{"id":9727,"date":"2018-05-18T09:00:50","date_gmt":"2018-05-18T13:00:50","guid":{"rendered":"https:\/\/blogs.mathworks.com\/pick\/?p=9727"},"modified":"2018-05-17T15:46:04","modified_gmt":"2018-05-17T19:46:04","slug":"wavelet-tech-talks-matlab-code-files","status":"publish","type":"post","link":"https:\/\/blogs.mathworks.com\/pick\/2018\/05\/18\/wavelet-tech-talks-matlab-code-files\/","title":{"rendered":"Wavelet Tech Talks – MATLAB Code Files"},"content":{"rendered":"
\n <\/p>\n

Sean<\/a>‘s pick this week is Wavelet Tech Talks – MATLAB Code Files<\/a> by Kirthi Devleker<\/a>.\n <\/p>\n

<\/introduction><\/p>\n

Ever wonder what a wavelet is or what the MathWorks’ “Wavelet Toolbox”<\/a> is actually useful for? Check out Kirthi’s videos<\/a> that describe the concept and uses for a wavelet.\n <\/p>\n

The files associated with the videos are hosted on the File Exchange so you can experiment with the code yourself. Kirthi also has a few other examples posted under his profile.\n <\/p>\n

Until a couple years ago I’d never known enough about wavelets for them to be useful. Recently, I’ve found uses for them in machine learning. The two uses I’ve had are to generate features for a traditional machine learning algorithm and to transform a one-dimensional signal into a two-dimensional time-frequency using the continuous wavelet transform<\/a>. Doing this transformation opens up the whole world of deep learning<\/a> to signal data as the signal is now represented as an image.\n <\/p>\n

There have been a few other recent improvements to the Wavelet Toolbox to make using it easier as well. Specifically adding apps:\n <\/p>\n

\n
    \n
  • Wavelet Signal Denoiser<\/a> to filter difficult signals.\n <\/li>\n
  • Signal Analyzer<\/a> having scalogram for easy time-frequency visualization.\n <\/li>\n<\/ul><\/div>\n

    Comments<\/a><\/h3>\n

    Have you had a use for wavelets or a difficult signal to process?<\/p>\n

    Give it a try and let us know what you think here<\/a> or leave a comment<\/a> for Kirthi.\n <\/p>\n