•Literature on transport mode detection with mobile phone network data was reviewed.•A systematic review method was applied to minimize bias and ensure reproducibility.•It shows that simple ...rule-based methods making use of geodata were often employed.•Research gaps exist on data cleaning, fine-grained detection/evaluation and biases.
The rapid development in telecommunication networks is producing a huge amount of information regarding how people (with their mobile devices) move and behave over space and time. While GPS data, typically collected by smartphone apps, are restricted to rather small samples of the population, mobile phone network data, routinely collected by mobile network operators, potentially allow to analyze travel behaviors and social interaction of the whole population, with full temporal (e.g., longitudinal) coverage at a comparatively low cost. Therefore, recent years have seen an increasing interest in using such data for human mobility studies. However, due to their noisy and temporally infrequent/irregular nature, extracting mobility information such as transport modes from these data is particularly challenging. This paper provides an in-depth, systematic review of transport mode detection based on mobile phone network data. The results of the review show that existing studies tend to identify easy-to-detect modes (e.g., train or metro), or aggregate fine-grained modes into more general groups (e.g., public versus private transport). Rule-based methods making use of geographic data were often developed. More importantly, due to the lack of ground truth data, evaluation of the proposed methods was seldom done and reported. Finally, we identify a list of research gaps currently being faced in this field, particularly regarding robust and real-time data cleaning and mode detection methods, “benchmark” datasets and metrics allowing the comparison of different mode detection methods, as well as privacy and bias issues.
As a result of the coronavirus pandemic, in spring 2020 numerous protective measures were taken in Germany and all over the world. This has changed our everyday life and our mobility considerably. It ...is in question whether and how the pandemic and the lockdown have impacted transport mode use, attitudes towards transport modes and the ownership of individual mobility options during the lockdown period. In order to shed light on these essential aspects of transport policy, we carried out a representative travel survey in Germany during the strictest period of lockdown in the beginning of April. We have analysed overall and individual changes in transport mode usage and attitudes towards transport modes, focussing on the bicycle, the car and public transport. Also, the changes in the perception of individual mobility options with a focus on car-free households were investigated. Our results indicate that public transport lost ground during the particularly restricted period of lockdown while individual modes of transport, especially the private car, became more important. Our findings are highly relevant for transport policy when developing measures for expanding the possibilities for sustainable individual transport and developing concepts that strengthen public transport. These aspects are key for achieving a sustainable transport system in the medium- and long-term despite the coronavirus pandemic.
•We conducted a representative travel survey during the particularly restricted period of lockdown in Germany.•Fewer people had the public transport and the bicycle in their choice set; the share of car users remained stable.•Respondents felt less comfortable using public transport during the lockdown while the car showed a “feel-good” factor.•One third of the members of car-free households miss having a car in the corona pandemic.
Cars are a commuting lifeline worldwide, despite contributing significantly to air pollution. This is the first global assessment on air pollution exposure in cars across ten cities: Dhaka ...(Bangladesh); Chennai (India); Guangzhou (China); Medellín (Colombia); São Paulo (Brazil); Cairo (Egypt); Sulaymaniyah (Iraq); Addis Ababa (Ethiopia); Blantyre (Malawi); and Dar-es-Salaam (Tanzania). Portable laser particle counters were used to develop a proxy of car-user exposure profiles and analyse the factors affecting particulate matter ≤2.5 μm (PM2.5; fine fraction) and ≤10 μm (PM2.5–10; coarse fraction). Measurements were carried out during morning, off- and evening-peak hours under windows-open and windows-closed (fan-on and recirculation) conditions on predefined routes. For all cities, PM2.5 and PM10 concentrations were highest during windows-open, followed by fan-on and recirculation. Compared with recirculation, PM2.5 and PM10 were higher by up to 589% (Blantyre) and 1020% (São Paulo), during windows-open and higher by up to 385% (São Paulo) and 390% (São Paulo) during fan-on, respectively. Coarse particles dominated the PM fraction during windows-open while fine particles dominated during fan-on and recirculation, indicating filter effectiveness in removing coarse particles and a need for filters that limit the ingress of fine particles. Spatial variation analysis during windows-open showed that pollution hotspots make up to a third of the total route-length. PM2.5 exposure for windows-open during off-peak hours was 91% and 40% less than morning and evening peak hours, respectively. Across cities, determinants of relatively high personal exposure doses included lower car speeds, temporally longer journeys, and higher in-car concentrations. It was also concluded that car-users in the least affluent cities experienced disproportionately higher in-car PM2.5 exposures. Cities were classified into three groups according to low, intermediate and high levels of PM exposure to car commuters, allowing to draw similarities and highlight best practices.
Display omitted
•Particulate matter (PM) exposure in cars was measured across ten global cities.•Windows-open scenarios resulted in the highest PM10 and PM2.5 concentrations.•PM exposure was significantly higher during morning-peak hours in most cities.•Recirculation showed up to 80% less in-car PM2.5 compared to windows-open.•Off-peak trips showed up to 73% less PM2.5 exposure compared to morning-peak hours.
•A CNN architecture is proposed to infer transportation modes from GPS trajectories.•An adaptable and efficient layout for the input layer of the CNN is designed.•Key factors in the CNN: remove ...anomalies, data augmentation, use the bagging concept.•The proposed CNN achieves the accuracy of 84.8%, higher than other studies.
Identifying the distribution of users’ transportation modes is an essential part of travel demand analysis and transportation planning. With the advent of ubiquitous GPS-enabled devices (e.g., a smartphone), a cost-effective approach for inferring commuters’ mobility mode(s) is to leverage their GPS trajectories. A majority of studies have proposed mode inference models based on hand-crafted features and traditional machine learning algorithms. However, manual features engender some major drawbacks including vulnerability to traffic and environmental conditions as well as possessing human’s bias in creating efficient features. One way to overcome these issues is by utilizing Convolutional Neural Network (CNN) schemes that are capable of automatically driving high-level features from the raw input. Accordingly, in this paper, we take advantage of CNN architectures so as to predict travel modes based on only raw GPS trajectories, where the modes are labeled as walk, bike, bus, driving, and train. Our key contribution is designing the layout of the CNN’s input layer in such a way that not only is adaptable with the CNN schemes but represents fundamental motion characteristics of a moving object including speed, acceleration, jerk, and bearing rate. Furthermore, we ameliorate the quality of GPS logs through several data preprocessing steps. Using the clean input layer, a variety of CNN configurations are evaluated to achieve the best CNN architecture. The highest accuracy of 84.8% has been achieved through the ensemble of the best CNN configuration. In this research, we contrast our methodology with traditional machine learning algorithms as well as the seminal and most related studies to demonstrate the superiority of our framework.
Purpose
Transport is the European Union (EU) sector that produces the second highest amount of greenhouse gas emissions. In its attempts to promote the environmentally sustainable development of ...transport, the EU has focussed on intermodal transport in particular – but with limited success. It is important to understand how freight transport is selected, which criteria are used and what role environmental sustainability and intermodal transport play in the selection. Therefore, the purpose of this paper is to focus on the role of environmental sustainability and intermodal transport in transport mode decisions. The authors look at this issue from the perspective of logistics service providers (LSPs) and buyers, as they are important stakeholders in guiding this process.
Design/methodology/approach
To gain a holistic view of the current state of research, the authors have conducted a systematic literature review of the role of environmental sustainability and intermodal transport in transport mode decisions. The authors have further examined the findings concerning requests for quotations (RfQs), tenders and transport contracts, as these are also linked to decisions on transport choice.
Findings
The findings from the literature review include the results of descriptive and structured content analysis of the selected articles. They show that the discussion on environmental sustainability and intermodal transport as a sustainable mode, together with the transport mode selection criteria, RfQs/tenders and transport contracts, is still a rather new and emerging topic in the literature. The main focus related to the selection of transport mode has been on utility and cost efficiency, and only recently have issues such as environmental sustainability and intermodal transport started to gain greater attention. The findings also indicate that the theoretical lenses most typically used have been preference models and total cost theories, although the theoretical base has recently become more diversified.
Research limitations/implications
There is still a need to extend the theoretical and methodological base, which could then lead to innovative theory building and testing. Such diverse application of methodologies will help in understanding how environmental sustainability can be better linked to mode choice decisions.
Practical implications
The findings will be of interest to policy makers and companies opting for environmentally sustainable transport solutions.
Social implications
If the EU, shippers and LSPs take a more active stance in promoting environmentally sustainable transformation models, this will have long-lasting societal impacts.
Originality/value
It seems that this systematic literature review of the topic is one of the first such attempts in the current body of literature.
The present study tested an extended theory of planned behaviour (TPB) model within the domain of transport mode choice and identified the most important factors impacting on whether participants ...drove or used public transport to commute to work. Structural equation modelling of data from 827 participants showed that car use was determined by intention and habit but not perceived behavioural control (PBC), whereas public transport use was influenced solely by intention. The analysis also revealed that TPB variables (attitude, subjective norm and PBC) influenced use of both transport modes indirectly through their effects on intention and habit. In contrast, the incremental validity of variables not contained in the model (moral norm, descriptive norm and environmental concern) was mixed and varied according to transport mode. Theoretical and applied implications of the findings are discussed.
•A large well stratified sample was achieved from the UK.•An extended TPB model in which there are two paths to behaviour; one through intention and the other through habit.•Habit is an alternate path leading to transport use behaviours.•Environmental concern does not predict intention to use a particular transport mode. It does predict habit for car use.•PBC is more important in predicting public rather than private transport use.
Exposure concentration and inhaled dose of particles during door-to-door trips walking and using motorized transport modes (subway, bus, taxi) are evaluated along a selected route in a commercial ...district of Singapore. Concentrations of particles smaller than 2.5 μm in size (PM2.5), black carbon, particle-bound polycyclic aromatic hydrocarbons, number of particles, active surface area and carbon monoxide have been measured in-situ using portable instruments. Simultaneous measurements were conducted at a nearby park to capture the background concentrations. The heart rate of the participants was monitored during the measurements as a proxy of the inhalation rate used to calculate the inhaled dose of particles. All measured metrics were highest and well above background levels during walking. No significant difference was observed in the exposure concentration of PM2.5 for the three motorized transport modes, unlike for the metrics associated with ultrafine particles (UFP). The concentration of these freshly emitted particles was significantly lower on subway trips. The absence of combustion sources, use of air conditioning and screen doors at station platforms are effective measures to protect passengers' health. For other transport modes, sections of trips close to accelerating and idling vehicles, such as bus stops, traffic junctions and taxi stands, represent hotspots of particles. Reducing the waiting time at such locations will lower pollutants exposure and inhaled dose during a commute. After taking into account the effect of inhalation and travel duration when calculating dose, the health benefit of commuting by subway for this particular district of Singapore became even more evident. For example, pedestrians breathe in 2.6 and 3.2 times more PM2.5 and UFP, respectively than subway commuters. Public buses were the second best alternative. Walking emerged as the worst commuting mode in terms of particle exposure and inhaled dose.
Display omitted
•Transport policies need to consider exposure to pollutants on public transport.•Commuters are exposed to elevated concentrations of particles.•Commuting by subway reduces the inhaled dose of fine and ultrafine particles.•Walking results in the highest inhaled dose of particles at the present study site.•Pedestrian pathways need to be separated from vehicular traffic.
This paper presents an analysis of social dilemmas that arise when passengers are faced with choosing between personal vehicles and buses in a mixed traffic flow. We conducted the computer simulation ...using a cellular automata framework to analyze the case. The Revised S-NFS model describes the dynamics of vehicles in a single lane, while Kukida's model defines the rules for lane changing. The presence of social dilemma is determined by the social efficiency deficit. We selected four scenarios that represent different states on the fundamental diagram of personal vehicle flow: free flow, critical point, congested flow, and heavy congested flow. The simulations were performed on an infinite two-lane road. The results show that a social dilemma of the prisoner type exists in congested and heavy congested flow, but not in free flow. Additionally, we have conducted a simulation for the scenario with a dedicated bus lane. This simulation has shown the presence of the chicken-type social dilemma. Simulation results can enhance our comprehension of choosing transportation modes.
The number of daily commuters in Greater Cairo has exceeded 15 million nevertheless personal exposure studies in transport microenvironments are limited. The aim of this study is to quantify PM2.5 ...exposure during peak hours in four transport modes of Greater Cairo - car (windows-open, windows-closed with recirculation and AC-on), microbus (windows-open), cycling and walking - and understand its underlying drivers. Data was collected using a pDR-1500 monitor and analysed to capture concentration variations, spatial variability, exposure doses, commuting costs versus inhaled doses, health burden and economic losses. Car with recirculation resulted in the least average PM2.5 concentrations (32 ± 6 μg/m3), followed by walking (77 ± 35 μg/m3), car with windows-open (82 ± 32 μg/m3), microbus with windows-open (96 ± 29 μg/m3) and cycling (100 ± 28 μg/m3). Evening hours observed average PM2.5 concentrations by 26–58% lesser than morning. Spatial variability analysis showed that 75th–90th percentile PM2.5 concentrations coincided with congested spots. Cycling and walking lanes are rare hence commuters are exposed to surges in PM2.5 concentrations when passing near construction and solid waste burning sites. Cycling and walking also resulted in inhaling 40-times and 32-times higher PM2.5 dose per kilometre than for car with recirculation. Commuting by microbus cost (with windows-open) ~45% of car cost (with recirculation) but it resulted in 4-times higher inhaled PM2.5 dose. As expected due to the lowest PM2.5 exposure concentrations, health burden resulting from car travel (with recirculation) caused the least death rates of 0.07 (95% CI 0.07–0.08) prematures deaths per 100,000 commuters/year while microbus with windows-open resulted in the highest death rates; 0.52 (95% CI 0.49–0.56). Microbus deaths represent 57% of national economic losses due to PM2.5 exposure amongst the four transport modes. This study provides real-time exposure data and analyses its implications on commuter health as a first step in informed decision-making and better urban planning.
Display omitted
•PM2.5 exposure is assessed in four modes of transport in Greater Cairo.•Recirculation in car reduces PM2.5 exposure by 61% compared with windows-open.•Microbus costs 45% of car with recirculation but has 4-times PM2.5 inhaled dose.•Cyclists inhale 40-times PM2.5 doses (μg/km) that of car users with recirculation.•57% of premature deaths from PM2.5 transport exposure are microbus commuters.
•We process two months mobile network trajectories from the Greater Paris region.•The transport mode is inferred from all trajectories, using few labeled data.•Total road and rail OD flows are ...estimated over time at different resolutions.•The estimates are validated against survey and travel cards flows.
Fast urbanization generates increasing amounts of travel flows, urging the need for efficient transport planning policies. In parallel, mobile phone data have emerged as the largest mobility data source, but are not yet integrated to transport planning models. Currently, transport authorities are lacking a global picture of daily passenger flows on multimodal transport networks. In this work, we propose the first methodology to infer dynamic Origin-Destination flows by transport modes using mobile network data e.g., Call Detail Records. For this study, we pre-process 360 million trajectories for more than 2 million devices from the Greater Paris as our case study region. The model combines mobile network geolocation with transport network geospatial data, travel survey, census and travel card data. The transport modes of mobile network trajectories are identified through a two-steps semi-supervised learning algorithm. The later involves clustering of mobile network areas and Bayesian inference to generate transport probabilities for trajectories. After attributing the mode with highest probability to each trajectory, we construct Origin-Destination matrices by transport mode. Flows are up-scaled to the total population using state-of-the-art expansion factors. The model generates time variant road and rail passenger flows for the complete region. From our results, we observe different mobility patterns for road and rail modes and between Paris and its suburbs. The resulting transport flows are extensively validated against the travel survey and the travel card data for different spatial scales.