Giter Site home page Giter Site logo

bhuvaneshravi / human-activity-recognition-pytorch Goto Github PK

View Code? Open in Web Editor NEW
0.0 1.0 0.0 677 KB

Recognise a human activity from a wide range of possiblities using a Deep Learning Neural Network

Jupyter Notebook 90.74% Python 9.26%
python3 pytorch recursive-neural-network feedforward-neural-network human-activity-recognition deep-learning

human-activity-recognition-pytorch's Introduction

Prediction model for human activity recognition

Recognise a human activity from a wide range of possiblities using a Deep Learning Neural Network

Goal:

To recognize variety and wide range of activities performed by humans, using data collected from a combination of sensors from smartphone and smartwatch devices.

Implementation:

Have implemented deep learning concepts and developed two models with Feed Forward Fully Connected Network and Recurrent Neural Network adaptive frameworks. Fuse the inputs from two sensors – accelerometer and gyroscope of smartphone and smartwatch, which is in turn feed in to train the models. Later we used cross visualization technique to evaluate the efficiency of the models

Accuracy and hyperparameters tuning:

Accuracy of FNN model - 56.22% of model accuracy by tuning with the below hyper parameters. Recurrent Cycle - 1 Neurons – 10 Epochs – 50 Learning Rate – 0.01

Model Performance and results:

Model Accuracy

Alt text

Model Loss

Alt text

Confusion Matrix FNN

Alt text

Confusion Matrix RNN

Alt text

Please refer to the research paper(unpublished) Heterogeneous Human Activity Recognition with Dynamic Sensor Fusion using Deep Learning Models.pdf for futher explanation.

Contributions:

  1. Bhuvaneshwaran Ravi
  2. Serlin Tamilselvam
  3. Jayashree Srinivasan

human-activity-recognition-pytorch's People

Contributors

bhuvaneshravi avatar

Watchers

 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.