Git Product home page Git Product logo

deep-learning_human-activity-recognition's Introduction

Human Activity Recognition

Paper : Paper_Human Activity Recognition

Results:

  1. Data Preprocessing
  2. Input Pipeline
  3. Model architecture
  4. Metrics
    • Confusion Matrix
    • ROC AUC Curve
  5. Hyperparamter Optimization
    • Neurons in LSTM layer
    • Optimizer
    • Dropout rate

Results obtained so far:

Accuracy Test Data Set : 77.23 %

1. Training Data Visualization

Acc_TrainData

Gyro_TrainData

2. Test Data Visualization

Acc_TestData Gyro_TestData

3. Posture Data Visualization

WALKING

acceleration signals of experiment 1 when user 1 was performing activity_ 1(WALKING)

gyroscope signals of experiment 1 when user 1 was performing activity_ 1(WALKING)

WALKING_UPSTAIRS

gyroscope signals of experiment 1 when user 1 was performing activity_ 2(WALKING_UPSTAIRS)

acceleration signals of experiment 1 when user 1 was performing activity_ 2(WALKING_UPSTAIRS)

WALKING_DOWNSTAIRS

acceleration signals of experiment 1 when user 1 was performing activity_ 3(WALKING_DOWNSTAIRS)

gyroscope signals of experiment 1 when user 1 was performing activity_ 3(WALKING_DOWNSTAIRS)

SITTING

acceleration signals of experiment 1 when user 1 was performing activity_ 4(SITTING)

gyroscope signals of experiment 1 when user 1 was performing activity_ 4(SITTING)

STANDING

acceleration signals of experiment 1 when user 1 was performing activity_ 5(STANDING)

gyroscope signals of experiment 1 when user 1 was performing activity_ 5(STANDING)

LAYING

acceleration signals of experiment 1 when user 1 was performing activity_ 6(LAYING)

gyroscope signals of experiment 1 when user 1 was performing activity_ 6(LAYING)

STAND_TO_SIT

acceleration signals of experiment 1 when user 1 was performing activity_ 7(STAND_TO_SIT)

gyroscope signals of experiment 1 when user 1 was performing activity_ 7(STAND_TO_SIT)

SIT_TO_STAND

acceleration signals of experiment 1 when user 1 was performing activity_ 8(SIT_TO_STAND)

gyroscope signals of experiment 1 when user 1 was performing activity_ 8(SIT_TO_STAND)

SIT_TO_LIE

acceleration signals of experiment 1 when user 1 was performing activity_ 9(SIT_TO_LIE)

gyroscope signals of experiment 1 when user 1 was performing activity_ 9(SIT_TO_LIE)

LIE_TO_SIT

acceleration signals of experiment 1 when user 1 was performing activity_ 10(LIE_TO_SIT)

gyroscope signals of experiment 1 when user 1 was performing activity_ 10(LIE_TO_SIT)

STAND_TO_LIE

acceleration signals of experiment 1 when user 1 was performing activity_ 11(STAND_TO_LIE)

gyroscope signals of experiment 1 when user 1 was performing activity_ 11(STAND_TO_LIE)

LIE_TO_STAND

acceleration signals of experiment 1 when user 1 was performing activity_ 12(LIE_TO_STAND)

gyroscope signals of experiment 1 when user 1 was performing activity_ 12(LIE_TO_STAND)

4. Histogram: Training Examples per Activity

5. Metrics

Metrics_HAR

6. Confusion Matrix

Confusion matrix

7. ROC-AUC Curve

deep-learning_human-activity-recognition's People

Contributors

bkaiwalya 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.