Recognizing Human Activity Using Smartphones

1. Aim

The purpose of this project is to use the dataset provided at UCI ML Repository for detecting regular human activities. This dataset has been prepared from the recordings of 30 subjects performing activities of daily living (ADL) while carrying a waist-mounted smartphone with embedded inertial sensors.

2. Description of Dataset

Each record in the dataset has the following:

• A 561-feature vector with frequency and time variables.
• The corresponding activity label.
• Triaxial acceleration from the accelerometer.
• Triaxial Angular velocity from the gyroscope.
• Identifier of subject on whom experiment was done.

3. Proposed Solution

The python code contains the implementation of SVM for preparing a learning model having an accuracy of approximately 91%.

4. Libraries/Language

• Python 3.x
• Numpy, Scipy, Pandas