Icon

Multivariate_​Time_​Series_​RNN_​Keras_​Deployment

Multivariate Time Series Analysis with an RNN - Deployment

This is a simple example workflow for the deployment of a multivariant time series, LSTM based, recurrent neural network.

It is based on the bike demand predition dataset from Kaggle and uses the trained model to predict the demand in the next hour based on the demand and the other features in the last 10 hours.



Read and preprocess new data Apply the deep learning model topredict the demand in the next hour Denormalize and round thepredicted value Read the trained deep learning model and the normalization model Read trainednetworkRead normalizer modelDay of monthDay of weekMonth HourRead new data Keras NetworkReader Model Reader Extract Date Fields Restructure Data Normalizer (Apply) Keras NetworkExecutor CSV Reader Denomrmalize Predictionsand Round to Int Read and preprocess new data Apply the deep learning model topredict the demand in the next hour Denormalize and round thepredicted value Read the trained deep learning model and the normalization model Read trainednetworkRead normalizer modelDay of monthDay of weekMonth HourRead new dataKeras NetworkReader Model Reader Extract Date Fields Restructure Data Normalizer (Apply) Keras NetworkExecutor CSV Reader Denomrmalize Predictionsand Round to Int

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: kathrinmelcher
Created at: 2020-10-13
On NodePit since: 2021-01-27
Last update: 2024-12-21
Created with KNIME version: v4.3.0
Tags: time seriesdeep learningRNNLSTMmultivariate time seriesmanufacturing

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!