Analyzing Students' Computational Models as They Learn in STEM Disciplines

Anton Dukeman; Shashank Shekhar; Faruk Caglar; Aniruddha Gokhale; Gautam Biswas; John S. Kinnebrew

Download Paper | Permalink

Conference: 2014 ASEE Annual Conference & Exposition
Location: Indianapolis, Indiana
Publication Date: June 15, 2014
Start Date: June 15, 2014
End Date: June 18, 2014
ISSN: 2153-5965
Conference Session: K-12 and Pre-College Engineering Division Poster Session
Tagged Division: K-12 & Pre-College Engineering
Page Count: 8
Page Numbers: 24.186.1 - 24.186.8
DOI: 10.18260/1-2--20077
Permanent URL: https://strategy.asee.org/20077
Download Count: 552

Request a correction

Aniruddha Gokhale is an Associate Professor of Computer Science and Engineering in the Dept of Electrical Engineering and Computer Science at Vanderbilt University, Nashville, TN, USA. Prof. Gokhale got his BE (Computer Engineering) from Pune University, Pune, India in 1989; MS (Computer Science) from Arizona State University, Tempe, AZ in 1992; and PhD (Computer Science) from Washington University in St. Louis, St. Louis, MO in 1998. Prior to his current position at Vanderbilt University, he was a Member of Technical Staff at Lucent Bell Labs. He is a Senior Member of both the IEEE and ACM.His research interests are in solving distributed systems challenges for real-time and embedded systems through effective software engineering principles and algorithm development. He is applying these expertise to develop an effective, cloud-based and ubiquitous infrastructure for scalable, collaborative STEM education.

visit author page

biography

Gautam Biswas Vanderbilt University orcid.org/0000-0002-2752-3878

visit author page

Gautam Biswas is a Professor of Computer Science, Computer Engineering, and Engineering Management in the EECS Department and a Senior Research Scientist at the Institute for Software Integrated Systems (ISIS) at Vanderbilt University. He has an undergraduate degree in Electrical Engineering from the Indian Institute of Technology (IIT) in Mumbai, India, and M.S. and Ph.D. degrees in Computer Science from Michigan State University in E. Lansing, MI.

Prof. Biswas conducts research in Intelligent Systems with primary interests in hybrid modeling, simulation, and analysis of complex embedded systems, and their applications to diagnosis, prognosis, and fault-adaptive control. As part of this work, he has worked on fault diagnosis and fault-adaptive control of secondary sodium cooling systems for nuclear reactors, automobile engine coolant systems, fuel transfer systems for aircraft, Advanced Life Support systems and power distribution systems for NASA. He has also initiated new projects in health management of complex systems, which includes online algorithms for distributed monitoring, diagnosis, and prognosis. More recently, he is working on data mining for diagnosis, and developing methods that combine model-based and data-driven approaches for diagnostic and prognostic reasoning. This work, in conjunction with Honeywell Technical Center and NASA Ames, includes developing sophisticated data mining algorithms for extracting causal relations amongst variables and parameters in a system. For this work, he recently received the NASA 2011 Aeronautics Research Mission Directorate Technology and Innovation Group Award for Vehicle Level Reasoning System and Data Mining methods to improve aircraft diagnostic and prognostic systems.

In other research projects, he is involved in developing simulation-based environments for learning and instruction. The most notable project in this area is the Teachable Agents project, where students learn science by building causal models of natural processes. More recently, he has exploited the synergy between computational thinking ideas and STEM learning to develop systems that help students learn science and math concepts by building simulation models. He has also developed innovative educational data mining techniques for studying students’ learning behaviors and linking them to metacognitive strategies. His research has been supported by funding from NASA, NSF, DARPA, and the US Department of Education. His industrial collaborators include Airbus, Honeywell Technical Center, and Boeing Research and Development. He has published extensively, and has over 300 refereed publications.

Dr. Biswas is an associate editor of the IEEE Transactions on Systems, Man, and Cybernetics, Prognostics and Health Management, and Educational Technology and Society journal. He has served on the Program Committee of a number of conferences, and most recently was Program co-chair for the 18th International Workshop on Principles of Diagnosis and Program co-chair for the 15th International Conference on Artificial Intelligence in Education. He is currently serving on the Executive committee of the Asia Pacific Society for Computers in Education and is the IEEE Computer Society representative to the Transactions on Learning Technologies steering committee. He is also serving as the Secretary/Treasurer for ACM Sigart. He is a senior member of the IEEE Computer Society, ACM, AAAI, and the Sigma Xi Research Society.

visit author page

author page

John S. Kinnebrew Vanderbilt University

Download Paper | Permalink

Abstract

Modeling Student Program Evolution in STEM DisciplinesThe 21st century workplace places a heavy emphasis on STEM disciplines making them anessential part of middle school and high school education. Unfortunately the US is laggingbehind the rest of the world in STEM competency at all levels. One of the ways STEM educationcan be made more interesting and relevant is by tying it to real-world problems. With this inmind, we have been developing a system called C3STEM (Challenge-based CollaborativeCommunity-centered STEM), where students can learn the fundamentals of STEM disciplineslike physics and mathematics by modeling real-world systems, simulating the models tounderstand the behavior of the system, and then running experiments with the simulation modelsto solve complex problems. One such domain that we are working on is the modeling of trafficflow in urban areas. C3STEM provides students with an agent-based modeling environment anda visual programming interface, complete with conditionals and mathematical operations, whichallows students to build vehicle models using computational thinking constructs. C3STEMallows students to simulate their models by incorporating model translation and execution withNetLogo. Students can view their simulation alone or side-by-side with an expert simulationrunning in lockstep and employing the same initial parameters. By building vehicle models inC3STEM, students learn science curriculum fundamentals and mathematical modeling principlesin realistic contexts. They can then use their individual vehicle models to build traffic flowmodels through city streets and intersections.We present preliminary work on modeling the evolution of students’ programs/models in theC3STEM environment. In this paper, we present an initial analysis of two small studiesperformed in summer 2013, one involving seven high school students who were consideringundergraduate studies and future careers in engineering, and the other involving six middleschool students, who attended a one week long science summer camp. In these studies, studentsfirst modeled basic vehicular deceleration to come to a halt at a stop sign and then accelerationaway from the stop sign. Subsequent tasks included modeling driver behavior at a stoplight anddriver behavior while attempting a left turn across traffic.Our initial analysis employs measures typically used to compare much larger segments ofsoftware code and modifies them to apply to the much smaller amount of code that studentscreate in C3STEM. Some of the more well-known comparison metrics, such as the bag of wordsscore and abstract syntax tree edit distance, allow us to assign a similarity score between eachversion of a student’s model and the expert model. Tracking model changes over time allows usto better understand students’ modeling progressions and hopefully their understanding ofphysics, mathematics, and computational thinking constructs. Detecting errors in student modelsallows us to scaffold the student’s learning to facilitate understanding of both computationalthinking skills and domain specific knowledge.

Citation
Format

Dukeman, A., & Shekhar, S., & Caglar, F., & Gokhale, A., & Biswas, G., & Kinnebrew, J. S. (2014, June), Analyzing Students' Computational Models as They Learn in STEM Disciplines Paper presented at 2014 ASEE Annual Conference & Exposition, Indianapolis, Indiana. 10.18260/1-2--20077

TY  - CPAPER
AB  -               Modeling Student Program Evolution in STEM DisciplinesThe 21st century workplace places a heavy emphasis on STEM disciplines making them anessential part of middle school and high school education. Unfortunately the US is laggingbehind the rest of the world in STEM competency at all levels. One of the ways STEM educationcan be made more interesting and relevant is by tying it to real-world problems. With this inmind, we have been developing a system called C3STEM (Challenge-based CollaborativeCommunity-centered STEM), where students can learn the fundamentals of STEM disciplineslike physics and mathematics by modeling real-world systems, simulating the models tounderstand the behavior of the system, and then running experiments with the simulation modelsto solve complex problems. One such domain that we are working on is the modeling of trafficflow in urban areas. C3STEM provides students with an agent-based modeling environment anda visual programming interface, complete with conditionals and mathematical operations, whichallows students to build vehicle models using computational thinking constructs. C3STEMallows students to simulate their models by incorporating model translation and execution withNetLogo. Students can view their simulation alone or side-by-side with an expert simulationrunning in lockstep and employing the same initial parameters. By building vehicle models inC3STEM, students learn science curriculum fundamentals and mathematical modeling principlesin realistic contexts. They can then use their individual vehicle models to build traffic flowmodels through city streets and intersections.We present preliminary work on modeling the evolution of students’ programs/models in theC3STEM environment. In this paper, we present an initial analysis of two small studiesperformed in summer 2013, one involving seven high school students who were consideringundergraduate studies and future careers in engineering, and the other involving six middleschool students, who attended a one week long science summer camp. In these studies, studentsfirst modeled basic vehicular deceleration to come to a halt at a stop sign and then accelerationaway from the stop sign. Subsequent tasks included modeling driver behavior at a stoplight anddriver behavior while attempting a left turn across traffic.Our initial analysis employs measures typically used to compare much larger segments ofsoftware code and modifies them to apply to the much smaller amount of code that studentscreate in C3STEM. Some of the more well-known comparison metrics, such as the bag of wordsscore and abstract syntax tree edit distance, allow us to assign a similarity score between eachversion of a student’s model and the expert model. Tracking model changes over time allows usto better understand students’ modeling progressions and hopefully their understanding ofphysics, mathematics, and computational thinking constructs. Detecting errors in student modelsallows us to scaffold the student’s learning to facilitate understanding of both computationalthinking skills and domain specific knowledge.
AU  - Anton Dukeman
AU  - Shashank Shekhar
AU  - Faruk Caglar
AU  - Aniruddha Gokhale
AU  - Gautam Biswas
AU  - John S. Kinnebrew
CY  - Indianapolis, Indiana
DA  - 2014/06/15
PB  - ASEE Conferences
TI  - Analyzing Students' Computational Models as They Learn in STEM Disciplines
UR  - https://strategy.asee.org/20077
DO  - 10.18260/1-2--20077
ER  -