Unified framework for triaxial accelerometer-based fall event detection and classification using cumulants and hierarchical decision tree classifier

Healthcare Technology Letters

article

Satya Samyukta Kambhampati¹  Vishal Singh¹  M. Sabarimalai Manikandan¹  Barathram Ramkumar¹ 

[1] School of Electrical Sciences, Indian Institute of Technology Bhubaneswar

关键词: accelerometers;    acceleration measurement;    decision trees;    support vector machines;    signal classification;    medical signal processing;    feature extraction;    biomedical measurement;    body sensor networks;    triaxial accelerometer-based fall event detection;    hierarchical decision tree classifier;    cumulant extraction;    acceleration signals;    single waist-mounted triaxial accelerometer;    ACC signals;    fifth-order cumulants;    supports vector machine;    fall event classification algorithm;    human activity classification;    second-order cumulants;    naive Bayes;    multilayer perceptron;    SVM classifiers;    time-domain features;    third-order cumulants;    fourth-order cumulants;    optimal detection;    lowest false alarm rate;   

DOI  :  10.1049/htl.2015.0018

学科分类：肠胃与肝脏病学

来源: Wiley

【 摘 要 】

In this Letter, the authors present a unified framework for fall event detection and classification using the cumulants extracted from the acceleration (ACC) signals acquired using a single waist-mounted triaxial accelerometer. The main objective of this Letter is to find suitable representative cumulants and classifiers in effectively detecting and classifying different types of fall and non-fall events. It was discovered that the first level of the proposed hierarchical decision tree algorithm implements fall detection using fifth-order cumulants and support vector machine (SVM) classifier. In the second level, the fall event classification algorithm uses the fifth-order cumulants and SVM. Finally, human activity classification is performed using the second-order cumulants and SVM. The detection and classification results are compared with those of the decision tree, naive Bayes, multilayer perceptron and SVM classifiers with different types of time-domain features including the second-, third-, fourth- and fifth-order cumulants and the signal magnitude vector and signal magnitude area. The experimental results demonstrate that the second- and fifth-order cumulant features and SVM classifier can achieve optimal detection and classification rates of above 95%, as well as the lowest false alarm rate of 1.03%.

【 授权许可】

CC BY|CC BY-ND|CC BY-NC|CC BY-NC-ND