United States

Quant PER is a growing subdiscipline that shows promise in helping our students succeed. My research group has sprouted&amp;nbsp;from this opportunity. I&#39;ll talk about building a functioning learning analytics lab, testing waters with exploratory statistics, moving into correlation data mining, and then proceeding onto predictive analytics. We&#39;ve used maching learning to predict students overall class grade percentage to within about 6% average error, before they even start the class. Come see all the fun things the BoxSand Research Group at Oregon State University is doing.

AAPT WM 21

The Growth of a Quant PER Group

big data

machine learning

The 9th Brazilian Conference on Intelligent Systems (BRACIS), the 16h Encontro Nacional de Inteligência Artificial e Computacional (ENIAC), and the 12th Concurso de Teses e Dissertações em Inteligência Artificial e Computacional (CTDIAC) was held from 20 to 23 October, 2020.

BRACIS originated from the combination of the two most important scientific events in Brazil in Artificial Intelligence (AI) and Computational Intelligence (CI): the Brazilian Symposium on Artificial Intelligence - SBIA (22 editions), and the Brazilian Symposium on Neural Networks - SBRN (13 editions). ENIAC is a national forum for researchers, practitioners, educators and students to present and discuss innovations, trends, experiences, developments and work in progress in the fields of Artificial and Computational Intelligence. CTDIAC is a satellite event whose goals are to disseminate and award the best dissertations and theses (MSc and PhDs concluded in Brazilian universities from June 2018 to May 2020) in Artificial and Computational Intelligence areas.

In this year, the Symposium on Knowledge Discovery, Mining and Learning (KDMiLe) will be held in conjunction with BRACIS 2020. This sysposium aims at integrating researchers, practitioners, developers, students and users to present their research results, to discuss ideas, and to exchange techniques, tools, and practical experiences – related to the Data Mining and Machine Learning areas.

BRACIS 2020

Quant PER is a growing subdiscipline that shows promise in helping our students succeed. My research group has sprouted&nbsp;from this opportunity. I'll talk about building a functioning learning analytics lab, testing waters with exploratory statistics, moving into correlation data mining, and then proceeding onto predictive analytics. We've used maching learning to predict students overall class grade percentage to within about 6% average error, before they even start the class. Come see all the fun things the BoxSand Research Group at Oregon State University is doing.

technical paper

AAPT® is a strong professional physics science society dedicated to the pursuit of excellence in physical science education.

Winter and Summer National Meetings:
These National Meetings, held each winter and summer, are opportunities for members, colleagues, and future physicists from around the world to:

- participate in physics workshops
- meet and greet other physics educators
- form networks nationally and locally
- engage exhibitors and learn about the latest physics resources
- discuss innovations in teaching methods
- share the results of research about teaching and learning.

If you're not able to log in, you're most likely using **incorrect login credentials**. Double-check that you are using the same email and password that you used to register for the conference, submit your abstract or access your AAPT membership. There may also be **an issue with your AAPT meeting registration**. Please email aapt2021@underline.io and programs@aapt.org and we will work quickly to resolve this issue.

Machine learning algorithms represent an exciting new class of quantitative methods to understand physics classes and students. Recent work has applied these algorithms to understand physics major retention to degree and the risk factors influencing success in introductory physics. This talk will explore the application of these algorithms to identify students most at risk of failure in introductory calculus-based physics. These predictions are complicated by the very unbalanced nature of the samples; most students do not fail physics. Machine learning algorithms&nbsp;will be explored in depth including&nbsp;decision trees and random forests. These will be applied to understand student risk both using institutional variables such as college GPA and within class variables such as homework grades with the goal of making accurate predictions early in the class. Limitations and data requirements for these algorithms as well as their accuracy for underrepresented populations will also be discussed.

Using Machine Learning to Identify At-Risk Students in Physics Classes

Hands-on experience is of utmost importance to physics laboratory experiences. Like most other schools and colleges, classes at Central Washington University had to adjust quickly to online-learning setups this past quarter. This new teaching style unfortunately pushed aside in-person interactive laboratory sessions that could have been used to supplement lecture-style videos that students watched as a part of their introductory medical physics seminar. Utilizing pre-measured data, videos, and photographs from a live clinical linear accelerator, the team at Northwest Medical Physics Center was able to create an online laboratory experience for real-time student engagement. In this presentation, the method of implementation of the lab will be discussed, along with goals for future expansion of the virtual medical physics lab program.

Virtual Medical Physics Undergraduate Laboratory Experience with Linear Accelerator Data

This educational research is about teaching electromagnetic interaction or rock formation. We use&nbsp;&nbsp;&nbsp;papers showing the elementary electron-electron-photon&nbsp;Feynman diagrams or&nbsp; sentimentation -metamorphism-melting geo-diagrams. The individual papers could be rotated, inverted, and combined to provide diagrams for any electromagnetic interaction process or rock formation. Combining orientations of single paper ,we make combinations of three or more papers. &nbsp;Time is running vertically upward in every diagram. Given the opportunity to manipulate the papers, students became involved and rapidly developed understanding of&nbsp;electromagnetic interaction or rock formation. The students did strikingly better on the post-tests than the pre-tests.

Teaching Physics with Hands-on Diagrams

2020 has seen a release of multiple exciting new results in gravitational wave science! In this session, we will review these latest discoveries that have opened new windows into understanding the universe. Then we will introduce teachers to activities that can be used in the classroom, both remote and in-person, to introduce secondary science students to some of the major concepts related to understanding and detecting gravitational waves, including the new results! Detectors such as LIGO and Virgo will be examined, as well as the use of Multimessenger Astronomy.

Gravitational Wave Science for the Secondary Classroom: Discoveries and Activities

&nbsp;Virtual or simulating experiments are developed and introduced by many organizations to enrich physics experiments within and beyond classrooms. Yet in the rural areas where resources are limits both physics experiment instruments and internet connection, teachers find it difficult to integrate experiments into classroom teaching activities. &nbsp;We analyzed the roles and current situations of simulating experiments in high school physics teaching in China. Evaluated several current running physics experiment simulation software packages. We found PhET is suitable for redeveloping and integrating into an off-line running package, which will benefit experiment teaching in rural areas where internet coverage is poor. The paper presents the approaches of redeveloping. For the sake of generality, we use Java language and HTML language for programming, and use HTML5 technique to integrate the experiments into an off-line running package. Successful on-the-site running shows the feasibility and applicability of redeveloping PhET simulation experiment for physics experiment teaching.

Re-development in Physics Experiment Teaching Using Simulation Based on PhET

Partnerships between our professional organizations and manufacturers are making it much more affordable to bring spatial light modulators (SLMs) into undergraduates' hands. SLMs are one way to shape light, in space or in time, making possible programmable dynamic holograms that actually have corporeal substance, and can play a role in&nbsp;faster-than-light imaging, as&nbsp;well as the use of&nbsp;entangled photon pairs (which cannot really be described as individual particles), such that the photons incident upon the detecting camera have never interacted with the object successfully imaged&nbsp;(which is&nbsp;called "ghost imaging," in reference to Einstein's concern over "spooky action at a distance"); this "spooky" result is achieved by exploiting&nbsp; correlations &nbsp;that are required by conservation of energy &amp; momentum. —&nbsp;Observed phenomena of these sorts prompt students to revise their mental model of what a "particle" is!

Shaping Light in Time and Space

A drinking bird (DB) also known as dunking bird or dipping bird is an interesting and amusing toy, swinging back-and-forth like a simple pendulum.&nbsp; But the drinking bird is an excellent experimental toy for thermodynamics in physics.&nbsp; The field of thermodynamics explains about mechanism of work, heat and energy, temperature, pressure and volume.&nbsp; These quantities are working in everywhere in nature, our daily life, engineering technologies, etc., and a drinking bird is often called a heat engine.&nbsp; It changes heat flows into work very efficiently. So, the drinking bird makes a perfect experimental device for understanding theory of heat and energy (thermodynamics).&nbsp; DB’s mechanical and thermomechanical motion can explain theories and laws of thermodynamics and irreversible thermodynamics.

Mechanism of a Water Drinking Bird, Thermodynamics and Irreversible Thermodynamics

Many concepts in physics involve abstract ideas that require learners to imagine invisible causes, while interpreting the concrete effects and integrating seemingly ambiguous representations (ERs). The difficulty of this parallel processing often results in learners developing misconceptions and lacking the skills to communicate about these concepts effectively. This paper describes a study that used an augmented reality program (Magna-AR) to help learners see abstract magnetic fields within a real-world environment using the internal magnetic field sensor within mobile devices. Learners were asked to use Magna-AR to construct 3D visualizations of magnetic fields of the Earth and around other smaller magnets. Learners were also asked to draw 2D visualizations of magnetic fields and to identify the connections between various ERs of magnetic fields. A selected subset of the learners also participated in follow-up interviews. Preliminary analyses of these data will be discussed.

Sensing and Representing Magnetic Fields in Augmented Reality

For highly interactive courses regularly&nbsp;using lab equipment, the transistion to remote instruction presents significant challenges. Breakout rooms during video conferences can be quite helpful for discussion, but without shared experiences with equipment, it's not quite complete.&nbsp; And, while there exist many videos and resources online, there are likely details or more salient points you'd like students to consider than what's readily available from the publisher or on the internet. This&nbsp;talk will present lessons learned in creating&nbsp;amateur videos of&nbsp;mock group-work as an attempt to keep the flow and atmosphere of a studio-format&nbsp;class constructive.&nbsp;This is part of a series of talks stemming from the NextGen PET FOLC project. This work was supported by the National Science Foundation grant NSF DUE-1626496.

On Creating Your Own Course Videos to Emulate Group Work

Vernier products have greatly changed how my classroom and lab is run. I have designed my classroom around student access to Vernier probeware so that lab can occur at anytime! In this talk I will discuss how I use some of my favorite prodcuts in class and online (I mean COVID and all). I will highlight the products that in my opinion have impacted student learning the greatest. This will include everything from motion to atomic spectra!

Premium content

The Growth of a Quant PER Group

Downloads

Next from AAPT WM 21

Using Machine Learning to Identify At-Risk Students in Physics Classes

Similar lecture

Cloud Computing and Machine Learning for Analysis ofLarge Volumes of Educational Data