S1 Analysis - misantamaria/deepvats-foundation GitHub Wiki

Analysis of S1

S1 description

s1_segments S1 is a synthetic dataset created through https://github.com/misantamaria/deepvats-foundation/blob/master/nbs/_synthetic_data.ipynb to analyze the power of the embeding space to show time series segments. As the image above show, it is defined to have four clearly defined segments:

Segment Start date End date Days Hours Minutes Timestamps
$df_1$ 2022-03-01 00:00 2022-03-08 11:59 7.5 180 10800 540
$df_2$ 2022-03-08 12:00 2022-03-14 23:59 6.5 156 9360 465
$df_3$ 2022-03-15 00:00 2022-03-24 23:59 10 240 1440 720
$df_4$ 2022-03-25 00:00 2022-03-28 23:59 4 96 57600 288
Complete 2022-03-01 00:00 2022-03-28 23:59 28 672 40320 2013

In the original analysis, the masked autoencoder architecture showed a great performance on detecting all the segments showin gthe changepoints as extreme points in the clusters joining three big clusters between them: image

This experimentation was done using, in inference, a window size w = 54, stride s = 2 and UMAP as algorithm to project the embeddings. As our previous scalability and stability analysis showed, it is a better option using UMAP followed by PCA in their GPU version. Thus, to test MOMENT on the detection of the segments of S1 we use w = 54, s = 2 and PCA followed by UMAP.

Paper experimentation

This are the images for S1 for MOMENT used for the research paper without the preprocessing.

MOMENT-small

Global view

ratio_1 ratio_02 1 2 3 4 5

Zero-shot

Cluster 1

1 2 3 5

Cluster 2

1 2

Cluster 3

ratio_1 ratio_02 1 2 3 4

Cluster 4

g2 etsisi upm es_8868_ (31) g2 etsisi upm es_8868_ (32) g2 etsisi upm es_8868_ (33) g2 etsisi upm es_8868_ (34) g2 etsisi upm es_8868_ (35) g2 etsisi upm es_8868_ (36) g2 etsisi upm es_8868_ (37) g2 etsisi upm es_8868_ (38)

Cluster 5

g2 etsisi upm es_8868_ (31) g2 etsisi upm es_8868_ (32) g2 etsisi upm es_8868_ (33) g2 etsisi upm es_8868_ (34) g2 etsisi upm es_8868_ (35) g2 etsisi upm es_8868_ (36) g2 etsisi upm es_8868_ (37) g2 etsisi upm es_8868_ (38) g2 etsisi upm es_8868_ (39)

The rest of images are saved at paper_imgs folder.

⚠️ **GitHub.com Fallback** ⚠️