Who you are is how you travel: A framework for transportation mode detection using individual and environmental characteristics

Bantis, Thanos; Haworth, James

doi:10.1016/j.trc.2017.05.003

Cited by 62 publications

(42 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The research also showed that additional knowledge such as bus stop location can improve the algorithm results. Bantis and Haworth (2017) analyzed the relationship between personal and socio-demographic characteristics and travel mode choice using a Bayesian network.…”

Section: Mode Detectionmentioning

confidence: 99%

Developing a passive GPS tracking system to study long-term travel behavior

Marra

Becker

Corman

2019

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

This paper describes development and testing of a passive GPS tracking smartphone application and corresponding data analysis methodology designed to increase the quality of travel behavior information collected in long-term travel surveys. The new approach is intended to replace the pencil-and-paper travel diaries and prompted recall methods that require more user involvement due to requirements for manual data entry and/or high battery usage. Reducing the burden placed on users enables researchers to collect data over longer periods, thus improving the quality of travel behavior research. To reduce battery use the smartphone-based application collects GPS data less frequently than other methods. Therefore, new algorithms were developed to identify trips and activities, transport mode, and even the specific vehicle used by the traveler. An important finding was the significant advantage of using users past data to improve mode detection results. The system was tested successfully in Zürich and Basel (Switzerland).

show abstract

Section: Mode Detectionmentioning

confidence: 99%

Developing a passive GPS tracking system to study long-term travel behavior

Marra

Becker

Corman

2019

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

show abstract

“…temporal information with socio-demographic characteristics of travelers can also lead to generating richer travel mode detection models (Bantis and Haworth, 2017). However, the methodologies using only one type of sensor can be more practical since accessing to several data sources may not be possible in many cities (Xiao et al, 2017).…”

Section: Introductionmentioning

confidence: 99%

Inferring transportation modes from GPS trajectories using a convolutional neural network

Dabiri

Heaslip

2018

Transportation Research Part C: Emerging Technologies

322

285

View full text Add to dashboard Cite

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. GPS is a ubiquitous positioning tool that records spatiotemporal information of moving objects carrying a GPS-enabled device (K. Heaslip). Transportation Research Part C 86 (2018) 360-371 0968-090X/ Published by Elsevier Ltd.T (e.g., a smartphone). The main advantageous of smart phones, compared to other GPS-equipped devices, is its enormous market penetration rate in a large number of countries and being relatively close to users nearly all of the time. As a consequence, such a dominant and area-wide sensing technology is capable of creating massive trajectory data of vehicles and people. A GPS trajectory, also called movement, of an object is constructed by connecting GPS points of their GPS-enabled device. A GPS point, here, is denoted as (lat, long, t), where lat, long, and t are latitude, longitude, and timestamp, respectively. The study of individuals' mobility patterns from GPS datasets has led to a variety of behavioral applications including learning significant locations, anomaly detection, locationbased activity recognition, and identification of transport modes (Lin and Hsu, 2014), in which the latter is the focus of this study. Nonetheless, GPS devices can only record time and positional characteristics of travels without any explicit information on utilized transport modes....

show abstract

“…The raw SCD cannot be fed directly into the supervised models. As suggested by previous works, employment status is closely related to temporal travel features and travel mode choice [5], [15]. Therefore, how to represent the temporal behavior in different travel modes from SCD is fundamental for employment status prediction.…”

Section: A Temporal Profile Representation As a 3d Imagementioning

confidence: 98%

“…In the proposed methodology, passengers labeled with survey data were used to train a supervised learning model. As suggested, employment status is closely related to temporal travel behaviors and travel mode [5], [15], so an SCD representation method was used to characterize the two types of features. Each individual's temporal profiles in different travel modes were structured into a 3D image of size N × M × D, where N indicates the seven days of a week, M is the number of time slots in the day and D is the number of the travel mode.…”

mentioning

confidence: 99%

A Deep Learning Approach to Infer Employment Status of Passengers by Using Smart Card Data

Zhang

Cheng

2020

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Understanding the employment status of passengers in public transit systems is significant for transport operators in many real applications such as forecasting travel demand and providing personalized transportation service. This paper develops a deep learning approach to infer a passenger's employment status by using smart card data (SCD) with a household survey. This paper first extracts an individual passenger's weekly travel patterns in different travel modes from the raw SCD as a three-dimensional image. A deep learning architecture, called a thresholding multi-channel convolutional neural network, was developed to predict an individual's employment status. The approach proposed here solves two critical problems of using the SCD for employment status studies. First, it automatically incorporates learning temporal features in different travel modes without the need for handcrafted travel feature design. Second, it considers the class-imbalance problem by leveraging the ensemble of oversampling and thresholding techniques. By applying our approach to a real dataset collected from the metropolitan area of London, U.K., about 72% of passengers were correctly categorized into six types of employment statuses. The promising results show the tight correlation between temporal travel behavior, mode choice, and social-demographic roles. To the best of our knowledge, this is the first paper to infer employment status by using the SCD.Index Terms-Deep learning, employment status inference, travel mode choice, smart card data, temporal travel behavior.

show abstract

Who you are is how you travel: A framework for transportation mode detection using individual and environmental characteristics

Cited by 62 publications

References 27 publications

Developing a passive GPS tracking system to study long-term travel behavior

Developing a passive GPS tracking system to study long-term travel behavior

Inferring transportation modes from GPS trajectories using a convolutional neural network

A Deep Learning Approach to Infer Employment Status of Passengers by Using Smart Card Data

Contact Info

Product

Resources

About