Using machine learning techniques to capture engineering design behaviors

James P. Bywater; Jennifer L. Chiu; Mark Floryan; Jie Chao; Corey Schimpf; Charles Xie; Camilo Vieira; Alejandra J. Magana; Chandan Dasgupta

Using machine learning techniques to capture engineering design behaviors

James P. Bywater
, Jennifer L. Chiu
, Mark Floryan
, Jie Chao
, Corey Schimpf
, Charles Xie
, Camilo Vieira
, Alejandra J. Magana
, Chandan Dasgupta

Department of Engineering Education

University of Virginia
Concord Consortium
Purdue University
Indian Institute of Technology Bombay

Research output: Contribution to journal › Conference article › peer-review

1 Scopus citations

Abstract

Engaging students in disciplinary practices can help students but many teachers face barriers implementing practice-based instruction as capturing, assessing, and providing feedback on practices can be labor and time intensive. This working paper reports on our early attempts to leverage machine learning techniques to analyze large process datasets of students engaged in engineering design projects within computer-aided environments. By identifying students’ engineering design behaviors, we hope to examine how different sequences of these behaviors can be used provide intelligent feedback and guidance.

Original language	English
Pages (from-to)	1359-1360
Number of pages	2
Journal	Proceedings of International Conference of the Learning Sciences, ICLS
Volume	3
Issue number	2018-June
State	Published - 2018
Event	13th International Conference of the Learning Sciences, ICLS 2018: Rethinking Learning in the Digital Age: Making the Learning Sciences Count - London, United Kingdom Duration: Jun 23 2018 → Jun 27 2018

Cite this

@article{88f20d63540d450e9f5f4db656554160,

title = "Using machine learning techniques to capture engineering design behaviors",

abstract = "Engaging students in disciplinary practices can help students but many teachers face barriers implementing practice-based instruction as capturing, assessing, and providing feedback on practices can be labor and time intensive. This working paper reports on our early attempts to leverage machine learning techniques to analyze large process datasets of students engaged in engineering design projects within computer-aided environments. By identifying students{\textquoteright} engineering design behaviors, we hope to examine how different sequences of these behaviors can be used provide intelligent feedback and guidance.",

author = "Bywater, \{James P.\} and Chiu, \{Jennifer L.\} and Mark Floryan and Jie Chao and Corey Schimpf and Charles Xie and Camilo Vieira and Magana, \{Alejandra J.\} and Chandan Dasgupta",

note = "Publisher Copyright: {\textcopyright} ISLS.; 13th International Conference of the Learning Sciences, ICLS 2018: Rethinking Learning in the Digital Age: Making the Learning Sciences Count ; Conference date: 23-06-2018 Through 27-06-2018",

year = "2018",

language = "English",

volume = "3",

pages = "1359--1360",

journal = "Proceedings of International Conference of the Learning Sciences, ICLS",

issn = "1814-9316",

publisher = "International Society of the Learning Sciences (ISLS)",

number = "2018-June",

}

TY - JOUR

T1 - Using machine learning techniques to capture engineering design behaviors

AU - Bywater, James P.

AU - Chiu, Jennifer L.

AU - Floryan, Mark

AU - Chao, Jie

AU - Schimpf, Corey

AU - Xie, Charles

AU - Vieira, Camilo

AU - Magana, Alejandra J.

AU - Dasgupta, Chandan

PY - 2018

Y1 - 2018

N2 - Engaging students in disciplinary practices can help students but many teachers face barriers implementing practice-based instruction as capturing, assessing, and providing feedback on practices can be labor and time intensive. This working paper reports on our early attempts to leverage machine learning techniques to analyze large process datasets of students engaged in engineering design projects within computer-aided environments. By identifying students’ engineering design behaviors, we hope to examine how different sequences of these behaviors can be used provide intelligent feedback and guidance.

AB - Engaging students in disciplinary practices can help students but many teachers face barriers implementing practice-based instruction as capturing, assessing, and providing feedback on practices can be labor and time intensive. This working paper reports on our early attempts to leverage machine learning techniques to analyze large process datasets of students engaged in engineering design projects within computer-aided environments. By identifying students’ engineering design behaviors, we hope to examine how different sequences of these behaviors can be used provide intelligent feedback and guidance.

UR - https://www.scopus.com/pages/publications/85053826375

M3 - Conference article

AN - SCOPUS:85053826375

SN - 1814-9316

VL - 3

SP - 1359

EP - 1360

JO - Proceedings of International Conference of the Learning Sciences, ICLS

JF - Proceedings of International Conference of the Learning Sciences, ICLS

IS - 2018-June

T2 - 13th International Conference of the Learning Sciences, ICLS 2018: Rethinking Learning in the Digital Age: Making the Learning Sciences Count

Y2 - 23 June 2018 through 27 June 2018

ER -

Using machine learning techniques to capture engineering design behaviors

Abstract

Other files and links

Fingerprint

Cite this