Presented by Dr. Conrad Tucker, Associate Professor in the School of Engineering Design, Technology, and Professional Programs. Dr. Conrad Tucker examined the potential of artificial intelligence (AI) to instantaneously provide information that personalizes learning for individual students.
Advancing Personalized Learning through Big Data and Artificial Intelligence
1. http://www.engr.psu.edu/datalab/ 11
Advancing Personalized Learning
through Big Data and Artificial
Intelligence
February 27th, 2018
Conrad S. Tucker, Ph.D., MBA
Associate Professor: Engineering Design and Industrial
and Manufacturing Engineering
Affiliate Faculty: Computer Science and Engineering
Email:ctucker4@psu.edu
7. http://www.engr.psu.edu/datalab/ 7
Now hold on a minute…
• we’re not trying to replace the
instructor/ teaching assistant
• we want the instructor/teaching
assistant to focus on knowledge
dissemination, rather than
repetitive task correction
Introduction
8. http://www.engr.psu.edu/datalab/ 8
An Analogy
Engeneers are great at
matematics but not
that great at grammer
An automated spell
checker could correct
spelling and grammar
An instructor
can assess
whether or not
an idea is
journal-worthy
Introduction
29. http://www.engr.psu.edu/datalab/ 29
References• Lesniak, K., & Tucker, C. S. (2018). Dynamic Rendering of Remote Indoor Environments Using Real-Time Point Cloud
Data. ASME Journal of Computing and Information Science in Engineering, Accepted.
• Dering, M., Tucker, C. S., & Kumara, S. (2018). An Unsupervised Machine Learning Approach To Assessing Designer
Performance During Physical Prototyping. ASME Journal of Computing and Information Science in Engineering, DOI:
10.1115/1.4037434
• Dering, M., & Tucker, C. S. (2017). A Convolutional Neural Network Model for Predicting a Product’s Function, Given Its
Form. ASME Journal of Mechanical Design, DOI:10.1115/1.4037309
• Bezawada, S., Hu, Q., Gray, A., Brick, T., & Tucker, C. S. (2017). Automatic Facial Feature Extraction for Predicting
Designers’ Comfort with Engineering Equipment during Prototype Creation. ASME Journal of Mechanical Design, 139(2),
DOI:10.1115/1.4035428
• Lesniak, K., Tucker, C. S., Bilén, S.G., Terpenny, J., & Anumba, C. (2017). Immersive Distributed Design through Real Time
Capture, Translation and Rendering of 3D Mesh Data. ASME Journal of Computing and Information Science in
Engineering (JCISE), 17(3), DOI:10.1115/1.4035001 (The conference version of this paper won the Best Paper Award at
the 2016 ASME IDETC/CIE Conference under the Virtual Environments and Systems (VES) division)
• Dering, M. L., & Tucker, C. S. (2017, December). Generative adversarial networks for increasing the veracity of big data.
In Big Data (Big Data), 2017 IEEE International Conference on (pp. 2595-2602)
• Dering, M., & Tucker, C. S. (2017, June). Board # 146 Early Predicting of Student Struggles Using Body Language Paper.
2017 ASEE Annual Conference & Exposition
• Lopez, C., & Tucker, C. S. (2017, June). Board # 91 When to Provide Feedback? Exploring Human-Co-Robot Interactions in
Engineering Environments. 2017 ASEE Annual Conference & Exposition. Columbus, Ohio.
• Bharathi, A., & Tucker, C. S. (2015, August). Investigating the Impact of Interactive Immersive Virtual Reality
Environments in Enhancing Online Engineering Design Activities. Proceedings of the 2015 ASME IDETC/CIE, DETC 2015-
47388
• Dickens, B., Sellers, S., Harms, G., Startle, O., & Tucker, C. S. (2015, August). A Proposed Virtual Reality Approach for
Minimizing Information Loss in Multi-User, Scalable Environments. Proceedings of the 2015 ASME IDETC/CIE, DETC
2015-47414
Editor's Notes
Now the current space of virtual reality online learning experiences is pretty limited.
Globally digital world
Especially in virtual reality, it is quite difficult to track a user’s interest and engagement in the same effect as a regular classroom.
Start muttering. Ask = WHY did you ask that, then say Yes! That is exactly the problem we decided to try and solve.
Tell from example = information is lost, knowledge dissemination founded in Shannons information theory of communication
Talk a lot here on the roles of each of these positions. Mostly from section 3.
This study has aimed to get a better understanding of the information loss experienced in brick and mortar systems and to propose virtual reality solutions that help mitigate these limitations.
In order to achieve a scalable virtual reality environment, we have attempted to minimize information loss by examining Shannon’s information theory as shown above.
Our research focuses not necessarily on the encoding and decoding of information, but rather the channel through which the message is passed.
The channel determines how the information is passed between the source and receiver, and is often the root cause of information loss
Talk quietly here and be like “knowledge dissemination is rooted in shannons information theory in which information loss exists. (“speak up, why, because I cant hear you, EXACTLY”) You can tell from my example there that information was lost between us in knowledge dissemination. In a simple sense, <next slide>, I am the source, emitting an audial and visual output of my presence and my voice. <next slide> in our experiment we focused on an education simulation, so the source was a constant educator. <next slide>. And the receiver is you, receiving the information emitted from the source. <next slide> in our experiment we used a simulated student as our receivers, and the modeling is similar to this current room in that each receiver has a different amount of information loss based on where they are in the room. <next slide>