Giter VIP home page Giter VIP logo

human-activity-recognition's Introduction

Human Activity Recognition


INFO 7245- Big-Data-Systems-and-Intelligence-Analytics
Final Project

Problem Statement: Predict Human Activity and classify them into WALKING, WALKING UPSTAIRS, WALKING DOWNSTAIRS, SITTING, STANDING and LAYING

Dataset: Human Activity Recognition
7352 observations with 128 datapoints taken within 2.56 seconds with 50% carry forwarded in the training dataset. Each datapoint has 9 measurements for:
• Body Acceleration X axis
• Body Acceleration Y axis
• Body Acceleration Z axis
• Body Gyroscope X axis
• Body Gyroscope Y axis
• Body Gyroscope Z axis
• Total Acceleration X axis
• Total Acceleration Y axis
• Total Acceleration Z axis

Goal:
• Showcase that Standard Neural Networks shouldn’t be used to predict Sequential Classification Problem
• Implement Deep Neural Networks and prove it to be better than Standard Neural Network for Sequential Classification Problem

Steps Completed:
• Importing data
• Exploratory Data Analysis
• Implementing Machine Learning algorithms
>o Decision Tree
>o K Nearest Neighbors
>o SVC
>o Gaussian Naïve Bayes
>o Quadratic Discriminant Analysis
• Implementing Recurrent Neural Network (RNN) with keras
• Implementing Long-Short Term Memory (LSTM) with tensorflow
• Created Android App to track Human Activity using Accelerometer and Gyroscope sensors

Results:
LSTM has a better accuracy at predicting the human activity as compared to any machine learning algotihm or even RNN. RNN has 81.81% accuracy where as LSTM has 88.97% accuracy

Future Scope:
• Inclusion of third variable to improve prediction accuracy
• Android App enhancements with user better interface


For more details, please refer HumanActivityRecognition_Report

Project Website: https://krutsdeshpande.wixsite.com/bigdata-har

human-activity-recognition's People

Contributors

prithvikamath avatar

Watchers

James Cloos avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.