Related Experiment Video
Updated: May 2, 2026
16:14
Trajectory Data Analyses for Pedestrian Space-time Activity Study
Published on: February 25, 2013
13.5K
Enhancing Activity Recognition using CPD-based Activity Segmentation
Samaneh Aminikhanghahi1, Diane J Cook1
1School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA.
Pervasive and Mobile Computing
|February 3, 2025
Summary
This study introduces a new change point detection model to segment sensor data, improving human activity recognition accuracy by over 1% in real-time smart home applications. The method effectively identifies activity boundaries and transitions for better health monitoring and security insights.
Area of Science:
- Computer Science
- Artificial Intelligence
- Machine Learning
Background:
- Accurate human activity recognition from sensor data is crucial for applications like health monitoring and security.
- Effective segmentation of behavior-based sensor data is a prerequisite for reliable activity recognition.
Purpose of the Study:
- To enhance human activity recognition by accurately identifying activity borders and transitions.
- To develop a real-time activity segmentation model using change point detection.
Main Methods:
- A novel change point detection-based model was developed for segmenting behavior-driven sensor data.
- The proposed method was evaluated using sensor data collected from 29 smart home environments.
Main Results:
- The model successfully segments sensor data, providing insights into activity boundaries and transitions.
- The real-time segmentation approach improved the average accuracy of human activity recognition by over 1%.
Conclusions:
- The proposed change point detection-based activity segmentation method enhances the performance of human activity recognition.
- This approach offers a valuable tool for real-time analysis in smart home applications, improving monitoring and intervention capabilities.
More Related Videos
Related Concept Videos
01:06Fixed Action Patterns
16.0K
A fixed action pattern (FAP) is a specific, hard-wired sequence of behaviors that occurs in response to an external stimulus, called a sign stimulus. The behavior is “fixed” because it is essentially unchangeable—proceeding similarly across individuals of a species every time it occurs.
16.0K
01:20¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)
1.3K
When proton-coupled carbon-13 spectra are simplified by a broadband proton decoupling technique, structural information about the coupled protons is lost. Distortionless enhancement by polarization transfer (DEPT) is a technique that provides information on the number of hydrogens attached to each carbon in a molecule. While the DEPT experiment utilizes complex pulse sequences, the pulse delay and flip angle are specifically manipulated. The resulting signals have different phases depending on...
1.3K
01:22Force Classification
2.8K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
2.8K