Predicting short-term bus passenger demand using a pattern hybrid approach

This paper proposes an Interactive Multiple Model-based Pattern Hybrid (IMMPH) approach to predict short-term passenger demand. The approach maximizes the effective information content by assembling the knowledge from pattern models using historical data and optimizing the interaction between them using real-time observations. It can dynamically estimate the priori pattern models combination in advance for the next time interval. The source demand data were collected by Smart Card system along one bus service route over one year. After correlation analysis, three temporal relevant pattern time series are generated, namely, the weekly, daily and hourly pattern time series. Then statistical pattern models are developed to capture different time series patterns. Finally, an amended IMM algorithm is applied to dynamically combine the pattern models estimations to output the final demand prediction. The proposed IMMPH model is validated by comparing with statistical methods and an artificial neural network based hybrid model. The results suggest that the IMMPH model provides a better forecast performance than its alternatives, including prediction accuracy, robustness, explanatory power and model complexity. The proposed approach can be potentially extended to other short-term time series forecast applications as well, such as traffic flow forecast.     

Coherent approach for modeling and nowcasting hourly near-road Black Carbon concentrations in Seattle,Washington

With a growing awareness of the importance of near-road air pollution and an increasing population of near-road pedestrians, it is imperative to “nowcast” near-road air quality conditions to the general public. This necessitates the building hourly predictive models that are both accurate and easy to use. This study demonstrates an approach to model the hourly near-road Black Carbon (BC) concentrations given on-road traffic information and current meteorological conditions using datasets from two urban sites in Seattle, Washington. The optimal set of prediction variables is determined with a Bayesian Model Averaging (BMA) method and three different model structures are further developed and compared by goodness-of-fit. An innovative approach is proposed to translate wind direction from numerical values to categorical variables with statistical significance. By modeling the autocorrelation within the BC time series using an AR(1) component, the model achieves a satisfactory prediction accuracy. The conditional heteroscedasticity and heavy-tailed distribution of the model residuals are successfully identified and modeled by the General Auto Regressive Conditional Heteroscedasticity (GARCH) model, which provides valuable insights to the interpretation of prediction results. The methodological procedure demonstrated in selecting and fine-tuning the model is computationally efficient and valuable for further implementation onto online platforms for near-road BC nowcasting. A comparison between the two sites also reveals the effectiveness of local freight regulation for mitigating the environmental impacts from a heavy truck fleet.     

Vehicle electrification in a developing country: Status and issue,from a well-to-wheel perspective

The increase of public attention, scientific research and political interest in environmental problems associated with transportation has provided the motivation for re-invention of electric vehicles. However the usage of grid-dependent EVs with a high-carbon electricity grid might produce more damage to the environment. This study aims to provide an environmental impact comparison of ICEVs, HEVs and EVs during their usage cycle, by modeling their energy consumption (electricity or fuel) and the supply chains of the supplied energy, (well-to-wheel) based on a life cycle assessment. The results show that running EVs with the existing mixed sources of electrical energy produce larger impacts on the environment 60% of the time; when compared to HEVs. When compared to ICEVs, EVs produce a larger environmental impact on 7 out of 15 environmental impact categories. Overall the environmental impacts of EVs are substantial based on the well-to-wheel analysis. It will continue to be so if no change is made to the methods of electricity generation in the near future. Given that the environmental profile of EVs is linked with the existing national electricity generation mix, the national electricity supply must be made cleaner before the electrification of the urban transport system.     

Estimation method for railway passengers’ train choice behavior with smart card transaction data

Smart card systems have become the predominant method of collecting public transport fares in Japan. Transaction data obtained through smart cards have resulted in a large amount of archived information on how passengers use public transportation. The data have the potential to be used for modeling passenger behavior and demand for public transportation. This study focused on train choices made by railway passengers. If each passenger’s train choice can be identified over a long period of time, this information would be useful for improving the customer relationship management of the railway company and for improving train timetables. The aim of this study was to develop a methodology for estimating which train is boarded by each smart card holder. This paper presents a methodology and an algorithm for estimation using long-term transaction data. To validate the computation time and accuracy of the estimation, an empirical analysis is carried out using actual transaction data provided by a railway company in Japan. The results show that the proposed method is capable of estimating passenger usage patterns from smart card transaction data collected over a long time period.     

Designing heterogeneous sensor networks for estimating and predicting path travel time dynamics: An information-theoretic modeling approach

With a particular emphasis on the end-to-end travel time prediction problem, this paper proposes an information-theoretic sensor location model that aims to minimize total travel time uncertainties from a set of point, point-to-point and probe sensors in a traffic network. Based on a Kalman filtering structure, the proposed measurement and uncertainty quantification models explicitly take into account several important sources of errors in the travel time estimation/prediction process, such as the uncertainty associated with prior travel time estimates, measurement errors and sampling errors. By considering only critical paths and limited time intervals, this paper selects a path travel time uncertainty criterion to construct a joint sensor location and travel time estimation/prediction framework with a unified modeling of both recurring and non-recurring traffic conditions. An analytical determinant maximization model and heuristic beam-search algorithm are used to find an effective lower bound and solve the combinatorial sensor selection problem. A number of illustrative examples and one case study are used to demonstrate the effectiveness of the proposed methodology.     

时间序列法预测沥青路面损坏状况指数研究

由于沥青路面损坏状况影响因素很多,因此要准确预测路面损坏状况较困难。文章采用时间序列法建立预测模型,结合同三高速公路（上海段）路面损坏状况的实测数据进行预测分析。分析结果表明时间序列法具有较高的预测精度和易修正性。     

Estimating a model of dynamic activity generation based on one-day observations: Method and results

In this paper we develop and explore an approach to estimate dynamic models of activity generation on one-day travel-diary data. Dynamic models predict multi-day activity patterns of individuals taking into account dynamic needs as well as day-varying preferences and time-budgets. We formulate an ordered-logit model of dynamic activity-agenda-formation decisions and show how one-day observation probabilities can be derived from the model as a function of the model’s parameters and, with that, how parameters can be estimated using standard loglikelihood estimation. A scale parameter cannot be identified because information on within-person variability is lacking in one-day data. An application of the method to data from a national travel survey illustrates the method. A test on simulated data indicates that, given a pre-set scale, the parameters can be identified and that estimates are robust for a source of heterogeneity not captured in the model. This result indicates that dynamic activity-based models of the kind considered here can be estimated from data that are less costly to collect and that support the large sample sizes typically required for travel-demand modeling. We conclude therefore that the proposed approach opens up a way to develop large-scale dynamic activity-based models of travel demand.     

Vehicular emissions prediction with CART-BMARS hybrid models

Vehicular emission models play a key role in the development of reliable air quality modeling systems. To minimize uncertainties associated with these models, it is essential to match the high-resolution requirements of emission models with up-to-date information. However, these models are usually based on average trip speed, not on environmental parameters like ambient temperature, and vehicle’s motion characteristics, such as speed, acceleration, load and power. This contributes to the degradation of its predictive performance. In this paper, we propose to use the non-parametric Classification and Regression Trees (CART), the Boosting Multivariate Adaptive Regression Splines (BMARS) algorithm and a combination of them in hybrid models to improve the accuracy of vehicular emission prediction using on-board measurements and the chassis dynamometer testing. The experimental comparison between the proposed CART-BMARS hybrid model with the BMARS and artificial neural networks (ANNs) algorithms demonstrates its effectiveness and efficiency in estimating vehicular emissions.     

Long distance truck tracking from advanced point detectors using a selective weighted Bayesian model

Truck flow patterns are known to vary by season and time-of-day, and to have important implications for freight modeling, highway infrastructure design and operation, and energy and environmental impacts. However, such variations cannot be captured by current truck data sources such as surveys or point detectors. To facilitate development of detailed truck flow pattern data, this paper describes a new truck tracking algorithm that was developed to estimate path flows of trucks by adopting a linear data fusion method utilizing weigh-in-motion (WIM) and inductive loop point detectors. A Selective Weighted Bayesian Model (SWBM) was developed to match individual vehicles between two detector locations using truck physical attributes and inductive waveform signatures. Key feature variables were identified and weighted via Bayesian modeling to improve vehicle matching performance. Data for model development were collected from two WIM sites spanning 26 miles in California where only 11 percent of trucks observed at the downstream site traversed the whole corridor. The tracking model showed 81 percent of correct matching rate to the trucks declared as through trucks from the algorithm. This high accuracy showed that the tracking model is capable of not only correctly matching through vehicles but also successfully filtering out non-through vehicles on this relatively long distance corridor. In addition, the results showed that a Bayesian approach with full integration of two complementary detector data types could successfully track trucks over long distances by minimizing the impacts of measurement variations or errors from the detection systems employed in the tracking process. In a separate case study, the algorithm was implemented over an even longer 65-mile freeway section and demonstrated that the proposed algorithm is capable of providing valuable insights into truck travel patterns and industrial affiliation to yield a comprehensive truck activity data source.     

Capturing the conditions that introduce systematic variation in bike-sharing travel behavior using data mining techniques

The potential of smart-card transactions within bike-sharing systems (BSS) is still to be explored. This research proposes an original offline data mining procedure that takes advantage of the quality of these data to analyze the bike usage casuistry within a sharing scheme. A difference is made between usage and travel behavior: the usage is described by the actual trip-chaining gathered with every smart-card transaction and is directly influenced by the limitations of the BSS as a public renting service, while the travel behavior relates to the spatio-temporal distribution, the travel time and trip purpose. The proposed approach is based on the hypothesis that there are systematic usage types which can be described through a set of conditions that permit to classify the rentals and reduce the heterogeneity in travel patterns. Hence, the proposed algorithm is a powerful tool to characterize the actual demand for bike-sharing systems. Furthermore, the results show that its potential goes well beyond that since service deficiencies rapidly arise and their impacts can be measured in terms of demand. Consequently, this research contributes to the state of knowledge on cycling behavior within public systems and it is also a key instrument beneficial to both decision makers and operators assisting the demand analysis, the service redesign and its optimization.     

Life cycle assessment of heated apron pavement system operations

Heated pavement systems (HPS) offer an attractive alternative to the cumbersome process of removing ice and snow from airport pavements using traditional snow removal systems. Although snow and ice removing efficiency and economic benefits of HPS have been assessed by previous studies, their environmental impact is not well known. Airport facilities offering public or private services need to evaluate the energy consumption and global warming potential of different types of snow and ice removal systems. Energy usage and emissions from the operations of hydronic heated pavement system using geothermal energy (HHPS-G), hydronic HPS using natural gas furnace (HHPS-NG), electrically heated pavement system (EHPS), and traditional snow and ice removal system (TSRS) are estimated and compared in this study using a hybrid life cycle assessment (LCA). Based on the system models assessed in this study, HPS application in the apron area seems to be a viable option from an energy or environmental perspective to achieve ice/snow free pavement surfaces without using mechanical or chemical methods. TSRS methods typically require more energy and they produce more greenhouse gas (GHG) emissions compared to HPS during the operation phase, under the conditions and assumptions considered in this study. Also, HPS operations require less energy and have less GHG emissions during a snow event with a smaller snowfall rate and a larger snow duration.     

Life cycle assessment of High Speed Rail in China

China has built the world’s largest High Speed Rail (HSR) network. Its environmental impacts have been examined by the means of life cycle assessment (LCA) which describes the whole picture of the HSR system instead of single stages, with a case study for the high-speed railway that links Beijing and Shanghai. The research employs the China-specific life cycle inventory database Chinese Core Life Cycle Database (CLCD). Vehicle operation dominates most impact categories, while vehicle manufacturing/maintenance/disposal and infrastructure construction contribute mostly to mineral consumption (43% and 38%) and organic compounds in water (54% for infrastructure construction). Several scenarios are developed to explore effects of changes in HSR development, utilization, electricity mix, and infrastructure planning and construction. Suggestions are provided for improving the life cycle environmental performance of China’s HSR systems.     

Understanding time use: Daily or weekly data?

The appropriate duration of time diaries as a source of time use data is analyzed in a structured way. Nine detailed European surveys based on seven-days diaries are used in order to study different dimensions of data quality, duration and variability of activities, and modeling capabilities. Pseudo diaries of 1, 2 (one week, one weekend) and 3 (one week, both weekend) days are constructed to further analyze these issues, selecting the seven-days diaries data as a benchmark. Comparative results show that two and three-days weighted surveys seem to be an adequate surrogate for the information obtained in weekly surveys that capture a basic work–leisure cycle.     

Adaptive traffic parameter prediction: Effect of number of states and transferability of models

Traffic parameters can show shifts due to factors such as weather, accidents, and driving characteristics. This study develops a model for predicting traffic speeds under these abrupt changes within regime switching framework. The proposed approach utilizes Hidden Markov, Expectation Maximization, Recursive Least Squares Filtering, and ARIMA methods for an adaptive forecasting method. The method is compared with naive and mean updating linear and nonlinear time series models. The model is fitted and tested extensively using 1993 I-880 loop data from California and January 2014 INRIX data from Virginia. Analysis for number of states, impact of number of states on forecasting, prediction scope, and transferability of the model to different locations are investigated. A 5-state model is found to be providing best results. Developed model is tested for 1-step to 45-step forecasts. The accuracy of predictions are improved until 15-step over nonadaptive and mean adaptive models. Except 1-step predictions, the model is found to be transferable to different locations. Even if the developed model is not retrained on different datasets, it is able to provide better or close results with nonadaptive and adaptive models that are retrained on the corresponding dataset.     

Latent stage model for carsharing usage frequency estimation with Montréal case study

In order to predict the monthly usage frequency of members of a car-sharing scheme by analysing the gradual change of behaviour over time, a new model is proposed based on the Markov Chains model with latent stages. The model accounts for changing patterns of frequency from soon after signing up to later stages by including five latent user ‘life stages’. In applying the model to panel data from Montreal’s free-floating carsharing service the authors calculate each user’s ’lifetime’ applied to ‘system operation time’, the time period since the start of the scheme. Three-fold validation reveals effective performance of the model for both lifetime and system operation time dimensions. The model is further applied to illustrate how previous carsharing experience and the extension of the scheme to a larger area can affect usage frequency changes. We conclude that this approach is effective for usage prediction for novel transport schemes.

     

Dynamic travel time prediction using data clustering and genetic programming

The current state-of-practice for predicting travel times assumes that the speeds along the various roadway segments remain constant over the duration of the trip. This approach produces large prediction errors, especially when the segment speeds vary temporally. In this paper, we develop a data clustering and genetic programming approach for modeling and predicting the expected, lower, and upper bounds of dynamic travel times along freeways. The models obtained from the genetic programming approach are algebraic expressions that provide insights into the spatiotemporal interactions. The use of an algebraic equation also means that the approach is computationally efficient and suitable for real-time applications. Our algorithm is tested on a 37-mile freeway section encompassing several bottlenecks. The prediction error is demonstrated to be significantly lower than that produced by the instantaneous algorithm and the historical average averaged over seven weekdays (p-value <0.0001). Specifically, the proposed algorithm achieves more than a 25% and 76% reduction in the prediction error over the instantaneous and historical average, respectively on congested days. When bagging is used in addition to the genetic programming, the results show that the mean width of the travel time interval is less than 5 min for the 60–80 min trip.     

Origin-destination pattern estimation based on trajectory reconstruction using automatic license plate recognition data

Origin-destination (OD) pattern estimation is a vital step for traffic simulation applications and active urban traffic management. Many methods have been proposed to estimate OD patterns based on different data sources, such as GPS data and automatic license plate recognition (ALPR) data. These data can be used to identify vehicle IDs and estimate their trajectories by matching vehicles identified by different sensors across the network. OD pattern estimation using ALPR data remains a challenge in real-life applications due to the difficulty in reconstructing vehicle trajectories. This paper proposes an offline method for historical OD pattern estimation based on ALPR data. A particle filter is used to estimate the probability of a vehicle’s trajectory from all possible candidate trajectories. The initial particles are generated by searching potential paths in a pre-determined area based on the time geography theory. Then, the path flow estimation process is conducted through dividing the reconstructed complete trajectories of all detected vehicles into multiple trips. Finally, the OD patterns are estimated by adding up the path flows with the same ODs. The proposed method was implemented on a real-world traffic network in Kunshan, China and verified through a calibrated microscopic traffic simulation model. The results show that the MAPEs of the OD estimation are lower than 19%. Further investigation shows that there exists a minimum required ALPR sampling rate (60% in the test network) for accurately estimating the OD patterns. The findings of this study demonstrate the effectiveness of the proposed method in OD pattern estimation.     

Forward power-train energy management modeling for assessing benefits of integrating predictive traffic data into plug-in-hybrid electric vehicles

In this paper, a forward power-train plug-in hybrid electric vehicle model with an energy management system and a cycle optimization algorithm is evaluated for energy efficiency. Using wirelessly communicated predictive traffic data for vehicles in a roadway network, as envisioned in intelligent transportation systems, traffic prediction cycles are optimized using a cycle optimization strategy. This resulted in a 56-86% fuel efficiency improvements for conventional vehicles. When combined with the plug-in hybrid electric vehicle power management system, about 115% energy efficiency improvements were achieved. Further improvements in the overall energy efficiency of the network were achieved with increased penetration rates of the intelligent transportation assisted enabled plug-in hybrid electric vehicles.     

An empirical analysis of children’s after school out-of-home activity-location engagement patterns and time allocation

Children are an often overlooked and understudied population group, whose travel needs are responsible for a significant number of trips made by a household. In addition, children’s travel and activity participation during the post-school period have direct implication for adults’ activity-travel patterns. A better understanding of children’s after school activity-travel patterns and the linkages between parents and children’s activity-travel needs is necessary for accurate prediction and forecasting of activity-based travel demand modeling systems. In this paper, data from the 2002 Child Development Supplement of the Panel Study of Income Dynamics is used to undertake a comprehensive assessment of the post-school out-of-home activity-location engagement patterns of children aged 5–17 years. Specifically, this research effort utilizes a multinomial logit model to analyze children’s post-school location patterns, and employs a multiple discrete–continuous extreme value model to study the propensity of children to participate in, and allocate time to, multiple activity episode purpose-location types during the after-school period. The results show that a wide variety of demographic, attitudinal, environmental, and others’ activity-travel pattern characteristics impact children’s after school activity engagement patterns.     

Stochastic frontier estimation of budgets for Kuhn–Tucker demand systems: Application to activity time-use analysis

We propose a stochastic frontier approach to estimate budgets for the multiple discrete–continuous extreme value (MDCEV) model. The approach is useful when the underlying time and/or money budgets driving a choice situation are unobserved, but the expenditures on the choice alternatives of interest are observed. Several MDCEV applications hitherto used the observed total expenditure on the choice alternatives as the budget to model expenditure allocation among choice alternatives. This does not allow for increases or decreases in the total expenditure due to changes in choice alternative-specific attributes, but only allows a reallocation of the observed total expenditure among different alternatives. The stochastic frontier approach helps address this issue by invoking the notion that consumers operate under latent budgets that can be conceived (and modeled) as the maximum possible expenditure they are willing to incur. The proposed method is applied to analyze the daily out-of-home activity participation and time-use patterns in a survey sample of non-working adults in Florida. First, a stochastic frontier regression is performed on the observed out-of-home activity time expenditure (OH-ATE) to estimate the unobserved out-of-home activity time frontier (OH-ATF). The estimated frontier is interpreted as a subjective limit or maximum possible time individuals can allocate to out-of-home activities and used as the time budget governing out-of-home time-use choices in an MDCEV model. The efficacy of this approach is compared with other approaches for estimating time budgets for the MDCEV model, including: (a) a log-linear regression on the total observed expenditure for out-of-home activities and (b) arbitrarily assumed, constant time budgets for all individuals in the sample. A comparison of predictive accuracy in time-use patterns suggests that the stochastic frontier and log-linear regression approaches perform better than arbitrary assumptions on time budgets. Between the stochastic frontier and log-linear regression approaches, the former results in slightly better predictions of activity participation rates while the latter results in slightly better predictions of activity durations. A comparison of policy simulations demonstrates that the stochastic frontier approach allows for the total out-of-home activity time expenditure to either expand or shrink due to changes in alternative-specific attributes. The log-linear regression approach allows for changes in total time expenditure due to changes in decision-maker attributes, but not due to changes in alternative-specific attributes.