The analysis of travel mode choice is important in transportation planning and policy-making in order to understand and forecast travel demands Research in the field of machine learning has been exploring the use of random forest as a framework within which many traffic and transport problems can be investigated The random forest (RF) is a powerful method for constructing an ensemble of random decision trees It de-correlates the decision trees in the ensemble via randomization that leads to an improvement of forecasting and reduces the variance when averaged over the trees However, the usefulness of RF for travel mode choice behavior remains largely unexplored This paper proposes a robust random forest method to analyze travel mode choices for examining the prediction capability and model interpretability Using the travel diary data from Nanjing, China in 2013, enriched with variables on the built environment, the effects of different model parameters on the prediction performance are investigated The comparison results show that the random forest method performs significantly better in travel mode choice prediction for higher accuracy and less computation cost In addition, the proposed method estimates the relative importance of explanatory variables and how they relate to mode choices This is fundamental for a better understanding and effective modeling of people’s travel behavior

Applying a random forest method approach to model travel mode choice behavior

This paper investigates how recurrent parking demand can be managed by dynamic parking pricing and information provision in the morning commute. Travelers are aware of time-varying pricing information and time-varying expected occupancy, through either their day-to-day experience or online information provision, to make their recurrent parking choices. We first formulate the parking choices under the User Equilibrium (UE) conditions using the Variational Inequality (VI) approach. More importantly, the System Optimal (SO) parking flow pattern and SO parking prices are also derived and solved efficiently using Linear Programming. Under SO, any two parking clusters cannot be used at the same time by travelers between more than one Origin–Destination (O–D) pairs. The SO parking flow pattern is not unique, which offers sufficient flexibility for operators to achieve different management objectives while keeping the flow pattern optimal. We show that any optimal flow pattern can be achieved by charging parking prices in each area that only depend on the time or occupancy, regardless of origins and destinations of users of this area. In the two numerical experiments, the best system performance is usually achieved by pricing the more preferred (convenient) area such that it is used up to a terminal occupancy of around 85–95%. Optimal pricing essentially balances the parking congestion (namely cruising time) and the level of convenience.

Optimal dynamic parking pricing for morning commute considering expected cruising time

Cruising-for-parking is a critical mobility issue in urban cities. The cost and accessibility of parking significantly influence people’s travel behavior (such as mode choice) and facility choice (on-street or garage parking). Furthermore, parking affects traffic performance for all users of a city. Car-users may have to cruise for on-street parking space before reaching destinations and cause delays eventually to everyone, even users with destinations outside limited parking areas. It is therefore crucial to understand the impact of parking on mobility and identify traffic management policies to avoid the negative externalities. Most existing studies of parking either fall short in reproducing the dynamic spatiotemporal features of traffic congestion in general and the cruising-for-parking phenomenon, or require data that are expensive and difficult to collect. In this paper, the authors propose an aggregated dynamic model for multimodal mobility with the consideration of parking, and utilize the model to evaluate management policies, such as parking pricing. The proposed approach is based on the recent development of the low-scattered Macroscopic Fundamental Diagram (MFD), which demonstrated decent representation of the complex dynamics of transport system at network-level for single-mode and bi-modal (car and bus) urban networks. The MFD-based bi-modal modeling framework is extended with a parking module where cruising delay and change of behavior (e.g. mode choice and parking facility choice) caused by parking are taken into account. Pricing strategies of parking are then developed to reduce congestion and travel cost. Result of a case study shows that traffic performance under various types of parking policies can be investigated and close-to-optimum pricing schemes can be obtained. Furthermore, parking market competition can be simulated and studied with the proposed modeling approach.

Modeling and optimization of multimodal urban network with limitedparking and dynamic pricing

Cruising-for-parking constraints mobility in urban networks. Car-users may have to cruise for on-street parking before reaching their destinations. The accessibility and the cost of parking significantly influence people's travel behavior (such as mode choice, or parking facility choice between on-street and garage). The cruising flow causes delays eventually to everyone, even users with destinations outside limited parking areas. It is therefore important to understand the impact of parking limitation on mobility, and to identify efficient parking policies for travel cost reduction. Most existing studies on parking fall short in reproducing the dynamic spatiotemporal features of traffic congestion in general, lack the treatment of dynamics of the cruising-for-parking phenomenon, or require detailed input data that are typically costly and difficult to collect. In this paper, we propose an aggregated and dynamic approach for modeling multimodal traffic with the treatment on parking, and utilize the approach to design dynamic parking pricing strategies. The proposed approach is based on the Macroscopic Fundamental Diagram (MFD), which can capture congestion dynamics at network-level for single-mode and bi-modal (car and bus) systems. A parsimonious parking model is integrated into the MFD-based multimodal modeling framework, where the dynamics of vehicular and passenger flows are considered with a change in the aggregated behavior (e.g. mode choice and parking facility choice) caused by cruising and congestion. Pricing strategies are developed with the objective of reducing congestion, as well as lowering the total travel cost of all users. A case study is carried out for a bi-modal city network with a congested downtown region. An elegant feedback dynamic parking pricing strategy can effectively reduce travel delay of cruising and the generic congestion. Remarkably, such strategy, which is applicable in real-time management with limited available data, is fairly as efficient as a dynamic pricing scheme obtained from system optimum conditions and a global optimization with full information about the future states of the system. Stackelberg equilibrium is also investigated in a competitive behavior between different parking facility operators. Policy indications on on-street storage capacity management and pricing are provided.

/pdf/modeling-and-optimization-of-multimodal-urban-networks-with-254ajkyt5p.pdf

Modeling and optimization of multimodal urban networks with limited parking and dynamic pricing

Free-floating car-sharing schemes operate without fixed car-sharing stations, ahead reservations or return-trip requirements. Providing fast and convenient motorization, they attract both public transport users and (former) car-owners. Thus, their impact on individual travel behavior depends on the user type. Estimating the travel behavior impact of these systems therefore requires quantitative data. Using a two-wave survey approach (shortly after launch of the scheme plus one year later) including travel diaries, this research indicates that (due to their membership) 6% of the free-floating car-sharing customers reduce their private vehicle ownership. Moreover, the results suggest that free-floating car-sharing both complements and competes with station-based car-sharing.

/pdf/measuring-the-car-ownership-impact-of-free-floating-car-29jxi0ys7v.pdf

Measuring the car ownership impact of free-floating car-sharing: A case study in Basel, Switzerland

This paper provides further insight into the usefulness of smartphones and dedicated GPS devices for collecting current travel survey data. GPS and accelerometer time series for 33 European research project PEACOX study participants are available for analysis; these were tracked simultaneously with smartphones and dedicated devices for 8 weeks. Meaningful diaries can be extracted from both data sources. However, if high resolution data is needed, results suggest that dedicated GPS devices are still relevant; they have no battery issues, meaning that more data is recorded and that data quality is more stable.

Comparison of Travel Diaries Generated from Smartphone Data and Dedicated GPS Devices

Travel surveys are increasingly taking advantage of GPS data, which offer precise route and time observations and a potentially reduced response burden. In these surveys, travel diaries are usually constructed automatically where research on the employed procedures has been focused on mode identification. The goal of the research reported here was to improve trip purpose identification. The analysis used random forests, a machine-learning approach that had been successfully applied to mode identification. The analysis was based on GPS tracks and accelerometer data collected by 156 participants who took part in a 1-week travel survey in Switzerland that was completed in 2012. The results show that random forests provide robust trip purpose classification. For ensemble runs, the share of correct predictions was between 80% and 85%. Different setups of the classifier were possible and sometimes required by the application context. The training set and its input variables (feature set) of the classifier were ...

Trip Purpose Identification from GPS Tracks

This paper reports on the development of an agent-based cruising-for-parking simulation using the cellular automaton (CA) approach. The software was tested on a small-scale scenario, and a first verification step was performed for a real-world scenario for the town center of Zurich. Approaches to integrating the simulation into MATSim, a multi-agent transport simulation program, are discussed. The software is open source and can be downloaded from a free software repository. Empirical data that may be valuable for future model calibration are currently being surveyed in a global positioning system (GPS) study at the authors’ institute.

/pdf/an-agent-based-cellular-automaton-cruising-for-parking-3ivstghyvj.pdf

An agent-based cellular automaton cruising-for-parking simulation

GPS data has become almost ubiquitous and data collection and processing technologies have advanced considerably. In transportation research, GPS traces are used, along with other data sources, to construct travel diaries, as they promise higher accuracy of collected data, combined with fewer fatigue effects. In this research, we present such a study, where a sample from Zurich, Switzerland, used GPS devices to monitor their daily trips for a week. A follow-up survey provided complementary information, including sociodemographic characteristics of the participants, as well as a large number of attitudinal parameters. Route choice models were estimated using this data set for car and public transport trips, along with a joint route and mode choice model, which also considered bike and walk stages. To the best of our knowledge, this is the first time that GPS data have been used for the estimation of mode and route choice models. The model fit is reasonable for all models and in line with those obtained with traditional data-collection methods. The coefficient estimates have the appropriate signs and meaningful magnitudes. A number of transformations were performed on some of the variables, improving the model fit significantly, and reducing the number of variables. We discuss some of the difficulties associated with such data collection efforts, and point out the advantages that can come from follow-up studies, based on similar concepts.

Route and mode choice models using GPS data

Parking search is widely accepted to be a significant contributor to congestion in city centers. The high parking occupation on Saturdays in Zurich suggest this also an issue there. Raw personbased GPS data from Switzerland and especially Zurich is analysed regarding parking search characteristics. For processing the POSDAP routines developed at the institute are extended. The descriptive analysis considers driving times and distances but also subsequent walk stages. Results suggest that search tra c is a local phenomenon and not as dramatic for the overall city as expected.

Lara Montini

Papers

Comparison of Travel Diaries Generated from Smartphone Data and Dedicated GPS Devices

Trip Purpose Identification from GPS Tracks

An agent-based cellular automaton cruising-for-parking simulation

Route and mode choice models using GPS data

Searching for Parking in GPS Data