Does anyone has WaveformData data referred in the "Time Series Anomaly Detection Using Deep Learning" example?

This is the data I'm referring to:

https://in.mathworks.com/help/deeplearning/ug/time-series-anomaly-detection-using-deep-learning.html

Answer 1

[Cris LaPierre]

The data ships as part of the example. It can be obtained by running the first line of code in the linked example

load WaveformData

You may need to have the Deep Learning Toolbox installed to access it. You can check if you have it by running the following command in MATLAB

which WaveformData.mat

[S Baharath Sai]

Thanks much Cris, for your prompt reply. Appreciate if you could share the dataset here.

Since loading this example requires mulitple toolboxes.

[Maria Battle]

Agreed. Please make the dataset available outside of the Deep Learning toolbox. Thank you.

[Zhengling Li]

hello there,

i have installed r2023a version for mac, and still cannot load this waveformdata, (have already deep learning toolbox installed.) any help? thanks.

[Cris LaPierre]

Beginning in R2023a, the product documentation is no longer installed by default (see here). A side effect of this is that some example datasets are no longer installed by default. You can still access them by either installing the documentation, or by finding an example in the online documentation that uses that file, and then use the 'Open in MATLAB Online' or 'Copy Command' workflows to open that example (along with any associated data files) in your MATLAB instance.

The copy command the example above is openExample('nnet/TimeSeriesAnomalyDetectionUsingDeepLearningExample')

The file is downloaded to a local folder along with any necessary supporting files. If it is a file you use often, consider adding the example folder to your MATLAB Path.

[Zhengling Li]

thanks a lot for the infos, it works!

Answer 2

[Maria Battle]

If for some reason you don't have access to WaveformData, you might be able to create a dataset for yourself using a wave form generator. It's not necessarily elegant, but the below might get you started. Ref: https://www.mathworks.com/help/wlan/gs/waveform-generation.html

wave_out = cell(1);
for k = 1:5 % specify how many samples you want
    cfgHESU = wlanHESUConfig;
    bits = randi([0 1],1,4);
    osf = 2;
    
    waveformHESU = wlanWaveformGenerator(bits,cfgHESU, ...
        NumPackets=1,IdleTime=15e-6, ...
        OversamplingFactor=osf);
    
    fsHESU = wlanSampleRate(cfgHESU.ChannelBandwidth);
    time = (0:length(waveformHESU)-1)/fsHESU;
    wave_out{k} = [time; abs(waveformHESU')];
end

[S Baharath Sai]

Thank you, much :)

Answer 3

[Nikolaev]

wave_out = cell(1);

for k = 1:5 % specify how many samples you want

cfgHESU = wlanHESUConfig;

bits = randi([0 1],1,4);

osf = 2;

waveformHESU = wlanWaveformGenerator(bits,cfgHESU, ...

NumPackets=1,IdleTime=15e-6, ...

OversamplingFactor=osf);

fsHESU = wlanSampleRate(cfgHESU.ChannelBandwidth);

time = (0:length(waveformHESU)-1)/fsHESU;

wave_out{k} = [time; abs(waveformHESU')];

end

[Nikolaev]

Не понял

Вообще

[Nikolaev]

Пожалуйста расскажите мне

как это делать