[FEAT] Add data processing script for dataset B (outside training data) #37

Open
opened 2025-03-16 13:35:21 +00:00 by nuluh · 0 comments
nuluh commented 2025-03-16 13:35:21 +00:00 (Migrated from github.com)

Problem Statement

The model achieve above 90% accuracy for all algorithm might be due to train test under same data. There should be tested using another data outside its training data.

Proposed Solution

  1. Modify existing process_stft.py to be more flexible by make the script able to be executed directly with several arguments using sys.argv() instead of hard coding it for each different dataset.
  2. Modify existing process_stft.py to adapt new model scheme with 6 damage scenarios instead of 4

Alternatives Considered

No response

Component

Data Processing

Priority

Critical (blocks progress)

Implementation Ideas

No response

Expected Benefits

This will give flexibility and ensure the model is indeed making correct prediction

Additional Context

No response

### Problem Statement The model achieve above 90% accuracy for all algorithm might be due to train test under same data. There should be tested using another data outside its training data. ### Proposed Solution 1. Modify existing `process_stft.py` to be more flexible by make the script able to be executed directly with several arguments using `sys.argv()` instead of hard coding it for each different dataset. 2. Modify existing `process_stft.py` to adapt new model scheme with 6 damage scenarios instead of 4 ### Alternatives Considered _No response_ ### Component Data Processing ### Priority Critical (blocks progress) ### Implementation Ideas _No response_ ### Expected Benefits This will give flexibility and ensure the model is indeed making correct prediction ### Additional Context _No response_
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: nuluh/thesis#37