im-dpaul / Human-Activity-Recognition

Classification of Human Activities by reading the inertial sensors data collected using Smartphone.

Human Activity Recognition with Smartphones Data

Kaggle Machine Learning Project

The Human Activity Recognition database 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.

Kaggle Competition Link:

Human Activity Recognition with Smartphones

Answer : My Kaggle Notebook

Results of Model used in the Notebook

Logistic Regression:
Accuracy - 96.13%

Support Vector Classifier:
Accuracy - 96.50%

Decision Tree:
Accuracy - 85.68%

Random Forest:
Accuracy - 92.60%