Related Experiment Video
Updated: May 10, 2026

Design and Analysis for Fall Detection System Simplification
Published on: April 6, 2020
Unsupervised abnormal human behaviour detection using acceleration data
Juan Luis Carús1, Víctor Peláez, Gloria López
1Fundación CTIC-Centro Tecnológico, Gijón, Asturias, Spain.
Abstract:
Abnormal human behavior detection under free-living conditions is a reliable technique to detect activity disorders and diseases. This work proposes an acceleration-based algorithm to detect abnormal behavior as an abnormal increase or decrease in physical activity (PA). The algorithm is based on statistical features of human physical activity. Using a period of observed physical activity as a reference, the algorithm is able to detect abnormal behavior in other periods of time. The approach is unsupervised as the modeling of the reference behavior is not required. It has been validated with a group of 12 users under free-living conditions for two days. Results show a precision greater than 75% and a recall of 92%.
Related Concept Videos
Relative Motion Analysis - Acceleration
Relative Motion Analysis using Rotating Axes - Acceleration
Time differentiation is...
Average Acceleration
Measuring Acceleration Due to Gravity
A simple pendulum can be described as a point mass and a string. Meanwhile, a physical pendulum is any object whose oscillations are similar to a simple pendulum, but cannot be modeled as a point mass on a string because its mass is distributed over a larger area. The behavior of a physical pendulum can be modeled using the principles of...
