A Mobile Cloud Collaboration Fall Detection System Based on Ensemble Learning

TL;DR

This paper introduces a mobile cloud-based fall detection system utilizing an ensemble decision tree algorithm called FEDT, achieving high accuracy and reliability for practical fall detection scenarios.

Contribution

It proposes a novel ensemble learning algorithm FEDT for fall detection and a three-stage mobile cloud system integrating lightweight filtering, feature extraction, and cloud-based classification.

Findings

FEDT outperforms existing methods by 1-3% in sensitivity and specificity.

The system provides reliable fall detection in real-world scenarios.

The integrated system effectively combines mobile filtering with cloud-based analysis.

Abstract

Falls are one of the important causes of accidental or unintentional injury death worldwide. Therefore, this paper presents a reliable fall detection algorithm and a mobile cloud collaboration system for fall detection. The algorithm is an ensemble learning method based on decision tree, named Falldetection Ensemble Decision Tree (FEDT). The mobile cloud collaboration system can be divided into three stages: 1) mobile stage: use a light-weighted threshold method to filter out the activities of daily livings (ADLs), 2) collaboration stage: transmit data to cloud and meanwhile extract features in the cloud, 3) cloud stage: deploy the model trained by FEDT to give the final detection result with the extracted features. Experiments show that the performance of the proposed FEDT outperforms the others' over 1-3% both on sensitivity and specificity, and more importantly, the system can provide reliable fall detection in practical scenario.