Feature extraction from pilot-controller voice communication using machine learning
Air traffic control (ATC) communication is an important link between pilots and controllers. Often, ATC controllers experience immense pressure when the airspace sector they are handling becomes more complex. Miscommunication in ATC communication could lead to accidents, costing lives or damage to p...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Language: | English |
| Published: |
2019
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/77463 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Language: | English |
| Summary: | Air traffic control (ATC) communication is an important link between pilots and controllers. Often, ATC controllers experience immense pressure when the airspace sector they are handling becomes more complex. Miscommunication in ATC communication could lead to accidents, costing lives or damage to property. This project measured the influence of factors affecting an airport’s operational environment, such as weather and flight arrival sequence, on ATC communication between pilot and controllers. This project focused on developing a machine learning technique to identify active rate, an important feature in ATC communication which measures amount of communication for a period of time. With the help of data analysis, strong correlation was identified between flight trajectory data and active rate. It was determined that anomalous flight trajectories increased ATC communication by 28%. Henceforth, a machine learning prediction model was developed to identify anomalous flight trajectory in real-time, using which an increase in ATC communication can be predicted. |
|---|