In this paper, we present a series of machine learning approaches for better understanding people’s travel mode choice. The widely used Logit model is dependent on the assumption that the utility items are independent, violating of this assumption caused inconsistent parameter estimations and biased predictions. To improve the prediction accuracy of mode choice, this paper employs the data fusion model based on stacking strategy and proposes a hybrid model of the unsupervised Denoising Autoencoder (DAE) combining with the supervised Random Forest (RF). A variety of features that may impact mode choice behavior are ranked and selected by using the feature selection algorithms. The proposed model, which is particularly useful and powerful in the choice behavior analysis and outperforms other widely used classifiers, is verified by travel diary data from Germany and Switzerland. The results can be used for better understanding and effectively modeling of human travel mode choice behavior.

The emergence and development of car sharing can not only satisfy people’s diverse travel demands, but also can bring a new solution to facilitate urban low-carbon and green development. With the increasing acceptance of car sharing, the market competition between car sharing and traditional taxis is becoming increasingly fierce. Therefore, we explore the advantages of car sharing to travelers compared with taxis. In this paper, we first use the GPS (Global Positioning System) trajectory data of car sharing orders to construct a comparative advantage model based on travel-cost. Then, we take Beijing as the research area to explore the travel-cost advantages of car sharing in terms of the time and space dimensions compared with taxis, through calculating the travel-cost of car sharing and using simulation to calculate that of taxis. The results of the comparison between car sharing and taxis from the perspective of travel-cost are as follows: (1) Compared with short trips, the travel-cost advantage of car sharing is relatively higher in medium and long trips; for travelers, the taxi has a higher travel-cost advantage when the travel time is either very long or very short. (2) On weekdays, it is more cost-effective to travel by shared cars for travelers before the rush hours in the evening, and the travel-cost advantage of using taxis is greater after the evening peak. (3) Compared with weekdays, it is more cost-effective to travel by shared cars on weekends wherever travelers are living in the main urban areas or in the remote suburbs. It is suggested that relevant departments should understand the travelers’ preference and analyze the influence mechanism of other various factors on the market demand for car sharing as per the focus on the market on the travel-cost advantages of car sharing, so as to promote the healthy and sustainable development of urban shared transportation.

With the rapid development of urbanization, the blind expansion of urban space has led to a series of social problems. In this process, the degree of urban function mixing affects the urbanization development level, making it particularly important to study the degree of coupling coordination between the two aspects. In this paper, taking Beijing as an example, we use urban point of interest (POI) data and taxi GPS trajectory data to calculate the urban POIs’ spatial entropy and taxis’ temporal entropy, based on the information entropy. We use the POIs’ spatial entropy and taxis’ temporal entropy to measure the urban function mixing degree. Also, the model of coupling coordination degree is used to measure the degree of coupling coordination between the urban function mixing degree and the urbanization development level. The results indicate the following: First, the POIs’ spatial entropy and taxis’ temporal entropy have significant regional imbalances. On the whole, both show a declining pattern when moving from the central urban area to the outer suburbs. The urban function mixing degree and urbanization development level are also higher in the central urban area than in the outer suburbs. Second, the coupling coordination among the urbanization development level, POIs’ spatial entropy, and taxis’ temporal entropy is distributed unevenly across various regions, which means that the three types of coupling coordination are in balanced development in the central urban area, but in unbalanced development in the outer suburbs. Third, from the perspective of spatial correlation characteristics, the higher is the degree of spatial agglomeration, the higher are the urban function mixing degree and urbanization development level, and the higher is the coupling coordination degree among the urbanization development level, POIs’ spatial entropy, and taxis’ temporal entropy. Therefore, relevant departments should plan the construction of urban functional areas reasonably, according to the degree of coupling coordination between the urban function mixing degree and the urbanization development level in different regions, so as to realize the healthy and sustainable development of a city.

Qualitative and quantitative user studies can reveal valuable insights into user behavior, which in turn can assist system designers in providing better user experiences. Car sharing (e.g., Zipcar and car2go), as an emerging App-based online shared mobility mode, has been increasing dramatically worldwide in recent years. However, to date, comprehensive user behavior in car sharing systems has not been investigated, which is essential for understanding their characteristics and promotion roadblocks. With the goal of understanding various facets of user behavior in online car sharing systems, in this paper, we performed a qualitative and quantitative user study by adopting a mixed-methods approach. We first designed an attitude-aware online survey with a set of qualitative questions to perceive people's subjective attitudes to online car sharing, where a total of 185 participants (68 females) completed the survey. Next, we quantitatively analyzed a one-year real-world car sharing operation dataset collected from the Chinese city Beijing, which involves over 68,000 unique users and over 587,850 usage records. We dissected this attitude-free dataset to understand the objective car sharing user behavior from different dimensions, e.g., spatial, temporal, and demographic. Furthermore, we conducted a comparative study by utilizing one-year data from other two representative Chinese city Fuzhou and Lanzhou to show if the obtained findings from Beijing data may be generalizable to other cities having different urban features, e.g., different city size, population density, wealth, and climate conditions. We also do a case study by designing a user behavior-aware usage prediction model (i.e., BeXGBoost) based on findings from our user study (e.g., unbalanced spatiotemporal usage patterns, weekly regularity, demographic-related usage difference, and low-frequency revisitation), which is the basis for car sharing service station deployment and vehicle rebalancing. Finally, we summarize a set of findings obtained from our study about the unique user behavior in online car sharing systems, combined with some detailed discussions about implications for design.

A station disruption is an abnormal operational situation that the entrance or exit gates of a metro station have to be closed for a certain of time due to an unexpected incident. The passengers’ travel behavioral responses to the alternative station disruption scenarios and the corresponding controlling strategies are complex and hard to capture. This can lead to the hardness of estimating the changes of the network-wide passenger demand, which is the basis of carrying out a response plan. This paper will establish a model to solve the metro station disruption problem by providing optimal additional bus-bridging services. Two main contributions are made: (1) a three-layer discrete choice behavior model is developed to analyze the dynamic passenger flow demand under station disruption; and (2) an integrated algorithm is designed to manage and control the station disruption crisis by providing additional bus-bridging services with the objective of minimizing the total travel time of affected passengers and the operating cost of bridging-buses. Besides, the multimodal transport modes, including metro, bridging-bus, shared-bike, and taxi, are considered as passengers’ alternative choices in face of the station disruption. A numerical study based on the Beijing metro network shows that additional bus-bridging services can significantly eliminate the negative impact of the station disruption.

The emergence and development of car-sharing has not only satisfied people’s diverse travel needs, but also brought new solutions for improving urban traffic conditions and achieving low-carbon and green sustainable development. In recent years, car-sharing has had competition with other ways of getting around, as the acceptance of car-sharing has grown, notably taxis. Therefore, it is particularly important to explore car-sharing travel costs advantages from the perspective of consumers and discover the competitive and complementary spaces between car-sharing and other modes. Therefore, taking Beijing as an example, this paper uses GPS trajectory data based on car-sharing orders to design a travel cost framework of car-sharing and taxis. We calculate and compare the travel cost difference between these two modes under different travel characteristics. The results indicate that car-sharing is a more economical way for consumers to travel for short or medium lengths of time, while people are more inclined to take taxis for distances of long duration. Compared with on workdays, at the weekend, the cost advantage of car-sharing is greater for long-distance trips. Moreover, the cost advantage of car-sharing increases gradually with the increase in travel distance. In addition, the travel costs of car-sharing and taxis are also affected by peak and off-peak traffic periods. Compared with off-peak periods, it is more cost-effective for travelers to take taxis during peak traffic periods for various travel distances. From the perspective of the travel cost, it is of great theoretical significance to discuss the substitution (market competition) and complementary relationship (market cooperation) between car-sharing and taxis in a detailed and systematic way. It provides methods and ideas for the comparative cost calculation of car-sharing and other travel modes. This paper also provides enlightenment and guidance for the development of car-sharing. Enterprises should implement differentiated pricing, designing different charging methods for different traffic periods, travel miles, and rental times, and set up additional stations in the surrounding areas of the city. Relevant government departments should also strictly manage the market access of car-sharing, and add or open car-sharing parking lots in centralized areas and for specific periods.