Multiple comparator classifier framework for accelerometer-based fall detection and diagnostic

被引:82
作者
Gibson, Ryan M. [1 ]
Amira, Abbes [1 ,2 ]
Ramzan, Naeem [1 ]
Casaseca-de-la-Higuera, Pablo [1 ]
Pervez, Zeeshan [1 ]
机构
[1] Univ West Scotland, Paisley, Renfrew, Scotland
[2] Qatar Univ, Doha, Qatar
关键词
Fall detection; Fall diagnostic; Improved comparator classification; Multiple combined classifiers; Wearable health monitoring; POSTTRAUMATIC STRESS SYMPTOMS; RISK-FACTORS; HEALTH; INJURY; IMPLEMENTATION; DEATHS; SENSOR;
D O I
10.1016/j.asoc.2015.10.062
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
There are a significant number of high fall risk individuals who are susceptible to falling and sustaining severe injuries. An automatic fall detection and diagnostic system is critical for ensuring a quick response with effective medical aid based on relative information provided by the fall detection system. This article presents and evaluates an accelerometer-based multiple classifier fall detection and diagnostic system implemented on a single wearable Shimmer device for remote health monitoring. Various classifiers have been utilised within literature, however there is very little current work in combining classifiers to improve fall detection and diagnostic performance within accelerometer-based devices. The presented fall detection system utilises multiple classifiers with differing properties to significantly improve fall detection and diagnostic performance over any single classifier and majority voting system. Additionally, the presented multiple classifier system utilises comparator functions to ensure fall event consistency, where inconsistent events are outsourced to a supervisor classification function and discrimination power is considered where events with high discrimination power are evaluated to further improve the system response. The system demonstrated significant performance advantages in comparison to other classification methods, where the proposed system obtained over 99% metrics for fall detection recall, precision, accuracy and F-value responses. (C) 2015 Elsevier B.V. All rights reserved.
引用
收藏
页码:94 / 103
页数:10
相关论文
共 46 条
[1]  
Age UK, 2010, FALLS 65S COST NHS 4
[2]  
Alamgir H., 2011, OCCUP MED, P25
[3]   The implementation of an intelligent and video-based fall detection system using a neural network [J].
Alhimale, Laila ;
Zedan, Hussein ;
Al-Bayatti, Ali .
APPLIED SOFT COMPUTING, 2014, 18 :59-69
[4]  
Ashmead GG., 2014, POSTGRAD OBSTET GYNE, V34, P1, DOI 10.1097/01.PGO.0000451801.67742.a8
[5]  
Aslan M., 2015, APPL SOFT C IN PRESS
[6]   Early cognitive-behavioural therapy for post-traumatic stress symptoms after physical injury - Randomised controlled trial [J].
Bisson, JI ;
Shepherd, JP ;
Joy, D ;
Probert, R ;
Newcombe, RG .
BRITISH JOURNAL OF PSYCHIATRY, 2004, 184 :63-69
[7]  
Bulotta S., 2013, NEURAL NETS SURROUND, P81, DOI [10.1007/978-3-642-35467-0_9, DOI 10.1007/978-3-642-35467-0_9]
[8]   SHIMMER™ - A Wireless Sensor Platform for Noninvasive Biomedical Research [J].
Burns, Adrian ;
Greene, Barry R. ;
McGrath, Michael J. ;
O'Shea, Terrance J. ;
Kuris, Benjamin ;
Ayer, Steven M. ;
Stroiescu, Florin ;
Cionca, Victor .
IEEE SENSORS JOURNAL, 2010, 10 (09) :1527-1534
[9]  
Catal C., 2015, APPL SOFT C IN PRESS
[10]   Falls in workers during pregnancy: Risk factors, job hazards, and high risk occupations [J].
Dunning, K ;
LeMasters, G ;
Levin, L ;
Bhattacharya, A ;
Alterman, T ;
Lordo, K .
AMERICAN JOURNAL OF INDUSTRIAL MEDICINE, 2003, 44 (06) :664-672