A Gentle Introduction to a Standard Human Activity Recognition Problem

Last Updated on August 5, 2019

Human activity recognition is the problem of classifying sequences of accelerometer data recorded by specialized harnesses or smart phones into known well-defined movements.

It is a challenging problem given the large number of observations produced each second, the temporal nature of the observations, and the lack of a clear way to relate accelerometer data to known movements.

Classical approaches to the problem involve hand crafting features from the time series data based on fixed-size windows and training machine learning models, such as ensembles of decision trees. The difficulty is that this feature engineering requires deep expertise in the field.

Recently, deep learning methods such as recurrent neural networks and one-dimensional convolutional neural networks or CNNs have been shown to provide state-of-the-art results on challenging activity recognition tasks with little or no data feature engineering.

In this tutorial, you will discover a standard human activity recognition dataset for time series classification and how to explore the dataset prior to modeling.

After completing this tutorial, you will know:

• How to load and prepare human activity recognition time series classification data.
• How to explore and visualize time series classification data in order to generate ideas
  To finish reading, please visit source site