Making mode detection transferable: extracting activity and travel episodes from GPS data using the multinomial logit model and Python

ABSTRACT The increasing popularity of global positioning systems (GPSs) has prompted transportation researchers to develop methods that can automatically extract and classify episodes from GPS data. This paper presents a transferable and efficient method of extracting and classifying activity episodes from GPS data, without additional information. The proposed method, developed using Python®, introduces the use of the multinomial logit (MNL) model in classifying extracted episodes into different types: stop, car, walk, bus, and other (travel) episodes. The proposed method is demonstrated using a GPS dataset from the Space-Time Activity Research project in Halifax, Canada. The GPS data consisted of 5127 person-days (about 47 million points). With input requirements directly derived from GPS data and the efficiency provided by the MNL model, the proposed method looks promising as a transferable and efficient method of extracting activity and travel episodes from GPS data.

[1]  Peter R. Stopher,et al.  Processing GPS data from travel surveys , 2005 .

[2]  Jean-Philippe Thiran,et al.  Modelling human perception of static facial expressions , 2008, 2008 8th IEEE International Conference on Automatic Face & Gesture Recognition.

[3]  R. Maddison,et al.  Global positioning system: a new opportunity in physical activity measurement , 2009, The international journal of behavioral nutrition and physical activity.

[4]  Miguel A. Labrador,et al.  Automating Mode Detection Using Neural Networks and Assisted GPS Data Collected Using GPS-Enabled Mobile Phones , 2008 .

[5]  Hugh Millward,et al.  Time use, travel behavior, and the rural–urban continuum: results from the Halifax STAR project , 2011 .

[6]  Eleni I. Vlahogianni,et al.  Statistical methods versus neural networks in transportation research: Differences, similarities and some insights , 2011 .

[7]  Eui-Hwan Chung,et al.  A Trip Reconstruction Tool for GPS-based Personal Travel Surveys , 2005 .

[8]  Robert Weibel,et al.  Revealing the physics of movement: Comparing the similarity of movement characteristics of different types of moving objects , 2009, Comput. Environ. Urban Syst..

[9]  Kay W. Axhausen,et al.  Processing Raw Data from Global Positioning Systems without Additional Information , 2009 .

[10]  Shauna L. Hallmark,et al.  Accuracy Issues with Route Choice Data Collection by Using Global Positioning System , 1999 .

[11]  Moshe Ben-Akiva,et al.  TRANSFERABILITY AND UPDATING OF DISAGGREGATE TRAVEL DEMAND MODELS , 1976 .

[12]  C. Lawson.  Final Report Advanced Applications of Person-based GPS in an Urban Environment , 2011 .

[13]  Xing Xie,et al.  Learning transportation mode from raw gps data for geographic applications on the web , 2008, WWW.

[14]  Jean Louise Wolf,et al.  Using GPS data loggers to replace travel diaries in the collection of travel data , 2000 .

[15]  Amer Shalaby,et al.  Enhanced System for Link and Mode Identification for Personal Travel Surveys Based on Global Positioning Systems , 2006 .

[16]  Martin T. Pietrucha,et al.  FIELD STUDIES OF PEDESTRIAN WALKING SPEED AND START-UP TIME , 1996 .

[17]  Filip Biljecki,et al.  Automatic segmentation and classification of movement trajectories for transportation modes , 2010 .

[18]  Nelly Kalfs,et al.  Global Positioning System as Data Collection Method for Travel Research , 2000 .

[19]  Kees Maat,et al.  Deriving and validating trip purposes and travel modes for multi-day GPS-based travel surveys: A large-scale application in the Netherlands , 2009 .

[20]  R. O’Brien,et al.  A Caution Regarding Rules of Thumb for Variance Inflation Factors , 2007 .

[21]  John LaPlante,et al.  A History of Pedestrian Signal Walking Speed Assumptions , 2007 .

[22]  Catherine T. Lawson,et al.  A GPS/GIS method for travel mode detection in New York City , 2012, Comput. Environ. Urban Syst..

[23]  D. McFadden,et al.  Specification tests for the multinomial logit model , 1984 .

[24]  Chester G. Wilmot,et al.  Evidence on Transferability of Trip-Generation Models , 1995 .

[25]  J. A. Calvin.  Regression Models for Categorical and Limited Dependent Variables , 1998 .

[26]  E. Murakami,et al.  Can using global positioning system (GPS) improve trip reporting , 1999 .

[27]  Florian Heiss,et al.  Discrete Choice Methods with Simulation , 2016 .

[28]  Haris N. Koutsopoulos,et al.  Improved methods for classification of pavement distress images , 1994 .

[29]  Darren M. Scott,et al.  GIS-based episode reconstruction toolkit (GERT): A transferable, modular, and scalable framework for automated extraction of activity episodes from GPS data , 2017 .

[30]  Joseph N. Prashker,et al.  Spatial and Temporal Transferability of Trip Generation Demand Models in Israel , 2005 .

[31]  H. Kundel,et al.  Measurement of observer agreement. , 2003, Radiology.

[32]  Moshe Ben-Akiva,et al.  Discrete Choice Analysis: Theory and Application to Travel Demand , 1985 .

[33]  J. G. Hunt,et al.  Modelling dual carriageway lane changing using neural networks , 1994 .

[34]  D. McFadden.  Conditional logit analysis of qualitative choice behavior , 1972 .

[35]  Peter R. Stopher,et al.  In-Depth Comparison of Global Positioning System and Diary Records , 2011 .

[36]  Darren M. Scott,et al.  GIS-based Map-matching: Development and Demonstration of a Postprocessing Map-matching Algorithm for Transportation Research , 2011, AGILE Conf..

[37]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.