Lopez, C. E., & Tucker, C. (2018, April), Towards Personalized Performance Feedback: Mining the Dynamics of Facial Keypoint Data in Engineering Lab Environments  Paper presented at 2018 ASEE Mid-Atlantic Section Spring Conference, Washington, District of Columbia. 10.18260/1-2--29500

\bibitem{asee_peer_29500}
  Lopez, C. E., \& Tucker, C. (2018, April), \emph{Towards Personalized Performance Feedback: Mining the Dynamics of Facial Keypoint Data in Engineering Lab Environments}
  Paper presented at 2018 ASEE Mid-Atlantic Section Spring Conference, Washington, District of Columbia.
  10.18260/1-2--29500

Christian Enmanuel Lopez and Conrad Tucker.  "Towards Personalized Performance Feedback: Mining the Dynamics of Facial Keypoint Data in Engineering Lab Environments".  2018 ASEE Mid-Atlantic Section Spring Conference, Washington, District of Columbia, 2018, April.  ASEE Conferences, 2018.  https://peer.asee.org/29500 Internet.  12 Dec, 2024

\bibitem{asee_peer_29500}
  Christian Enmanuel Lopez and Conrad Tucker.
  "Towards Personalized Performance Feedback: Mining the Dynamics of Facial Keypoint Data in Engineering Lab Environments".
  \emph{2018 ASEE Mid-Atlantic Section Spring Conference, Washington, District of Columbia, 2018, April}.
  ASEE Conferences, 2018.
  https://peer.asee.org/29500 Internet.  12 Dec, 2024

@INPROCEEDINGS{asee_peer_29500
author = "Christian Enmanuel Lopez and Conrad Tucker"
title = "Towards Personalized Performance Feedback: Mining the Dynamics of Facial Keypoint Data in Engineering Lab Environments"
booktitle = "2018 ASEE Mid-Atlantic Section Spring Conference"
year = "2018"
month = "April"
address = "Washington, District of Columbia"
publisher = "ASEE Conferences"
note = {https://peer.asee.org/29500}
number = {10.18260/1-2--29500}
}

TY  - CPAPER
AB  - According to the National Academy of Engineering, the development of personalized learning is one of the grand engineering challenges of the 21st century1. Even though affect-sensitive systems have been used for personalized learning, current systems provide feedback based on predefined relations of affective state and performance. However, studies have shown that the affective state that correlates to good performance could vary between tasks and students. Hence, these systems can only provide accurate performance feedback once the student completed the task at hand. In light of the current methods’ limitation, this work presents a machine learning method for predicting students’ performance by using the dynamics of their facial keypoint data captured while reading the instructions of a task, thus, avoiding the need to infer their affective state. A case study involving 40 students performing tasks in an engineering lab environment is used to validate the proposed method. The results reveal that the proposed model yielded an accuracy of 80%. The results indicate the importance of using students’ facial keypoint data captured while reading the instructions of a task, to predict their performance. This method could be implemented in engineering lab environments to provide real-time feedback to students and advance personalized learning.
AU  - Christian Enmanuel Lopez
AU  - Conrad Tucker
CY  - Washington, District of Columbia
DA  - 2018/04/06
PB  - ASEE Conferences
TI  - Towards Personalized Performance Feedback: Mining the Dynamics of Facial Keypoint Data in Engineering Lab Environments
UR  - https://peer.asee.org/29500
DO  - 10.18260/1-2--29500
ER  -