This repository contains code related to my personal explorations of LSTM RNN's using Keras (TensorFlow backend) for the classification of activites from daily living (ADL) from accelerometer data.
The data is obtained from wearable accelerometer devices. This type of research is often referred to as Human Activity Recognition (HAR). Other machine learning methods have been shown to be quite effective, and serve as benchmarks for the RNN performance.
My main objective is to explore the process of refining an RNN architecture and tuning hyperparameters, as well as monitoring training and architecture improvements.
The dataset used can be found within the UCI Machine Learning Repository, titled Dataset for ADL Recognition with Wrist-worn Accelerometer Data Set (https://archive.ics.uci.edu/ml/datasets/Dataset+for+ADL+Recognition+with+Wrist-worn+Accelerometer)