MétaCan
Menu
Back to cohort
Record W4285387998 · doi:10.1177/03611981221106483

Machine-Learning Approaches to Identify Travel Modes Using Smartphone-Assisted Survey and Map Application Programming Interface

2022· article· en· W4285387998 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

VenueTransportation Research Record Journal of the Transportation Research Board · 2022
Typearticle
Languageen
FieldSocial Sciences
TopicHuman Mobility and Location-Based Analysis
Canadian institutionsPolytechnique Montréal
Fundersnot available
KeywordsComputer scienceIdentification (biology)Support vector machineTravel surveyDecision treeGlobal Positioning SystemData miningTravel behaviorMachine learningArtificial intelligenceTransport engineeringEngineering

Abstract

fetched live from OpenAlex

Travel mode choice prediction is essential for transportation planning and travel demand prediction. One of the conventional travel survey methods is collecting data over landline telephones, which lacks efficiency because of financial and time resource needs. In this regard, smartphone-assisted travel surveys can be applied to overcome the mentioned deficiencies. Smartphone-assisted travel surveys allow respondents to record GPS data, travel purpose, and travel mode via an application, simplifying the survey process. With various sensors equipped, the precision of data is ensured. Based on the survey results, varied approaches have been seen to travel mode identification. For this study, a travel survey was conducted in Hangzhou, China, supported by the smartphone application TraceRecord integrated with online mapping services. Several steps were undertaken to recognize different kinds of travel modes. First, preprocessing was adopted to screen out defective logs. With the employment of A-Map Application Programming Interface (API), trajectory segmentation was substantially boosted. Then, separately, features related to velocity, acceleration, and heading were extracted from the survey data. To achieve better accuracy and efficacy, two classification algorithms—support vector machine (SVM) and gradient boosting decision tree (GBDT)—were applied to model the travel mode identification problem. Compared with the SVM, GBDT produced a higher prediction accuracy of 90.16%. Further analysis was implemented based on the results of the GBDT model, and velocity-related features contributed the most to the identification problem. The study explores the possibility of applying travel mode recognition in real-world conditions and discusses further mining of the survey data.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.019
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesScience and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.234
Threshold uncertainty score0.998

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0190.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.003
Science and technology studies0.0040.001
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.290
GPT teacher head0.441
Teacher spread0.150 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it