Road intersection identification from crowdsourced big trace data using Mask‐RCNN

2021 ◽  
Author(s):  
Xue Yang ◽  
Liang Hou ◽  
Mingqiang Guo ◽  
Yanjia Cao ◽  
Mingchun Yang ◽  
...  
Keyword(s):  
Trace Data

Trace-SRL: A Framework for Analysis of Microlevel Processes of Self-Regulated Learning From Trace Data

2020 ◽  
Vol 13 (4) ◽  
pp. 861-877
Author(s):  
John Saint ◽  
Alexander Whitelock-Wainwright ◽  
Dragan Gasevic ◽  
Abelardo Pardo
Keyword(s):  
Trace Data ◽  
Self Regulated Learning ◽  
Regulated Learning

scholarly journals Studying Undergraduate Course Consideration at Scale

AERA Open ◽  
2021 ◽  
Vol 7 ◽  
pp. 233285842199114
Author(s):  
Sorathan Chaturapruek ◽  
Tobias Dalberg ◽  
Marissa E. Thompson ◽  
Sonia Giebel ◽  
Monique H. Harrison ◽  
...  
Keyword(s):  
Empirical Study ◽  
Research University ◽  
Academic Major ◽  
College Completion ◽  
Course Selection ◽  
Choice Process ◽  
Trace Data ◽  
Student Interviews ◽  
Private Research

Elective curriculums require undergraduates to choose from a large roster of courses for enrollment each term. It has proven difficult to characterize this fateful choice process because it remains largely unobserved. Using digital trace data to observe this process at scale at a private research university, together with qualitative student interviews, we provide a novel empirical study of course consideration as an important component of course selection. Clickstream logs from a course exploration platform used by most undergraduates at the case university reveal that students consider on average nine courses for enrollment for their first fall term (<2% of available courses) and these courses predict which academic major students declare two years later. Twenty-nine interviews confirm that students experience consideration as complex and reveal variation in consideration strategies that may influence how consideration unfolds. Consideration presents a promising site for intervention in problems of equity, career funneling, and college completion.

scholarly journals Trip Travel Time Forecasting Based on Selective Forgetting Extreme Learning Machine

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
Zhiming Gui ◽  
Haipeng Yu
Keyword(s):  
Travel Time ◽  
Extreme Learning Machine ◽  
Road Networks ◽  
Time Estimation ◽  
Learning Ability ◽  
Prediction Algorithm ◽  
Travel Time Estimation ◽  
Trace Data ◽  
Learning Machine ◽  
Travel Time Forecasting

Travel time estimation on road networks is a valuable traffic metric. In this paper, we propose a machine learning based method for trip travel time estimation in road networks. The method uses the historical trip information extracted from taxis trace data as the training data. An optimized online sequential extreme machine, selective forgetting extreme learning machine, is adopted to make the prediction. Its selective forgetting learning ability enables the prediction algorithm to adapt to trip conditions changes well. Experimental results using real-life taxis trace data show that the forecasting model provides an effective and practical way for the travel time forecasting.

Visualizing Logical Correlation in Trace Data for System Debugging

Computer ◽  
2021 ◽  
Vol 54 (3) ◽  
pp. 28-36
Author(s):  
Chen Liu
Keyword(s):  
Trace Data

Demographic Characterization of Anonymous Trace Travel Data

2015 ◽  
Vol 2526 (1) ◽  
pp. 19-28 ◽  
Author(s):  
Joshua Auld ◽  
Abolfazl (Kouros) Mohammadian ◽  
Marcelo Simas Oliveira ◽  
Jean Wolf ◽  
William Bachman
Keyword(s):  
Test Data ◽  
Large Scale ◽  
Travel Demand ◽  
Null Model ◽  
Demographic Characteristics ◽  
Travel Pattern ◽  
Data Set ◽  
Trace Data ◽  
Demographic Models ◽  
Pattern Information

Research was undertaken to determine whether demographic characteristics of individual travelers could be derived from travel pattern information when no information about the individual was available. This question is relevant in the context of anonymously collected travel information, such as cell phone traces, when used for travel demand modeling. Determining the demographics of a traveler from such data could partially obviate the need for large-scale collection of travel survey data, depending on the purpose for which the data were to be used. This research complements methodologies used to identify activity stops, purposes, and mode types from raw trace data and presumes that such methods exist and are available. The paper documents the development of procedures for taking raw activity streams estimated from GPS trace data and converting these into activity travel pattern characteristics that are then combined with basic land use information and used to estimate various models of demographic characteristics. The work status, education level, age, and license possession of individuals and the presence of children in their households were all estimated successfully with substantial increases in performance versus null model expectations for both training and test data sets. The gender, household size, and number of vehicles proved more difficult to estimate, and performance was lower on the test data set; these aspects indicate overfitting in these models. Overall, the demographic models appear to have potential for characterizing anonymous data streams, which could extend the usability and applicability of such data sources to the travel demand context.

Sign in / Sign up

Export Citation Format

Share Document