Human Activity Recognition Using Smartphones Data Set

In this deep learning project, you will build a classification system where to precisely identify human fitness activities.


Each project comes with 2-5 hours of micro-videos explaining the solution.

Code & Dataset

Get access to 50+ solved projects with iPython notebooks and datasets.

Project Experience

Add project experience to your Linkedin/Github profiles.

What will you learn

  • Understanding the problem statement

  • Initializing necessary libraries and understanding its use

  • Importing Dataset from amazon AWS and performing basic EDA

  • Why is it necessary for shuffling data

  • Performing basic encoding and transformation

  • Applying a supervised neural network using multi-layer perceptron

  • Using SGD, LBFGS and ADAM optimizer alternatively

  • Visualization using strip plot

  • Applying Logistic Regression

  • Standard Scaling and normalizing the dataset

  • Applying Random Forest Regressor as model

  • Applying Neural Networks using Keras and including Dropouts in between the layer

  • Understanding "Softmax", "Relu",and "Crossentropyloss"

  • Applying K-nearest neighbors and visualizing KNN distance and accuracy

  • Plotting graphs using Scatter Matrix

  • Applying Recursive Feature Elimination along with SVM

  • Plotting confusion matrix for visualizing the result

  • Visualizing the best model using matplotlib

  • Selecting the best model and making predictions using CSV format

Project Description

The Human Activity Recognition dataset was built from the recordings of 30 study participants performing activities of daily living (ADL) while carrying a waist-mounted smartphone with embedded inertial sensors. The objective is to classify activities into one of the six activities performed.Each person performed six activities (WALKING, WALKING_UPSTAIRS, WALKING_DOWNSTAIRS, SITTING, STANDING, LAYING) wearing a smartphone (Samsung Galaxy S II) on the waist. 

Using its embedded accelerometer and gyroscope, we captured 3-axial linear acceleration and 3-axial angular velocity at a constant rate of 50Hz. The experiments have been video-recorded to label the data manually. The obtained dataset has been randomly partitioned into two sets, where 70% of the volunteers were selected for generating the training data and 30% the test data.

Similar Projects

Big Data Project Machine Learning Project to Forecast Rossmann Store Sales
In this machine learning project you will work on creating a robust prediction model of Rossmann's daily sales using store, promotion, and competitor data.
Big Data Project Home Depot Product Search Relevance ML Project in Python
Given a customer's search query and the returned product in text format, your predictive model needs to tell whether it is what the customer was looking for.
Big Data Project Deep Learning Project on Store Item Demand Forecasting
In this project, we are going to predict item-level sales data using different forecasting techniques.
Big Data Project Build an Image Classifier for Plant Species Identification
In this machine learning project, we will use binary leaf images and extracted features, including shape, margin, and texture to accurately identify plant species using different benchmark classification techniques.

Curriculum For This Mini Project

  Problem Statement Overview
  Data Set Overview
  Shuffle the Data
  Separate Input/Ouput Labels
  Encoding Labels
  Classification Models
  Neural Network Model
  Graphical Representation of Data
  Logistic Regression
  Scalar VS PCA
  Transformation Function - TSNE
  Activation Functions
  Keras Neural Network
  Random Forest Classifier
  SGD Model
  K-Nearest Neighbour
  Support Vector Classification
  TensorFlow Model
  K-Neighbour Classifier
  Confusion Matrix
  Multiple Classifiers
  Grid Search