Change point detection algorithms to assess pilot’s reactions to malfunctions

In this project the intern will work with time series data containing different parameters from a flight simulator. The intern will take these data and assess different learning as well as change point detection algorithms that can identify and segment pilot reactions to malfunctions and assign these reactions a proficiency metric. One of the possible approaches would be to assess the use of change point detection algorithms using a data driven approach. This will allow the partner organization to understand important segments of the flight data where large changes have taken place. These large changes will correspond to important pilot decisions of changing different flight parameters during different failures and would allow the partner organization to understand the appropriateness of such sequence of actions from data.

Faculty Supervisor:

Blake Richards

Student:

Raihan Seraj

Partner:

Paladin AI Inc

Discipline:

Engineering - computer / electrical

Sector:

Professional, scientific and technical services

University:

McGill University