Human Physical Activities Classification

What is it about?

This study concentrated on classifying six human physical activities sourced from the WiSDM dataset. Four distinct methods (Time Domain, Spectral Domain, Fractal dimension, and Haar Wavelet Transform) were employed to extract features from individual accelerometers after segmenting the signal of each activity through a sliding window. Subsequently, the features with the most significant impact were selected using gray wolf optimization for training the Multi-Class Support Vector Machines (MC-SVMs). The test outcomes revealed that the incorporation of Gray Wolf optimization with Multi-Class Support Vector Machines (MC-SVMs) enhanced the classification accuracy for the examined activities.

Featured Image

Why is it important?

The regular participation in the physical activities represents an essential part for the maintenance of fitness and good health. Regular physical activity can play an important role in the improvement of the cardio-vascular health, strengthening bones as well as muscles, enhancing flexibility, and promoting mental wellbeing. Exercising had proven its effectiveness in reducing chronic disease risk factors such as diabetes, obesity and heart diseases. The classification of the physical activities performed by humans is a process that includes the categorization and organization of different actions and movements performed by individuals on the basis of some certain characteristics and criteria. This process represents an essential part for many different applications, which include sciences, fitness tracking, health-care, exercising, robotics and bio-mechanics. The classification of physical activities, is important as it professionals and researchers in better understanding, analyzing, and tailoring the interventions or technologies to certain types of activities.