# Virtual LB 130th: Mel spectrogram feature + class balance simple solution

[https://www.kaggle.com/daisukelab/lanl-solution-by-mel-spectrogram-dataset-2](https://www.kaggle.com/daisukelab/lanl-solution-by-mel-spectrogram-dataset-2)
Sharing an approach which people might be interested.
Feature generation
Once converted into 62,900 mel-spectrogram data by fetching source 150,000 samples with sliding window.
fs=6MHz, step=40000/34, n_fft=40000 => mel-spectrogram data shape=[62900, 128, 128]
Convert mel-spectrogram data into 3 aggregated features: mean, std, trend like. => data shape=[62900, 384]
Balancing dataset
Apply stratified class balancing described in my kernel
[https://www.kaggle.com/daisukelab/balancing-dataset-while-earthquake-is-happening](https://www.kaggle.com/daisukelab/balancing-dataset-while-earthquake-is-happening)
By virtually handing dataset as labeled set.
Model
Simple LGBM.
Unfortunately I have deleted mel spectrogram dataset, I can post it upon your request later.