science_cases:lmsu_science_case
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revision | |||
science_cases:lmsu_science_case [2022/09/12 12:27] – admin | science_cases:lmsu_science_case [2022/09/12 13:44] (current) – admin | ||
---|---|---|---|
Line 37: | Line 37: | ||
|4|Magnetosphere|14.1| | |4|Magnetosphere|14.1| | ||
- | The boundaries of critical interest - bow shock and magnetopause - are minorities with only 3.7 and 2.3 % representation. The table highlights the **data imbalance issue** that requires investigating special techniques to ensure the [[: | + | The boundaries of critical interest - bow shock and magnetopause - are minorities with only 3.7 and 2.3 % representation. The table highlights the **[[: |
As a first step in pre-processing, | As a first step in pre-processing, | ||
Line 43: | Line 43: | ||
In the feature preparation stage, a sliding window of variable sizes (3 seconds to 3 minutes) with a hop size of 1 second was computed on the time series signal to obtain [[: | In the feature preparation stage, a sliding window of variable sizes (3 seconds to 3 minutes) with a hop size of 1 second was computed on the time series signal to obtain [[: | ||
- | The windowed features are fed first into a block of 3 convolutional layers with 1D filters, each followed by [[: | + | The windowed features are fed first into a block of 3 [[: |
The window size used in these experiments is 30 seconds. Overall, the [[: | The window size used in these experiments is 30 seconds. Overall, the [[: |
science_cases/lmsu_science_case.txt · Last modified: 2022/09/12 13:44 by admin