A Hybrid Method to Predict Sports Related Concussions with ML

May 24, 07:00PM PDT(02:00AM GMT).
  • Virtual SF Bay ACM
  • Free 83 Attendees
This seminar is hosted by SF Bay ACM Chapter

Existing evidence in Sports Related Concussions(SRC) is insufficient to determine the best combination of measures in the use of evaluation tools. I will start to discuss existing three Machine learning methodes and SRC prediction rules.

Then I will describes a hybrid machine learning model based on the combination of human/knowledge based domains and computer generated feature rankings to improve accuracy of diagnosing SRC. Four feature selection criteria were constructed to create the optimal model, which was run on both Google AutoML and Random Forest for validation. The results show that the hybrid model has the best performance in predicting resolution time for 14-day and 28-day thresholds, along with outperforming previous published work. This research has significant impact in the use of domains and symptom ranking with machine learning to increase diagnosis accuracy. The hybrid model’s success in the use of domains to increase the efficiency of model training may have practical applications in real time situations.

Melody Yin

Melody is an 8th grade student at The Harker School. She enjoys learning about a wide range of STEM concepts, particularly computer science. She has 2 years of coding experience in Java and Python. Among her many interests are science bowl and reading.
The event ended.
Watch Recording
*Recordings hosted on Youtube, click the link will open the Youtube page.
Contact Organizer