This study proposes a prediction model considering external weather and holiday factors to address the issue of accurately predicting urban taxi travel demand caused by complex data and numerous influencing factors.Th...This study proposes a prediction model considering external weather and holiday factors to address the issue of accurately predicting urban taxi travel demand caused by complex data and numerous influencing factors.The model integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)and Convolutional Long Short Term Memory Neural Network(ConvLSTM)to predict short-term taxi travel demand.The CEEMDAN decomposition method effectively decomposes time series data into a set of modal components,capturing sequence characteristics at different time scales and frequencies.Based on the sample entropy value of components,secondary processing of more complex sequence components after decomposition is employed to reduce the cumulative prediction error of component sequences and improve prediction efficiency.On this basis,considering the correlation between the spatiotemporal trends of short-term taxi traffic,a ConvLSTM neural network model with Long Short Term Memory(LSTM)time series processing ability and Convolutional Neural Networks(CNN)spatial feature processing ability is constructed to predict the travel demand for urban taxis.The combined prediction model is tested on a taxi travel demand dataset in a certain area of Beijing.The results show that the CEEMDAN-ConvLSTM prediction model outperforms the LSTM,Autoregressive Integrated Moving Average model(ARIMA),CNN,and ConvLSTM benchmark models in terms of Symmetric Mean Absolute Percentage Error(SMAPE),Root Mean Square Error(RMSE),Mean Absolute Error(MAE),and R2 metrics.Notably,the SMAPE metric exhibits a remarkable decline of 21.03%with the utilization of our proposed model.These results confirm that our study provides a highly accurate and valid model for taxi travel demand forecasting.展开更多
In view of the problem that the requirements of travel demand management and traffic policy-sensitivity are ignored during the establishment process of the travel demand forecasting model, a discrete-choice-based trav...In view of the problem that the requirements of travel demand management and traffic policy-sensitivity are ignored during the establishment process of the travel demand forecasting model, a discrete-choice-based travel demand forecasting model is proposed to demonstrate its applicability to travel demand management. A car-bus discrete choice model is established, including three variables, i. e,, individual socioeconomic characteristics, time, and cost, and the traffic policy-sensitivity is evaluated through two kinds of traffic policies： parking charges and bus priorities. The empirical results show that travel choice is insensitive to the policy of parking charges as 88. 41% of the travelers are insensitive to parking charges; travel choice is, however, sensitive to the policy of bus priorities as 67.70% of the car travelers and 77.02% of the bus travelers are sensitive to bus priorities. The discrete-choice-based travel demand forecasting model is quite policy-sensitive and also has a good adaptability for travel demand management when meeting the basic functions of the demand forecasting model.展开更多
In the last decades, there has been substantial development in modeling techniques of travel demand estimation. For low population areas the external trip estimation is important but usually neglected in travel demand...In the last decades, there has been substantial development in modeling techniques of travel demand estimation. For low population areas the external trip estimation is important but usually neglected in travel demand modeling process. In Egypt, the researches in this field are scarce due to lack of data. Accordingly, this paper aims to identify and estimate the main variables that affect the travel demand in low population areas, and to develop models to predict them. The study focused on the Port Said Govemorate in North East Egypt. A special questionnaire had been prepared in 2010 depending on interviews of passengers at basic taxi terminals in Port Said. And 2211 filled questionnaires were offering for research. To analyze the data, two modeling procedures were used. One is the multiple linear regression and the other is the generalized linear modeling （GLM） applying normal distributions. It is found that GLM procedure offers more suitable and accurate approach than the linear regression for developing number of trips. The final demand models have statistics within the acceptable regions and, also, they are conceptually reasonable. These results are so important for Egyptian highway authorities to improve the efficiency of highway transportation system in Egypt.展开更多
In this study, we examine the impacts that EVs （electric vehicles） have on vehicle usage patterns and environmental improvements, using our integrated travel demand forecasting model, which can simulate an individua...In this study, we examine the impacts that EVs （electric vehicles） have on vehicle usage patterns and environmental improvements, using our integrated travel demand forecasting model, which can simulate an individual activity-travel behavior in each time period, as well as consider an induced demand by decreasing travel cost. In order to examine the effects that charging/discharging have on the demand in electricity, we analyze scenarios based on the simulation results of the EVs＇ parking location, parking duration and the battery state of charge. From the simulation, result under the ownership rate of EVs in the Nagoya metropolitan area in 2020 is about 6%, which turns out that the total CO2 emissions have decreased by 4% although the situation of urban transport is not changed. After calculating the electricity demand in each zone using architectural area and basic units of hourly power consumption, we evaluate the effect to decrease the peak load by V2G （vehicle-to-grid）. According to the results, if EV drivers charge at home during the night and discharge at work during the day, the electricity demand in Nagoya city increases by approximately 1%, although changes in each individual zone range from -7% to ＋8%, depending on its characteristics.展开更多
Demand forecasting is often difficult due to the unobservability of the applicable historical demand series. In this study, the authors propose a demand forecasting method based on stochastic frontier analysis(SFA) mo...Demand forecasting is often difficult due to the unobservability of the applicable historical demand series. In this study, the authors propose a demand forecasting method based on stochastic frontier analysis(SFA) models and a model average technique. First, considering model uncertainty,a set of alternative SFA models with various combinations of explanatory variables and distribution assumptions are constructed to estimate demands. Second, an average estimate from the estimated demand values is obtained using a model average technique. Finally, future demand forecasts are achieved, with the average estimates used as historical observations. An empirical application of air travel demand forecasting is implemented. The results of a forecasting performance comparison show that in addition to its ability to estimate demand, the proposed method outperforms other common methods in terms of forecasting passenger traffic.展开更多
Traffic congestion has become a critical issue in developing countries,as it tends to increase social costs in terms of travel cost and time,energy consumption and environmental degradation.With limited resources,redu...Traffic congestion has become a critical issue in developing countries,as it tends to increase social costs in terms of travel cost and time,energy consumption and environmental degradation.With limited resources,reducing travel demand by influencing individuals’ travel behavior can be a better long-term solution.To achieve this objective,alternate travel options need to be provided so that people can commute comfortably and economically.This study aims to identify key motives and constraints in the consideration of carpooling policy with the help of stated preference questionnaire survey that was conducted in Lahore City.The designed questionnaire includes respondents’ socioeconomic demographics,and intentions and stated preferences on carpooling policy.Factor analysis was conducted on travelers’ responses,and a structural model was developed for carpooling.Survey and modeling results reveal that social,environmental and economic benefits,disincentives on car use,preferential parking treatment for carpooling,and comfort and convenience attributes are significant determinants in promoting carpooling.However,people with strong belief in personal privacy,security,freedom in traveling and carpooling service constraints would have less potential to use thecarpooling service.In addition,pro-auto and pro-carpooling attitudes,marital status,profession and travel purpose for carpooling are also underlying factors.The findings implicate that to promote carpooling policy it is required to consider appropriate incentives on this service and disincentives on use of private vehicle along with modification of people’s attitudes and intentions.展开更多
基金supported by the Surface Project of the National Natural Science Foundation of China(No.71273024)the Fundamental Research Funds for the Central Universities of China(2021YJS080).
文摘This study proposes a prediction model considering external weather and holiday factors to address the issue of accurately predicting urban taxi travel demand caused by complex data and numerous influencing factors.The model integrates the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN)and Convolutional Long Short Term Memory Neural Network(ConvLSTM)to predict short-term taxi travel demand.The CEEMDAN decomposition method effectively decomposes time series data into a set of modal components,capturing sequence characteristics at different time scales and frequencies.Based on the sample entropy value of components,secondary processing of more complex sequence components after decomposition is employed to reduce the cumulative prediction error of component sequences and improve prediction efficiency.On this basis,considering the correlation between the spatiotemporal trends of short-term taxi traffic,a ConvLSTM neural network model with Long Short Term Memory(LSTM)time series processing ability and Convolutional Neural Networks(CNN)spatial feature processing ability is constructed to predict the travel demand for urban taxis.The combined prediction model is tested on a taxi travel demand dataset in a certain area of Beijing.The results show that the CEEMDAN-ConvLSTM prediction model outperforms the LSTM,Autoregressive Integrated Moving Average model(ARIMA),CNN,and ConvLSTM benchmark models in terms of Symmetric Mean Absolute Percentage Error(SMAPE),Root Mean Square Error(RMSE),Mean Absolute Error(MAE),and R2 metrics.Notably,the SMAPE metric exhibits a remarkable decline of 21.03%with the utilization of our proposed model.These results confirm that our study provides a highly accurate and valid model for taxi travel demand forecasting.
文摘In view of the problem that the requirements of travel demand management and traffic policy-sensitivity are ignored during the establishment process of the travel demand forecasting model, a discrete-choice-based travel demand forecasting model is proposed to demonstrate its applicability to travel demand management. A car-bus discrete choice model is established, including three variables, i. e,, individual socioeconomic characteristics, time, and cost, and the traffic policy-sensitivity is evaluated through two kinds of traffic policies： parking charges and bus priorities. The empirical results show that travel choice is insensitive to the policy of parking charges as 88. 41% of the travelers are insensitive to parking charges; travel choice is, however, sensitive to the policy of bus priorities as 67.70% of the car travelers and 77.02% of the bus travelers are sensitive to bus priorities. The discrete-choice-based travel demand forecasting model is quite policy-sensitive and also has a good adaptability for travel demand management when meeting the basic functions of the demand forecasting model.
文摘In the last decades, there has been substantial development in modeling techniques of travel demand estimation. For low population areas the external trip estimation is important but usually neglected in travel demand modeling process. In Egypt, the researches in this field are scarce due to lack of data. Accordingly, this paper aims to identify and estimate the main variables that affect the travel demand in low population areas, and to develop models to predict them. The study focused on the Port Said Govemorate in North East Egypt. A special questionnaire had been prepared in 2010 depending on interviews of passengers at basic taxi terminals in Port Said. And 2211 filled questionnaires were offering for research. To analyze the data, two modeling procedures were used. One is the multiple linear regression and the other is the generalized linear modeling （GLM） applying normal distributions. It is found that GLM procedure offers more suitable and accurate approach than the linear regression for developing number of trips. The final demand models have statistics within the acceptable regions and, also, they are conceptually reasonable. These results are so important for Egyptian highway authorities to improve the efficiency of highway transportation system in Egypt.
文摘In this study, we examine the impacts that EVs （electric vehicles） have on vehicle usage patterns and environmental improvements, using our integrated travel demand forecasting model, which can simulate an individual activity-travel behavior in each time period, as well as consider an induced demand by decreasing travel cost. In order to examine the effects that charging/discharging have on the demand in electricity, we analyze scenarios based on the simulation results of the EVs＇ parking location, parking duration and the battery state of charge. From the simulation, result under the ownership rate of EVs in the Nagoya metropolitan area in 2020 is about 6%, which turns out that the total CO2 emissions have decreased by 4% although the situation of urban transport is not changed. After calculating the electricity demand in each zone using architectural area and basic units of hourly power consumption, we evaluate the effect to decrease the peak load by V2G （vehicle-to-grid）. According to the results, if EV drivers charge at home during the night and discharge at work during the day, the electricity demand in Nagoya city increases by approximately 1%, although changes in each individual zone range from -7% to ＋8%, depending on its characteristics.
基金supported by the National Natural Science Foundation of China under Grant Nos.71522004,11471324 and 71631008a Grant from the Ministry of Education of China under Grant No.17YJC910011
文摘Demand forecasting is often difficult due to the unobservability of the applicable historical demand series. In this study, the authors propose a demand forecasting method based on stochastic frontier analysis(SFA) models and a model average technique. First, considering model uncertainty,a set of alternative SFA models with various combinations of explanatory variables and distribution assumptions are constructed to estimate demands. Second, an average estimate from the estimated demand values is obtained using a model average technique. Finally, future demand forecasts are achieved, with the average estimates used as historical observations. An empirical application of air travel demand forecasting is implemented. The results of a forecasting performance comparison show that in addition to its ability to estimate demand, the proposed method outperforms other common methods in terms of forecasting passenger traffic.
基金conducted at University of Engineering and Technology Lahore with support of Department of Transportation Engineering and Management Department
文摘Traffic congestion has become a critical issue in developing countries,as it tends to increase social costs in terms of travel cost and time,energy consumption and environmental degradation.With limited resources,reducing travel demand by influencing individuals’ travel behavior can be a better long-term solution.To achieve this objective,alternate travel options need to be provided so that people can commute comfortably and economically.This study aims to identify key motives and constraints in the consideration of carpooling policy with the help of stated preference questionnaire survey that was conducted in Lahore City.The designed questionnaire includes respondents’ socioeconomic demographics,and intentions and stated preferences on carpooling policy.Factor analysis was conducted on travelers’ responses,and a structural model was developed for carpooling.Survey and modeling results reveal that social,environmental and economic benefits,disincentives on car use,preferential parking treatment for carpooling,and comfort and convenience attributes are significant determinants in promoting carpooling.However,people with strong belief in personal privacy,security,freedom in traveling and carpooling service constraints would have less potential to use thecarpooling service.In addition,pro-auto and pro-carpooling attitudes,marital status,profession and travel purpose for carpooling are also underlying factors.The findings implicate that to promote carpooling policy it is required to consider appropriate incentives on this service and disincentives on use of private vehicle along with modification of people’s attitudes and intentions.
