• URL: https://www.projectpro.io/project-use-case/human-activity-recognition

Problem description

• Dataset that I will be using to solve this problem 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 (using the Samsung Galaxy S II device).

• Objective of this project is to classify activities into one of the six activities performed by the participants (WALKING, WALKING_UPSTAIRS, WALKING_DOWNSTAIRS, SITTING, STANDING, LAYING)

• Embedded accelerometer and gyroscope were used to collect the data. I've captured 3-axial linear acceleration and 3-axial angular velocity at a constant rate of 50Hz

• 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.

• The experiments have been video-recorded to label the data manually.

Problem description from data science perspective

Solution description