what is the best way to classify multivariate(5-10 features) time series data of variable length 50-100 into classes(10-20)

[aafaqin]

what is the best way to classify multivariate(5-10 features) time series data of variable length 50-100 into classes(10-20) example- https://keras.io/examples/timeseries/timeseries_classification_from_scratch/#introduction

but this is just a single feature classifier

[omrylcn]

hi aafaqin you can try some state of art time series classification algorihms like ROCKET, Those links can help your problem

• https://towardsdatascience.com/a-brief-introduction-to-time-series-classification-algorithms-7b4284d31b97
• https://pub.towardsai.net/rocket-fast-and-accurate-time-series-classification-f54923ad

[sachinprasadhs]

Hi @aafaqin ,

Could you please refer the above comment and also refer https://www.analyticsvidhya.com/blog/2020/10/multivariate-multi-step-time-series-forecasting-using-stacked-lstm-sequence-to-sequence-autoencoder-in-tensorflow-2-0-keras/ which could help you. Thanks!

[github-actions[bot]]

This issue is stale because it has been open for 14 days with no activity. It will be closed if no further activity occurs. Thank you.

[github-actions[bot]]

This issue was closed because it has been inactive for 28 days. Please reopen if you'd like to work on this further.