Transportation Resource Allocation Research Articles

A Fuzzy Wavelet Neural Network (FWNN) and Hybrid Optimization Machine Learning Technique for Traffic Flow Prediction

Traffic go with the flow forecasting is essential in urban planning and management, optimizing transportation structures and resource allocation. However, accurately predicting visitors glide is tough because of its inherent complexity, nonlinearity, and diverse uncertain factors. The trouble declaration underscores the issue in as it should be forecasting site visitors flow, mainly in urban environments characterized through dynamic and complex site visitor’s styles. In the existing paintings there are numerous traditional devices getting to know models used for visitors flow prediction, however those conventional strategies show off barriers in reaching excessive prediction accuracy. Therefore, the proposed work targets to put into effect hybrid optimization techniques for correct prediction in shipping machine. Here fuzzy wavelet neural community (FWNN) is used to address complicated nonlinear structures with uncertain conditions and hybrid optimization method called hybrid firefly and particle swarm optimization (HFO-PSO) which combines the exploration and exploitation talents of firefly and this fusion allows the version to capture intricate visitor’s styles efficiently and optimize the prediction technique, improving accuracy and efficiency. Moreover, the prediction performance of the proposed model is established and compared by means of the usage of distinct measures.

Forecasting Road Freight and Passenger Transport Demands in Türkiye Using the Exponential Smoothing

Exponential smoothing is a popular technique used to analyze and forecast trends in various industries such as road transportation and passenger transportation. This method is used to calculate weighted averages using historical data and adjust forecasts based on recent trends. In the Turkish context, forecasting transportation demands using exponential smoothing provides valuable information for transportation planning and resource allocation. The increasing number of vehicles has caused many negative environmental consequences. This study analyzed ten years of data on road freight and passenger transportation on a regional scale in order to make future predictions. In the study, solution suggestions are presented based on the findings and the policies that should be implemented to solve the problem are evaluated.

Game Study on Morning Peak Road Congestion Problem

The morning peak road congestion problem has always been a hot issue in urban traffic management. Road congestion during the morning peak not only affects the travel efficiency of travelers, but also has a serious negative impact on the urban environment and economic development. This article starts from the perspective of game theory and focuses on the problem of road selection. This article considers government supervision and builds a game model from the two game subjects of the driver and the traffic controller. This article analyzes the relationship between the driver and the driver, the driver and the traffic controller. This paper studies the impact of traffic time, whether the driver investigates in advance, and whether the traffic commander conducts road command on the stable strategy of the driver's road choice game. The research results of this article show that drivers and drivers can achieve Nash equilibrium by choosing different roads, and drivers adopting collaborative strategies during the morning peak period can effectively alleviate road congestion. Under the condition of ensuring the cost of arranging traffic commanders for drivers and the government, drivers can investigate the road in advance and traffic commanders can direct road 2, which can effectively promote the smooth operation of the traffic system. At the same time, this article puts forward targeted policy suggestions, aiming to optimize the allocation of transportation resources, improve road traffic efficiency, reduce morning peak road congestion, and provide scientific reference and decision-making support for urban traffic management.

Addressing uncertainty in closed-loop supply chain networks: a multi-objective approach to integrated production and transportation problems

PurposeThis study aims to address the inherent uncertainties within closed-loop supply chain (CLSC) networks through the application of a multi-objective approach, specifically focusing on the optimization of integrated production and transportation processes. The primary purpose is to enhance decision-making in supply chain management by formulating a robust multi-objective model.Design/methodology/approachIn dealing with uncertainty, this study uses Pythagorean fuzzy numbers (PFNs) to effectively represent and quantify uncertainties associated with various parameters within the CLSC network. The proposed model is solved using Pythagorean hesitant fuzzy programming, presenting a comprehensive and innovative methodology designed explicitly for handling uncertainties inherent in CLSC contexts.FindingsThe research findings highlight the effectiveness and reliability of the proposed framework for addressing uncertainties within CLSC networks. Through a comparative analysis with other established approaches, the model demonstrates its robustness, showcasing its potential to make informed and resilient decisions in supply chain management.Research limitations/implicationsThis study successfully addressed uncertainty in CLSC networks, providing logistics managers with a robust decision-making framework. Emphasizing the importance of PFNs and Pythagorean hesitant fuzzy programming, the research offered practical insights for optimizing transportation routes and resource allocation. Future research could explore dynamic factors in CLSCs, integrate real-time data and leverage emerging technologies for more agile and sustainable supply chain management.Originality/valueThis research contributes significantly to the field by introducing a novel and comprehensive methodology for managing uncertainty in CLSC networks. The adoption of PFNs and Pythagorean hesitant fuzzy programming offers an original and valuable approach to addressing uncertainties, providing practitioners and decision-makers with insights to make informed and resilient decisions in supply chain management.

Travel Characteristics of Urban Residents Based on Taxi Trajectories in China: Beijing, Shanghai, Shenzhen, and Wuhan

With the advancement of urban modernization, more and more residents are flocking to large cities, leading to problems such as severe traffic congestion, uneven distribution of spatial resources, and deterioration of the urban environment. These challenges pose a serious threat to the coordinated development of cities. In order to better understand the travel behavior of metropolitan residents and provide valuable insights for urban planning, this study utilizes taxi trajectory data from the central areas of Beijing, Shanghai, Shenzhen, and Wuhan. First, the relationship between daytime taxi drop-off points and urban amenities is explored using Ordinary Least Squares (OLS). Subsequently, Geographically Weighted Regression (GWR) techniques were applied to identify spatial differences in these urban drivers. The results show that commonalities emerge across the four cities in the interaction between external transport stops and commercial areas. In addition, the average daily travel patterns of residents in these four cities show a trend of “three peaks and three valleys”, indicating the commonality of travel behavior. In summary, this study explores the travel characteristics of urban residents, which can help urban planners understand travel patterns more effectively. This is crucial for the strategic allocation of transport resources across regions, the promotion of sustainable urban transport, and the reduction in carbon emissions.

Clinical laboratory strategies for managing pandemic outbreaks

This review article comprehensively examines clinical laboratory strategies for managing pandemic outbreaks, with a particular focus on lessons learned from the COVID-19 pandemic. Drawing upon an extensive analysis of existing literature from databases such as PubMed, Web of Science, and Cochrane, as well as manual searches on Google Scholar, the study aims to provide insights into key aspects of pandemic preparedness and response. The literature review encompasses diverse combinations of medical terminology, emphasizing the role and response of clinical laboratories during pandemics. The primary focus areas include rapid test development and deployment, increased testing capacity, sample collection, and transportation protocols, data management, personnel safety, resource allocation, adaptability, and quality control measures. The inclusion of articles in this study adheres to rigorous criteria, ensuring a thorough and robust review process. The findings highlight the critical importance of rapid and accurate diagnostic testing, especially in the early stages of a pandemic, to facilitate timely interventions and containment. Efficient sample collection and transportation systems are crucial for maintaining the integrity of specimens, while advanced data management and reporting systems contribute to informed decision-making. Adaptability and flexibility are identified as indispensable traits for navigating the dynamic challenges of a pandemic, and stringent quality control measures are foundational for upholding the accuracy of diagnostic testing. The review underscores the collaborative efforts needed among clinical laboratories, public health agencies, and research institutions to strengthen global pandemic preparedness and response strategies.

Multi-Scale Non-Local Spatio-Temporal Information Fusion Networks for Multi-Step Traffic Flow Forecasting

Traffic flow prediction is a crucial research area in traffic management. Accurately predicting traffic flow in each area of the city over the long term can enable city managers to make informed decisions regarding the allocation of urban transportation resources in the future. The existing traffic flow prediction models either give insufficient attention to the interactions of long-lasting spatio-temporal regions or extract spatio-temporal features in a single scale, which ignores the identification of traffic flow patterns at various scales. In this paper, we present a multi-scale spatio-temporal information fusion model using non-local networks, which fuses traffic flow pattern features at multiple scales in space and time, complemented by non-local networks to construct the global direct dependence relationship between local areas and the entire region of the city in space and time in the past. The proposed model is evaluated through experiments and is shown to outperform existing benchmark models in terms of prediction performance.

The Current Development and Optimization of Smart Public Transportation in Taiyuan City

"With the development of technology and the smartification of cities, the urbanization process is accelerating rapidly. The population and the number of motor vehicles in cities are increasing rapidly, leading to evident issues such as traffic congestion and air pollution. Smart public transportation, as an integral component of smart cities, can reduce passengers' travel costs, improve travel efficiency to some extent, and provide big data support for the development of smart transportation and even smart cities. It is a cost-effective, convenient, and environmentally friendly mode of transportation.This article first analyzes the current situation of smart public transportation in Taiyuan city. It points out issues such as uneven allocation of public transportation resources, prolonged travel times for passengers using public transportation, and overcrowding during peak hours. Drawing on the development experiences of smart public transportation in cities both domestically and internationally, the article proposes optimization suggestions for the current state of smart public transportation in Taiyuan. These include refined management of public transportation, skip-stop operations, smart resource allocation, and improvement of infrastructure construction. The aim is to provide theoretical guidance for the optimization and improvement of smart public transportation in Taiyuan, enabling more efficient development of 'smart public transportation' in the city.".

A Multi-Scale Residual Graph Convolution Network with hierarchical attention for predicting traffic flow in urban mobility

Accurate prediction of traffic flow is essential for optimizing transportation resource allocation and enhancing urban mobility efficiency. However, traffic data generated daily are vast and complex, involving dynamic and intricate changes in the traffic road network and traffic flow. Therefore, real-time and accurate prediction of traffic flow is a challenging task that requires modeling the intricate spatial–temporal dynamics of traffic data. In this paper, we propose a novel approach for traffic flow prediction, based on a Multi-Scale Residual Graph Convolution Network with hierarchical attention. First, we design a novel encoder–decoder with multi-independent channels to capture traffic flow information from different time scales and diverse temporal dependencies. Second, we employ a coupled graph convolution network with residual graph attention to dynamically learn the varying spatial features among and within traffic stations. Third, we utilize channel attention to fuse the multi-scale spatial–temporal dependencies and accurately predict traffic flow. We evaluate the proposed approach on multiple benchmark datasets, and the experimental results demonstrate its superior performance compared to state-of-the-art approaches in terms of various metrics.

Driving impact and spatial effect of the digital economy development on carbon emissions in typical cities: a case study of Zhejiang, China.

The digital economy (DE) not only drives economic innovation and development but also has significant environmental effects by promoting lower carbon emissions. To investigate the spatial effects of DE on urban carbon emissions, this study comprehensively measures the level of DE development based on the panel data from 11 typical cities in Zhejiang Province from 2011 to 2020, by comparing analysis using different regression models. The following conclusions are obtained: (1) The total carbon emissions (TC) of Zhejiang cities in general show a fluctuating change trend of first increasing and then slowly decreasing, while carbon emission intensity and carbon emission per capita in general show a fluctuating change trend of decreasing. Cities with high TC are primarily concentrated in the Hangzhou Bay city cluster, accounted for 62 ~ 65% of the province's carbon emissions. The development of the DE in Zhejiang cities shows steady growth, but there are large differences among cities, with Hangzhou and Ningbo standing out as particularly prominent. (2) There is a significant inverted U-shaped relationship between the DE and the level of carbon emissions in Zhejiang Province. The influence coefficient of the DE on the primary term of TC is 0.613, and the influence coefficient of the quadratic term of TC is - 1.008. (3) In terms of the spatial spillover effect of the DE on carbon emissions, the study finds that compared to the direct effect, the spatial spillover effect is not significant. However, the allocation of transport resources shows a positive spatial spillover effect (increasing carbon emissions, coefficient value is 0.138), while technological progress shows a somewhat negative spatial spillover effect (decreasing carbon emissions, coefficient value is - 0.035). (4) The study also finds that the smart city pilot policy significantly reduces urban carbon emissions. Moreover, the effect of the DE on carbon emissions is confirmed through the significance test of the quadratic term when replacing the geographical and economic distance weight matrices. This indicates that the empirical findings are robust to these tests. Finally, several countermeasures to reduce carbon emissions are proposed from the perspective of DE development.

Understanding the spatio-temporally heterogeneous effects of built environment on urban travel emissions

Transportation has become one of the fastest-growing fields for greenhouse gas emissions. It is important to promote the coordinated development of cities and transportation. To deeply understand the emission distribution for urban travel, this study first applies a map matching algorithm to correct the vehicle Global Positioning System (GPS) trajectories on the road network and calculates the travel emissions by the COmputer Programme to calculate Emissions from Road Transport (COPERT) model. Most studies on the impact of built environment on travel emissions only consider the spatially heterogeneity of variables. Although the traditional GTWR can consider the spatio-temporally heterogeneous effects, the spatio-temporal bandwidth is selected at the same scale in the operation process, which limits the relationship analysis among diverse variables. Therefore, this study adopts a unilateral geographically and temporally weighted regression model (UGTWR) and its multiscale extended model (MUGTWR) to estimate the spatio-temporally heterogeneous effects of the built environment on urban travel emissions. In addition, considering the scale effect and zoning effect of the spatial geographical unit selection on the results, we conducted experiments separately on three spatial units: sub-district scale, Traffic Analysis Zones (TAZs) and grid scale to compare and obtain the most appropriate partitioning schemes. The results show that, the fitting effects of UGTWR and MUGTWR are better than that of GTWR, indicating that considering flexible bandwidth selection can effectively improve the accuracy of simulation. Moreover, the temporal and spatial bandwidth values of each independent variable calculated by MUGTWR reflect the heterogeneous characteristics in space and time of different built environment factors, which can provide scientific suggestions for formulating urban planning. The research results can provide planning strategies for optimizing the allocation of local transportation resources and guiding low-carbon travel behaviors.

Research on Market Share Prediction of Highway Passenger Transport Based on Exponential Smoothing Method

Highway transportation is an important part of our country traffic transportation system, taking on most of the capacity demand in passenger transport markets. But with the rapid development of domestic rail transportation technology, people's travel mode has gradually changed from highway transportation to rail transportation. This makes the highway passenger transport management department must consider the impact of the change of people's travel mode on the highway passenger transport market demand when making production plans. The market share of highway passenger transport is an important index to measure the development level of highway passenger transport, which can directly reflect the supply-demand relationship between highway passenger transport and passenger transport market. Therefore, this paper selects the market share of highway passenger transport as the prediction evaluation index, and predicts and analyzes the market share data of highway passenger transport in Henan Province from 2010 to 2021 based on the exponential smoothing method. It mainly calculates the single exponential smoothing results under several different smoothing coefficients by using the smoothing analysis tool in EXCEL, and determines the optimal smoothing coefficient by taking the minimum root mean square error (RMSE) as the criterion. Then, it solves the lag defect of the single exponential smoothing prediction results by using the quadratic exponential smoothing. Finally, the trend prediction model of highway passenger transport market share in Henan Province is obtained. The prediction results of this model can guide the rational allocation of highway transportation resources and the formulation of passenger transport production plan in Henan Province.

Travel Mode Choice Prediction Using Imbalanced Machine Learning

Travel mode choice prediction is critical for travel demand prediction, which influences transport resource allocation and transport policies. Travel modes are often characterised by severe class imbalance and inequality, which leads to the inferior predictive performance of minority modes and bias in travel demand prediction. In existing studies, the class imbalance in travel mode prediction has not been addressed with a general approach. Basic resampling methods were adopted without much investigation, and the performance was assessed by commonly used metrics (e.g., accuracy), which is not suitable for predicting highly imbalanced modes. To this end, this paper proposes an evaluation framework to systematically investigate the combination of six over/undersampling techniques and three prediction methods. In a case study using the London Passenger Mode Choice dataset, results show that applying over/undersampling techniques on travel mode substantially improves the F1 score (i.e., the harmonic mean of precision and recall) of minority classes, without considerably downgrading the overall prediction performance or model interpretation. These findings suggest that combining over/undersampling techniques and statistical/machine-learning methods is appropriate for predicting travel mode, which effectively mitigates the influence of class imbalance while achieving high predictive accuracy and model interpretation. In addition, the combination of over/undersampling techniques and prediction methods enriches the model options for predicting mode choice, which would better support transport planning.

Measurement Method of Comprehensive Transportation Development Quality Based on Transportation Efficiency

Transportation is the forerunner of economic and social development. Therefore, the high-quality development of comprehensive transportation is of great significance to ensure overall economic and social progress and the smooth implementation of major national strategies. The essence of high-quality development in transportation is to realize the optimal allocation of transportation resources. This study handles two aspects. First, the factors that reflect the quality of comprehensive transportation development are defined and analyzed, and an evaluation system is proposed to build China’s comprehensive transportation development quality with transportation efficiency as the core is proposed, taking into account transportation infrastructure and transportation scale. Second, the static comprehensive evaluation value is calculated by the entropy weight method, and then the incentive control model is constructed by introducing incentive factors to achieve a dynamic comprehensive evaluation of comprehensive transportation development. The research results not only propose new indicators but also evaluate different modes of transportation within the same dimension. The results show that the quality of comprehensive transportation development in China is generally on the rise, but there are obvious regional differences. The proposed model is derived from evaluation cases in transportation-related fields and has not yet been applied in the transportation field. It can help understand the development status of the industry and assist in policy formulation.

Traffic Flow Forecasting in the COVID-19: A Deep Spatial-temporal Model Based on Discrete Wavelet Transformation

Traffic flow prediction has always been the focus of research in the field of Intelligent Transportation Systems, which is conducive to the more reasonable allocation of basic transportation resources and formulation of transportation policies. The spread of COVID-19 has seriously affected the normal order in the transportation sector. With the increase in the number of infected people and the government's anti-epidemic policy, human outgoing activities have gradually decreased, resulting in increasingly obvious discreteness and irregularities in traffic flow data. This article proposes a deep-space time traffic flow prediction model based on discrete wavelet transform (DSTM-DWT) to overcome the highly discrete and irregular nature of the new crown epidemic. First, DSTM-DWT decomposes traffic flow into discrete attributes, such as flow trend, discrete amplitude, and discrete baseline. Second, we design the spatial relationship of the transportation network as a graph and integrate the new crown pneumonia epidemic data into the characteristics of each transportation node. Then, we use the graph convolutional network to calculate the spatial correlation of each node, and the temporal convolutional network to calculate the temporal correlation of the data. In order to solve the problem of high discreteness of traffic flow data during the epidemic, this article proposes a graph memory network (GMN), which is used to convert discrete magnitudes separated by discrete wavelet transform into high-dimensional discrete features. Finally, use DWT to segment the predicted traffic data, and then perform the inverse discrete wavelet transform between the newly segmented traffic trend and discrete baseline and the discrete model predicted by GMN to obtain the final traffic flow prediction result. In simulation experiments, this work was compared with the existing advanced baselines to verify the superiority of DSTM-DWT.

National Economic Benefits of Railway Transportation Analyzed Using Data Mining

This study focuses on the economic benefits of railway transportation from the aspect of data mining using convolution neural network (CNN), long short-term memory (LSTM), and multiple linear regression (MLRA) models. Improved CNN and LSTM (CNN-LSTM), and CNN and bidirectional LSTM (CNN-Bi-LSTM) models have been developed to enhance learning. The case data sets include operating mileage, and passenger and freight turnover for four transportation modes (railway, highway, aviation, and water transportation) from 1952 to 2020 in China; various evaluation indexes are used to verify model effectiveness. The CNN and LSTM model prediction error rates are 29% and 22%, respectively, verifying the role of an integrated transportation system in railway transportation and the time effect as a national economic benefit of railway transportation, respectively. The CNN-LSTM model prediction error rate is 12%, indicating that the economic benefits of railway transportation depend on the structure of various transportation modes and the time stage of transportation resource allocation. The prediction error rate of the CNN-Bi-LSTM model is 14%, suggesting the irreversibility of the impact of railway transportation resources on economic benefits. The MLRA model error rate is lower than those of the CNN and LSTM models, at 19%, but higher than those of the other models. The CNN-LSTM model is recommended to quantify the economic benefits of railway transportation. This study illustrates the systematic nature, periodicity, time lag, and irreversibility of railway transportation and economic development, providing a theoretical basis for the formulation of transportation development and investment plans.

Impact of Interfacility Patient Transport for Appendectomy on Patient Outcomes

<h3>Introduction</h3> Patients presenting to emergency departments with complaints requiring emergency general surgery (EGS) often require transport to tertiary care because fewer than 50% of hospitals have EGS services. The need for interfacility transport to tertiary care is associated with increased hospital length of stay (LOS) and morbidity among medical patients, however there is limited data available evaluating the cost and impact of transports among EGS patients. The purpose of this study was to analyze the costs, transport resource utilization, and outcomes of EGS patients transferred to tertiary care with acute appendicitis. <h3>Methods</h3> This was an IRB approved retrospective study of adult patients transferred from an in-network referral ED to a single tertiary care facility between 20 May 2015 & 30 September 2020 who were transferred with diagnosis of appendicitis. Data collected from the health system's electronic medical record (EMR) included patient demographics, emergency department and interfacility transport hemodynamics, diagnostic testing results, timeliness of referral and transport, transport level of care, social determinants of health, and patient charges. Data was analyzed with R version 1.0.2. Our Primary Outcome was the hospital length of stay and our secondary outcomes were time from initial presentation to incision, cost to patient, and transport resource allocation. <h3>Results</h3> A total of 480 adult patients were transferred for tertiary EGS care during the study period and were included in the final analysis. 89.4% of patients (n=429) received ambulance transport awhile 10.6% (n=51) were transported via private vehicle. All patients were discharged home alive. Critical Care Transport (CCT) teams transported 61.5% (n=295) of patients while Advanced Life Support (ALS) teams transported 26.0% (n=125). Although CCT teams were more likely than ALS teams to establish and maintain intravenous fluids (54.6% vs 37.6%, p=0.002) there was no difference in analgesia (36.9% vs 27.4% p=0.078), antiemetic (26.8% vs 20.0% p=0.178), or antibiotic (13.3% vs 6.4% p=0.062) administration between critical care and ALS providers. No life-saving interventions were provided by any transport team. Ambulance transport did not shorten hospital length of stay compared to transport via private vehicle (p=0.67). <h3>Conclusion</h3> In this single center study transport via ambulance did not reduce hospital length of stay compared to transport via private vehicle and there was no difference in the care provided between ALS and CCT teams.

The Influence of Social Determinants of Health on The Interfacility Transport of Patients for Appendicitis

<h3>Introduction</h3> Patients presenting to emergency departments with complaints requiring emergency general surgery (EGS) often require transport to tertiary care because fewer than 50% of hospitals have EGS services. The need for interfacility transport to tertiary care is associated with increased hospital length of stay (LOS) and morbidity among medical patients. Further Social Determinants of Health (SDOH) are known factors worsening patient outcomes. There is limited data available evaluating the presence and influence of SDOH among EGS patients transferred to tertiary care. The purpose of this study was to analyze the costs, transport resource utilization, and outcomes of EGS patients transferred to tertiary care with acute appendicitis. <h3>Methods</h3> This was an IRB approved retrospective study of adult patients transferred from an in-network referral ED to a single tertiary care facility between 20 May 2015 & 30 September 2020 who were transferred with diagnosis of appendicitis. Data collected from the health system's electronic medical record (EMR) included patient demographics, emergency department and interfacility transport hemodynamics, diagnostic testing results, timeliness of referral and transport, transport level of care, social determinants of health, and patient charges. Data was analyzed with R version 1.0.2. Our Primary Outcome was the hospital length of stay and our secondary outcomes were time from initial presentation to incision, cost to patient, and transport resource allocation. <h3>Results</h3> A total of 480 adult patients were transferred for tertiary EGS care during the study period and were included in the final analysis. 89.4% of patients (n=429) received ambulance transport awhile 10.6% (n=51) were transported via private vehicle. All patients were discharged home alive. SDOH were documented as present in 25.5% of patients transported via private vehicle and 30.8% of patients transferred via ambulance. The presence of SDOH did not length emergency department length of stay (p=0.12) or hospital length of stay (p=0.45). SDOH did not impact hospital length of stay when transport mode was also considered (p=0.447) <h3>Conclusion</h3> In this single center study, the presence of SDOH did not influence ED or hospital length of stay among patients transferred to tertiary care for appendectomy. Overall SDOH were poorly reported in the hospital and ambulance electronic medical record. Improved tracking of these social factors may alter the results of future research.

Evaluating the Comprehensive Development Level and Coordinated Relationships of Urban Multimodal Transportation: A Case Study of China’s Major Cities

Urban multimodal transportation effectively meets the diversified travel demand of residents. However, it also generates extensive development problems such as traffic congestion, exhaust emissions and low operational efficiency. Therefore, there is an urgent need in urban sustainable development to achieve the coordinated and stable development of various modes of transportation. In this study, we took 36 major cities in China as the research object; measured the comprehensive development level of urban multimodal transportation; used the coupling coordination degree model (CCDM) to research the coordinated development relationship among buses, rail transit, and taxis; and clarified the shortcomings of the coordinated development of multimodal transportation. The results show that the comprehensive development of urban multimodal transportation in China has shown a significant upward trend from 2016 to 2020, with an average annual growth rate of about 7.36%. There are significant differences in the development levels of multimodal transportation in different cities. In addition, the relationship among buses, rail transit, and taxis in the major cities in China presents a state of uncoordinated development. Therefore, the relevant departments of cities should optimize the allocation of transportation resources, in terms of infrastructure construction and operation, according to these development levels and coordination of multimodal transportation.

Application of an Adaptive Adjacency Matrix-Based Graph Convolutional Neural Network in Taxi Demand Forecasting

Accurate forecasting of taxi demand has facilitated the rational allocation of urban public transport resources, reduced congestion in urban transport networks, and shortened passenger waiting time. However, virtual station discovery and modelling of the demand when forecasting through graph convolutional neural networks remains challenging. In this study, the virtual station discovery problem was addressed by using a two-stage clustering approach, which considers the geographical and load characteristics of taxi demand. Furthermore, a fusion model combining non-negative matrix decomposition and a graph convolutional neural network was proposed in order to extract the features of the nodes for dimension reduction and adaptive adjacency matrix computation. By the construction of a local processing structure, further extraction of the local characteristics of the demand was achieved. The experimental results show that the method in this study outperforms state-of-the-art methods in terms of the root mean square error and average absolute value error. Therefore, the model proposed in this study is able to achieve accurate forecasting of taxi demand.