhou Comprehensive Transportation Hub

The target of integrated construction of comprehensive transportation hub is to integrate the traffic resources,achieve butt joint of pan-regional transportation mode,and finally realize the"seamless connection"of the goods and"zero transfer"of the passenger traffic.Relying on the particularity of the geographical location and the convenience of the Yangtze River channel,Luzhou puts forth effort to build a comprehensive transport hub in Southern Sichuan and has made great efforts in traffic infrastructure construction.However,there are still some problems.Combining practice of Luzhou,using the advanced experience of foreign and domestic cities for reference,the paper pointed out that for the sake of constructing a comprehensive transportation hub,we need to build the traffic integration on the basis of the efficiency.Besides,the paper proposed the strategies for construction.

Optimizing a Transportation System Using Metaheuristics Approaches (EGD/GA/ACO): A Forest Vehicle Routing Case Study

The large-scale optimization problem requires some optimization techniques, and the Metaheuristics approach is highly useful for solving difficult optimization problems in practice. The purpose of the research is to optimize the transportation system with the help of this approach. We selected forest vehicle routing data as the case study to minimize the total cost and the distance of the forest transportation system. Matlab software helps us find the best solution for this case by applying three algorithms of Metaheuristics: Genetic Algorithm (GA), Ant Colony Optimization (ACO), and Extended Great Deluge (EGD). The results show that GA, compared to ACO and EGD, provides the best solution for the cost and the length of our case study. EGD is the second preferred approach, and ACO offers the last solution.

Research on a TOPSIS energy efficiency evaluation system for crude oil gathering and transportation systems based on a GA-BP neural network

As the main link of ground engineering,crude oil gathering and transportation systems require huge energy consumption and complex structures.It is necessary to establish an energy efficiency evaluation system for crude oil gathering and transportation systems and identify the energy efficiency gaps.In this paper,the energy efficiency evaluation system of the crude oil gathering and transportation system in an oilfield in western China is established.Combined with the big data analysis method,the GA-BP neural network is used to establish the energy efficiency index prediction model for crude oil gathering and transportation systems.The comprehensive energy consumption,gas consumption,power consumption,energy utilization rate,heat utilization rate,and power utilization rate of crude oil gathering and transportation systems are predicted.Considering the efficiency and unit consumption index of the crude oil gathering and transportation system,the energy efficiency evaluation system of the crude oil gathering and transportation system is established based on a game theory combined weighting method and TOPSIS evaluation method,and the subjective weight is determined by the triangular fuzzy analytic hierarchy process.The entropy weight method determines the objective weight,and the combined weight of game theory combines subjectivity with objectivity to comprehensively evaluate the comprehensive energy efficiency of crude oil gathering and transportation systems and their subsystems.Finally,the weak links in energy utilization are identified,and energy conservation and consumption reduction are improved.The above research provides technical support for the green,efficient and intelligent development of crude oil gathering and transportation systems.

An Efficient Approach for Transforming Unbalanced Transportation Problems into Balanced Problems in Order to Find Optimal Solutions

In operations research, the transportation problem (TP) is among the earliest and most effective applications of the linear programming problem. Unbalanced transportation problems reflect the reality of supply chain and logistics situations where the available supply of goods may not precisely match the demand at different locations. To deal with an unbalanced transportation problem (UTP), it is essential first to convert it into a balanced transportation problem (BTP) to find an initial basic feasible solution (IBFS) and hence the optimal solution. The present paper is concerned with introducing a new approach to convert an unbalanced transportation problem into a balanced one and as a consequence to obtain optimum total transportation cost. Numerical examples are provided to demonstrate the suggested method.

Existing Case of Transportation System in Turkey and Transportation Trends in Istanbul

Transportation sector is one of the most important elements of a country’s economy with its highway,railway,airway and seaway modes,besides the information and communication infrastructure.Transportation sector has a pattern that affects the society continuously with its economic and social inputs that has a significant role in economies of countries in terms of being an important part of manufacturing process and effects of sizable investments on economy.Demands of more comfortable,more reliable,more safe and more punctual transport in developing economy is an arising trend worldwide and this shows an increase the importance of the transportation sector.Establishment of an efficient and functional transportation system is closely related with traffic safety,intermodal integration and balanced modal distribution.In Turkey,an important improvement has been achieved in these issues,but also some basic constitutive problems are still continuing.These constitutional problems can be summarized as providing traffic safety,integration of innovative implementations to transportation system,enhancing of infrastructure and an effective usage of existing infrastructure.

A time-space network-based model for transportation service optimization of China Railway Express

This paper describes the development and optimization plans for the China Railway Express(CR Express).As a new type of international land transport organization,CR Express has emerged with the continuous expansion of China toward European investment and trade,and in particular,has expanded with the continuous progress of the One Belt and One Road(OBOR)initiative.In addition to improving the service quality of CR Express,the operating costs must be reduced for developing“smart railways”that serve“smart cities”.We propose a dualobjective-based function mathematical optimization model;the satisfaction of the cargo owner is considered,and the timeliness,transportation capacity,and goods category constraints of CR Express transportation are designed.Moreover,we present the normalized equivalent method of the two-objective function of the model.Finally,a case study is conducted against the background of certain trains in the western corridor of CR Express to validate the effectiveness of the model and research methods proposed in this study.

Analysis of Historic Pavement and Bridge Conditions and Alternative Funding Levels for the Michigan Department of Transportation

In 1997 the Michigan Department of Transportation (MDOT) established an ambitious set of condition targets for its pavements and bridges, and the Department received increased revenue from a 4-cent-per-gallon increase in the state motor fuels tax to help meet its targets. However, over time, actual revenue was less than both what was initially estimated as needed to meet the targets and what was projected from the tax increase. Consequently, actual conditions were projected to fall short of the target levels, so the department issued bonds to address the shortfall through 2012. To support deliberations on future funding, in 2013 MDOT performed an analysis of historic conditions to determine what additional fuel tax revenues would have been required beginning in 1997 to: replace bond revenues used to fund pavement and bridge projects from 1997 to 2012;and enable MDOT to meet its condition targets. The analysis was performed using data on actual pavement and bridge funding and conditions;as well as predicted funding and conditions for different hypothetical increases in fuel taxes. The analysis concluded that, in addition to the actual increase of 4 cents per gallon, a fuel tax increase of another 10 cents per gallon would have been required in 1997 to replace bond revenue used for pavement and bridges and allow MDOT to meet its condition targets. The analysis results were used to help inform the discussion of Michigan’s target asset conditions and funding, and demonstrate application of MDOT’s pavement and bridge management systems for performing historic analyses.

A Study on Optimizing the Double-Spine Type Flow Path Design for the Overhead Transportation System Using Tabu Search Algorithm

Optimizing Flow Path Design(FPD)is a popular research area in transportation system design,but its application to Overhead Transportation Systems(OTSs)has been limited.This study focuses on optimizing a double-spine flow path design for OTSs with 10 stations by minimizing the total travel distance for both loaded and empty flows.We employ transportation methods,specifically the North-West Corner and Stepping-Stone methods,to determine empty vehicle travel flows.Additionally,the Tabu Search(TS)algorithm is applied to branch the 10 stations into two main layout branches.The results obtained from our proposed method demonstrate a reduction in the objective function value compared to the initial feasible solution.Furthermore,we explore howchanges in the parameters of the TS algorithm affect the optimal result.We validate the feasibility of our approach by comparing it with relevant literature and conducting additional tests on layouts with 20 and 30 stations.

Research on the Interactive Impact of Transportation Systems on Socio-Economic Development

This paper aims to explore the interactive impact between transportation systems and socio-economic development,employing Structural Equation Modeling(SEM)to analyze data from 31 provincial-level administrative regions in China from 2013 to 2022.It comprehensively considers key indicators from the economic,social,and transportation sectors.The paper constructs a model encompassing 5 latent variables and 15 observed variables.Through in-depth analysis,it reveals the promoting role of transportation systems on economic growth and social development,as well as the demand for transportation system construction and optimization driven by socio-economic development levels.The results indicate that an efficient transportation system can not only directly drive economic growth but also indirectly promote social development by improving social welfare and enhancing quality of life.This paper provides new insights into understanding the complex relationship between transportation systems and socio-economic development and holds significant implications for policymakers in optimizing transportation infrastructure to foster economic and social development.

Analysis of the Application of Artificial Intelligence in Transportation

With the advancement of the information age,the transportation industry has experienced rapid growth,leading to an expansion in the scale and number of highway constructions.However,this development has also given rise to numerous traffic issues,including frequent vehicle congestion and traffic accidents.To address these problems,it is essential to leverage modern technology for real-time information collection and analysis,providing robust technical support for intelligent transportation systems.This paper focuses on artificial intelligence(AI)technology,explaining its concept and its role in intelligent transportation.It reviews the various application areas and analyzes the use of AI in intelligent transportation.Finally,it proposes strategies for applying AI to promote the healthy development of intelligent transportation systems.

Automobile Transportation Logistics Supply Chain Management Strategy

To enhance the management level and quality of the automobile transportation logistics supply chain and promote innovation and development in automobile transportation logistics enterprises,it is essential to strengthen the construction of the automobile transportation logistics supply chain management model.This can be achieved through the gradual improvement of the automobile transportation logistics management process,ensuring that the management of the automobile transportation logistics supply chain proceeds in an orderly manner.The aim is to improve automobile transportation and logistics service levels while meeting the changing market supply needs.This will enable automobile transportation and logistics enterprises to maintain steady economic benefits and enhance their core competitiveness in the market.Therefore,this paper has conducted a comprehensive exploration and research on managing the automobile transportation logistics supply chain.Corresponding management strategies are proposed as a starting point to achieve the aforementioned goals.

Design and Application of Intelligent Control System for Molten Iron Transportation Based on 5G Technology

Molten transport is an important link in the iron and steel enterprise production,involves many complex factors,artificial management is difficult.Therefore,puts forward a kind of molten iron transport wisdom control system based on 5G technology,which mainly contains the intelligent identification tracking system,equipment status collection information acquisition system,locomotive vehicle terminal system,etc.Combined with the analysis of the actual application situation,the system could integrate all the processes and elements of molten iron produc-tion and transportation,realize the integration of operation and management,and also promote the improvement of the turnover efficiency of molten iron tank,reduce the demand for personnel,and reduce the labor cost.

Combinations of Transportation Policies to Promote BRT Usage Using Artificial Society Model

Various transportation systems have been developed in recent years.In this study,an artificial society model is developed to examine the combination of transportation policies in urban areas.In this model,each trip maker selects the primary and terminal transportation modes.An artificial society model is applied to the southeastern region of Osaka City,Japan.The effects of introducing BRT(bus rapid transit,primary transportation)and on-demand buses(terminal transportation)are investigated.The results confirm that BRT is used by a certain number of users.An increase in the use of BRT will increase the amount of walking,thus resulting in a healthy city.However,on-demand buses are rarely used as terminal transportation.Additionally,the development of bicycle parking stations near BRT stops is shown to be effective in the northern section of the BRT route.

Transportation mobility during COVID-19:a systematic review and bibliometric analysis

The COVID-19 pandemic has significantly affected global transportation mobility,presenting unprecedented challenges to transportation management.Public transit and ride-hailing services saw a drastic reduction in ridership,leading to an increased inclination towards private vehicles.The pandemic also altered travel patterns and individual mobility due to various COVID-19 protocols.This study conducted a comprehensive review of 96 academic papers spanning from January 1,2020,to December 31,2022,focusing on transportation and mobility using the Scopus database.Three major themes were identified:‘Impact on Ride-Hailing Services',‘Impact on Mode Preference',and‘Impact on Trip Purpose',with subdivisions based on keywords and key findings extracted using VOSviewer.The pandemic significantly impacted ride-hailing services,altering demand,usage,and safety measures.Mode preference shifted towards private vehicles due to safety concerns.The present study underscores the long-term implications of the pandemic,emphasizing recovery strategies for ride-hailing services and mode preferences post-pandemic.It highlights the need for sustainable transportation policies,advocating for enhanced public transportation systems,promoting active travel modes,and addressing socioeconomic disparities in mobility patterns.The findings emphasize the need for resilient transportation strategies in the face of future disruptions.

Building trust for traffic flow forecasting components in intelligent transportation systems via interpretable ensemble learning

Traffic flow forecasting constitutes a crucial component of intelligent transportation systems(ITSs).Numerous studies have been conducted for traffic flow forecasting during the past decades.However,most existing studies have concentrated on developing advanced algorithms or models to attain state-of-the-art forecasting accuracy.For real-world ITS applications,the interpretability of the developed models is extremely important but has largely been ignored.This study presents an interpretable traffic flow forecasting framework based on popular tree-ensemble algorithms.The framework comprises multiple key components integrated into a highly flexible and customizable multi-stage pipeline,enabling the seamless incorporation of various algorithms and tools.To evaluate the effectiveness of the framework,the developed tree-ensemble models and another three typical categories of baseline models,including statistical time series,shallow learning,and deep learning,were compared on three datasets collected from different types of roads(i.e.,arterial,expressway,and freeway).Further,the study delves into an in-depth interpretability analysis of the most competitive tree-ensemble models using six categories of interpretable machine learning methods.Experimental results highlight the potential of the proposed framework.The tree-ensemble models developed within this framework achieve competitive accuracy while maintaining high inference efficiency similar to statistical time series and shallow learning models.Meanwhile,these tree-ensemble models offer interpretability from multiple perspectives via interpretable machine-learning techniques.The proposed framework is anticipated to provide reliable and trustworthy decision support across various ITS applications.