{ "id": 250130, "title": "From waves📈 to images🖼️", "url": "/competitions/g2net-gravitational-wave-detection/discussion/250130", "author_name": "", "post_date": "2021-07-01T09:12:04.480589800Z", "votes": 21, "comment_count": 2, "views": 0, "content": "

Overview

\n

I show how to transform input signals to image representation in my notebook https://www.kaggle.com/ihelon/g2net-eda-and-modeling. It allows using nice pre-trained models for image processing tasks.

\n

Description

\n

We can transform 3 different signals into 3 different representations such as Spectrogram or
\nMel-frequency cepstral coefficients (MFCCs) or other signal representations.
\nAfter transformations you can combine three results into one image and use ConvModels with these data.

\n

Example

\n

Input signals:

\n

\"\"

\n

Spectograms:

\n

\"\"

\n

MFCC:

\n

\"\"

", "messages": [ { "id": "1371833", "postDate": "07/01/2021 09:12:04", "content": "

Overview

\n

I show how to transform input signals to image representation in my notebook https://www.kaggle.com/ihelon/g2net-eda-and-modeling. It allows using nice pre-trained models for image processing tasks.

\n

Description

\n

We can transform 3 different signals into 3 different representations such as Spectrogram or
\nMel-frequency cepstral coefficients (MFCCs) or other signal representations.
\nAfter transformations you can combine three results into one image and use ConvModels with these data.

\n

Example

\n

Input signals:

\n

\"\"

\n

Spectograms:

\n

\"\"

\n

MFCC:

\n

\"\"

", "rawMarkdown": "### Overview\nI show how to transform input signals to image representation in my notebook https://www.kaggle.com/ihelon/g2net-eda-and-modeling. It allows using nice pre-trained models for image processing tasks.\n### Description\nWe can transform 3 different signals into 3 different representations such as [Spectrogram](https://en.wikipedia.org/wiki/Spectrogram) or \n[Mel-frequency cepstral coefficients (MFCCs)](https://en.wikipedia.org/wiki/Mel-frequency_cepstrum) or other signal representations.\nAfter transformations you can combine three results into one image and use ConvModels with these data. \n### Example\n#### Input signals:\n![](https://i.imgur.com/FWSV1E2.png)\n#### Spectograms:\n![](https://i.imgur.com/jpLyWES.png)\n#### MFCC:\n![](https://i.imgur.com/QpsE3jN.png)", "votes": null }, { "id": "1372465", "postDate": "07/01/2021 18:12:09", "content": "

This looks like a lot of the work was produced in Matlab https://www.mathworks.com/matlabcentral/fileexchange/65789-gravitational-wave-signal-analysis-based-on-synchroextracting-transform-set?s_tid=srchtitle

", "rawMarkdown": "This looks like a lot of the work was produced in Matlab https://www.mathworks.com/matlabcentral/fileexchange/65789-gravitational-wave-signal-analysis-based-on-synchroextracting-transform-set?s_tid=srchtitle", "votes": null }, { "id": "1561307", "postDate": "10/27/2021 13:13:46", "content": "

Hey,

\n

Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.

\n

Thank you all,

\n

Regards,
\nChris

", "rawMarkdown": "Hey,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris", "votes": null } ], "comments": [ { "id": 1372465, "author_name": "captbullett", "author_url": "", "post_date": "07/01/2021 18:12:09", "content": "

This looks like a lot of the work was produced in Matlab https://www.mathworks.com/matlabcentral/fileexchange/65789-gravitational-wave-signal-analysis-based-on-synchroextracting-transform-set?s_tid=srchtitle

", "votes": null, "replies": [] }, { "id": 1561307, "author_name": "zerafachris", "author_url": "", "post_date": "10/27/2021 13:13:46", "content": "

Hey,

\n

Thank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.

\n

Thank you all,

\n

Regards,
\nChris

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1371833": "### Overview\nI show how to transform input signals to image representation in my notebook https://www.kaggle.com/ihelon/g2net-eda-and-modeling. It allows using nice pre-trained models for image processing tasks.\n### Description\nWe can transform 3 different signals into 3 different representations such as [Spectrogram](https://en.wikipedia.org/wiki/Spectrogram) or \n[Mel-frequency cepstral coefficients (MFCCs)](https://en.wikipedia.org/wiki/Mel-frequency_cepstrum) or other signal representations.\nAfter transformations you can combine three results into one image and use ConvModels with these data. \n### Example\n#### Input signals:\n![](https://i.imgur.com/FWSV1E2.png)\n#### Spectograms:\n![](https://i.imgur.com/jpLyWES.png)\n#### MFCC:\n![](https://i.imgur.com/QpsE3jN.png)", "1372465": "This looks like a lot of the work was produced in Matlab https://www.mathworks.com/matlabcentral/fileexchange/65789-gravitational-wave-signal-analysis-based-on-synchroextracting-transform-set?s_tid=srchtitle", "1561307": "Hey,\n\nThank you all for taking part in our competition. The participation has been overwhelmingly positive. We are currently conducting a survey to gauge the demographic and outreach achieved. Kindly spare 2min and fill in this survey https://forms.gle/QP9L16niPexozyhu5.\n\nThank you all,\n\nRegards,\nChris" }, "source": "meta" }