Human Activity Recognition Machine Learning and Tensorflow2.0 and Keras

This repository consist of code implementation for Human Activity Recognition using smart phone. We have implemented multi-class classification problem using both statistical and deep learning methods.
This project is to build a model that predicts the human activities such as Walking, Walking_Upstairs, Walking_Downstairs, Sitting, Standing or Laying.
This dataset is collected from 30 persons(referred as subjects in this dataset), performing different activities with a smartphone to their waists. The data is recorded with the help of sensors (accelerometer and Gyroscope) in that smartphone. This experiment was video recorded to label the data manually.

Library required for Machine Learning mapped solution

-numpy
-pandas
-matplotlib
-seaborn
-sklearn

Library required for Deep Learning mapped solution

-numpy
-pandas
-matplotlib
-tensorflow 2.0+
-sklearn

Dataset

Dataset for the same can be downloaded from the given link.
link - https://archive.ics.uci.edu/ml/datasets/human+activity+recognition+using+smartphones

Algorithm used in ML

-Logistic Regression
-Linear Support Vector Classifier
-Kernal Support Vector Classifier
-Decision Tree
-Random Forest
-Gradient Boosting Decision Tree

Algorithm used in DL

-Sequential LSTM Model

Author

Chirag Malaviya

Reference

Applied AI Case Study