scholarly journals A Data-Driven Travel Mode Share Estimation Framework based on Mobile Device Location Data

2021 ◽  
Author(s):  
Mofeng Yang ◽  
Yixuan Pan ◽  
Aref Darzi ◽  
Sepehr Ghader ◽  
Chenfeng Xiong ◽  
...  
Keyword(s):  
Mobile Device ◽  
Travel Behavior ◽  
Travel Demand ◽  
Ground Truth ◽  
Data Driven ◽  
Travel Mode ◽  
Location Data ◽  
Mode Share ◽  
Device Location ◽  
Ground Truth Information

Abstract Mobile device location data (MDLD) contains abundant travel behavior information to support travel demand analysis. Compared to traditional travel surveys, MDLD has larger spatiotemporal coverage of the population and its mobility. However, ground truth information such as trip origins and destinations, travel modes, and trip purposes are not included by default. Such important attributes must be imputed to maximize the usefulness of the data. This paper targets at studying the capability of MDLD on estimating travel mode share at aggregated levels. A data-driven framework is proposed to extract travel behavior information from MDLD. The proposed framework first identifies trip ends with a modified Spatiotemporal Density-based Spatial Clustering of Applications with Noise (ST-DBSCAN) algorithm. Then three types of features are extracted for each trip to impute travel modes using machine learning models. A labeled MDLD dataset with ground truth information is used to train the proposed models, resulting in a 95% recall rate in identifying trip ends and a 93% 10-fold cross-validation accuracy in imputing the five travel modes (drive, rail, bus, bike and walk) with a Random Forest (RF) classifier. The proposed framework is then applied to two large-scale MDLD datasets, covering the Baltimore-Washington metropolitan area and the United States, respectively. The estimated trip distance, trip time, trip rate distribution, and travel mode share are compared against travel surveys at different geographies. The results suggest that the proposed framework can be readily applied in different states and metropolitan regions with low cost in order to study multimodal travel demand, understand mobility trends, and support decision making.

scholarly journals A data-driven travel mode share estimation framework based on mobile device location data

2021 ◽  
Author(s):  
Mofeng Yang ◽  
Yixuan Pan ◽  
Aref Darzi ◽  
Sepehr Ghader ◽  
Chenfeng Xiong ◽  
...  
Keyword(s):  
Mobile Device ◽  
Data Driven ◽  
Travel Mode ◽  
Location Data ◽  
Mode Share ◽  
Device Location

Examining the Equity Impacts of Autonomous Vehicles: A Travel Demand Model Approach

2019 ◽  
Vol 2673 (5) ◽  
pp. 23-35 ◽  
Author(s):  
Jesse Cohn ◽  
Richard Ezike ◽  
Jeremy Martin ◽  
Kwasi Donkor ◽  
Matthew Ridgway ◽  
...  
Keyword(s):  
Performance Measures ◽  
Travel Behavior ◽  
Autonomous Vehicles ◽  
Travel Demand ◽  
Autonomous Vehicle ◽  
Demand Model ◽  
The Status ◽  
Mode Share ◽  
Transit Agencies ◽  
Travel Demand Model

As investments in autonomous vehicle (AV) technology continue to grow, agencies are beginning to consider how AVs will affect travel behavior within their jurisdictions and how to respond to this new mobility technology. Different autonomous futures could reduce, perpetuate, or exacerbate existing transportation inequities. This paper presents a regional travel demand model used to quantify how transportation outcomes may differ for disadvantaged populations in the Washington, D.C. area under a variety of future scenarios. Transportation performance measures examined included job accessibility, trip duration, trip distance, mode share, and vehicle miles traveled. The model evaluated changes in these indicators for disadvantaged and non-disadvantaged communities under scenarios when AVs were primarily single-occupancy or high-occupancy, and according to whether transit agencies responded to AVs by maintaining the status quo, removing low-performing routes, or applying AV technology to transit vehicles. Across the performance measures, the high-occupancy AV and enhanced transit scenarios provided an equity benefit, either mitigating an existing gap in outcomes between demographic groups or reducing the extent to which that gap was expanded.

scholarly journals AN INTERACTIVE COVID-19 MOBILITY IMPACT AND SOCIAL DISTANCING ANALYSIS PLATFORM

2020 ◽  
Author(s):  
Lei Zhang ◽  
Sepehr Ghader ◽  
Michael L. Pack ◽  
Chenfeng Xiong ◽  
Aref Darzi ◽  
...  
Keyword(s):  
Mobile Device ◽  
Research Team ◽  
Impact Analysis ◽  
Population Data ◽  
Public Officials ◽  
Process Data ◽  
Social Distancing ◽  
Location Data ◽  
Analysis Platform ◽  
Device Location

ABSTRACTThe research team has utilized privacy-protected mobile device location data, integrated with COVID-19 case data and census population data, to produce a COVID-19 impact analysis platform that can inform users about the effects of COVID-19 spread and government orders on mobility and social distancing. The platform is being updated daily, to continuously inform decision-makers about the impacts of COVID-19 on their communities using an interactive analytical tool. The research team has processed anonymized mobile device location data to identify trips and produced a set of variables including social distancing index, percentage of people staying at home, visits to work and non-work locations, out-of-town trips, and trip distance. The results are aggregated to county and state levels to protect privacy and scaled to the entire population of each county and state. The research team are making their data and findings, which are updated daily and go back to January 1, 2020, for benchmarking, available to the public in order to help public officials make informed decisions. This paper presents a summary of the platform and describes the methodology used to process data and produce the platform metrics.

scholarly journals Interactive COVID-19 Mobility Impact and Social Distancing Analysis Platform

2021 ◽  
pp. 036119812110438
Author(s):  
Lei Zhang ◽  
Aref Darzi ◽  
Sepehr Ghader ◽  
Michael L. Pack ◽  
Chenfeng Xiong ◽  
...  
Keyword(s):  
Mobile Device ◽  
Research Team ◽  
Impact Analysis ◽  
Population Data ◽  
Public Officials ◽  
Process Data ◽  
Social Distancing ◽  
Location Data ◽  
Analysis Platform ◽  
Device Location

The research team has utilized privacy-protected mobile device location data, integrated with COVID-19 case data and census population data, to produce a COVID-19 impact analysis platform that can inform users about the effects of COVID-19 spread and government orders on mobility and social distancing. The platform is being updated daily, to continuously inform decision-makers about the impacts of COVID-19 on their communities, using an interactive analytical tool. The research team has processed anonymized mobile device location data to identify trips and produced a set of variables, including social distancing index, percentage of people staying at home, visits to work and non-work locations, out-of-town trips, and trip distance. The results are aggregated to county and state levels to protect privacy, and scaled to the entire population of each county and state. The research team is making their data and findings, which are updated daily and go back to January 1, 2020, for benchmarking, available to the public to help public officials make informed decisions. This paper presents a summary of the platform and describes the methodology used to process data and produce the platform metrics.

scholarly journals Impact of close interpersonal contact on COVID-19 incidence: evidence from one year of mobile device data

2021 ◽  
Author(s):  
Forrest W. Crawford ◽  
Sydney A. Jones ◽  
Matthew Cartter ◽  
Samantha G. Dean ◽  
Joshua L. Warren ◽  
...  
Keyword(s):  
Mobile Device ◽  
Close Contact ◽  
Population Level ◽  
First Year ◽  
Contact Rate ◽  
Interpersonal Contact ◽  
Location Data ◽  
Frequency Of Contact ◽  
One Year ◽  
Device Location

AbstractClose contact between people is the primary route for transmission of SARS-CoV-2, the virus that causes coronavirus disease 2019 (COVID-19). We sought to quantify interpersonal contact at the population-level by using anonymized mobile device geolocation data. We computed the frequency of contact (within six feet) between people in Connecticut during February 2020 – January 2021. Then we aggregated counts of contact events by area of residence to obtain an estimate of the total intensity of interpersonal contact experienced by residents of each town for each day. When incorporated into a susceptible-exposed-infective-removed (SEIR) model of COVID-19 transmission, the contact rate accurately predicted COVID-19 cases in Connecticut towns during the timespan. The pattern of contact rate in Connecticut explains the large initial wave of infections during March–April, the subsequent drop in cases during June–August, local outbreaks during August–September, broad statewide resurgence during September–December, and decline in January 2021. Contact rate data can help guide public health messaging campaigns to encourage social distancing and in the allocation of testing resources to detect or prevent emerging local outbreaks more quickly than traditional case investigation.One sentence summaryClose interpersonal contact measured using mobile device location data explains dynamics of COVID-19 transmission in Connecticut during the first year of the pandemic.

scholarly journals Estimation of Travel Mode Choice Using Geostatistics: a Brazilian Case Study

2021 ◽  
Vol 73 (1) ◽  
pp. 182-197
Author(s):  
Anabele Lindner ◽  
Cira Souza Pitombo ◽  
Lucas Assirati ◽  
Jorge Ubirajara Pedreira Junior ◽  
Ana Rita Salgueiro
Keyword(s):  
Travel Behavior ◽  
Travel Demand ◽  
Spatial Information ◽  
Explanatory Power ◽  
Spatial Relationship ◽  
Correlated Data ◽  
Travel Mode ◽  
Spatially Correlated ◽  
Satisfactory Outcome ◽  
Geostatistical Approach

Traditional methods for travel demand estimation are often built on socioeconomic and travel information. The information required to conduct such studies is costly and rarely available in developing countries. Besides, some conventional methods do not consider the spatial relationship of variables and, in general, a large amount of socioeconomic and individual travel data is required. The key aim of this paper is to evaluate the importance of considering spatial information when estimating travel mode choices especially considering the lack of available data. The study area is the São Paulo Metropolitan Area (Brazil) and the dataset refers to an Origin-Destination Survey, conducted in 2007. This research paper analyzes the use of Geostatistics when estimating discrete travel mode choices. The results demonstrated a satisfactory outcome for the geostatistical approach. Finally, although socioeconomic and travel variables have greater explanatory power in predicting travel mode choices, spatial factors contribute to better understand the travel behavior and to provide further information when estimating spatially correlated data.

scholarly journals Mobile device data reveal the dynamics in a positive relationship between human mobility and COVID-19 infections

2020 ◽  
Vol 117 (44) ◽  
pp. 27087-27089 ◽  
Author(s):  
Chenfeng Xiong ◽  
Songhua Hu ◽  
Mofeng Yang ◽  
Weiyu Luo ◽  
Lei Zhang
Keyword(s):  
Mobile Device ◽  
Positive Relationship ◽  
Travel Demand ◽  
Human Mobility ◽  
Virus Transmission ◽  
Emergency Situation ◽  
Data Availability ◽  
The Public ◽  
Location Data ◽  
Epidemics Models

Accurately estimating human mobility and gauging its relationship with virus transmission is critical for the control of COVID-19 spreading. Using mobile device location data of over 100 million monthly active samples, we compute origin–destination travel demand and aggregate mobility inflow at each US county from March 1 to June 9, 2020. Then, we quantify the change of mobility inflow across the nation and statistically model the time-varying relationship between inflow and the infections. We find that external travel to other counties decreased by 35% soon after the nation entered the emergency situation, but recovered rapidly during the partial reopening phase. Moreover, our simultaneous equations analysis highlights the dynamics in a positive relationship between mobility inflow and the number of infections during the COVID-19 onset. This relationship is found to be increasingly stronger in partially reopened regions. Our study provides a quick reference and timely data availability for researchers and decision makers to understand the national mobility trends before and during the pandemic. The modeling results can be used to predict mobility and transmissions risks and integrated with epidemics models to further assess the public health outcomes.

scholarly journals Multiple Binary Classification Model of Trip Chain Based on the Fusion of Internet Location Data and Transport Data

2021 ◽  
Vol 13 (21) ◽  
pp. 12298
Author(s):  
Wenjing Wang ◽  
Yanyan Chen ◽  
Haodong Sun ◽  
Yusen Chen
Keyword(s):  
Travel Behavior ◽  
Large Scale ◽  
Binary Classification ◽  
Classification Model ◽  
Engineering Practice ◽  
Travel Mode ◽  
Location Data ◽  
Trip Chain ◽  
Multi Classification ◽  
The Relationship

Observing and analyzing travel behavior is important, requiring understanding detailed individual trip chains. Existing studies on identifying travel modes have mainly used some travel features based on GPS and survey data from a small number of users. However, few studies have focused on evaluating the effectiveness of these models on large-scale location data. This paper proposes to use travel location data from an Internet company and travel data from transport department to identify travel modes. A multiple binary classification model based on data fusion is used to find out the relationship between travel mode and different features. Firstly, we enlisted volunteers to collect travel data and record their travel trip process using a custom-developed WeChat program. Secondly, we have developed three binary classification models to explain how different attributes can be used to model travel mode. Compared with one multi-classification model, the accuracy of our model improved significantly, with prediction accuracies of 0.839, 0.899, 0.742, 0.799, and 0.799 for walk, metro, bike, bus, and car, respectively. This suggests that the model could be applied not only in engineering practice to identify the trip chain from Internet location data but also in decision support for transportation planners.

Using Deep Learning to Understand Travel Demands in Different Urban Districts

2021 ◽  
pp. 036119812199458
Author(s):  
Shunhua Bai ◽  
Junfeng Jiao
Keyword(s):  
Built Environment ◽  
Travel Behavior ◽  
Prediction Accuracy ◽  
Travel Demand ◽  
Short Term Memory ◽  
Future Research ◽  
Demand Forecast ◽  
Time And Space ◽  
The University ◽  
The Impact

Travel demand forecast plays an important role in transportation planning. Classic models often predict people’s travel behavior based on the physical built environment in a linear fashion. Many scholars have tried to understand built environments’ predictive power on people’s travel behavior using big-data methods. However, few empirical studies have discussed how the impact might vary across time and space. To fill this research gap, this study used 2019 anonymous smartphone GPS data and built a long short-term memory (LSTM) recurrent neural network (RNN) to predict the daily travel demand to six destinations in Austin, Texas: downtown, the university, the airport, an inner-ring point-of-interest (POI) cluster, a suburban POI cluster, and an urban-fringe POI cluster. By comparing the prediction results, we found that: the model underestimated the traffic surge for the university in the fall semester and overestimated the demand for downtown on non-working days; the prediction accuracy for POI clusters was negatively related to their adjacency to downtown; and different POI clusters had cases of under- or overestimation on different occasions. This study reveals that the impact of destination attributes on people’s travel demand can vary across time and space because of their heterogeneous nature. Future research on travel behavior and built environment modeling should incorporate the temporal inconsistency to achieve better prediction accuracy.

Sign in / Sign up

Export Citation Format

Share Document