Your Body Defines Your Fall Detection System

A Somatotype-Based Feature Selection Method

Xiaoling Fu, Zheng Tan, Chungang Yan, Zhong Li, Cheng Wang, Cheng-Xiang Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Fall detection for the elderly is in great demand in order to mitigate the effect of falls. As fall detection system is a safety shield on which people's lives depend, high detection sensitivity is always the pursuit of fall detection system. Previous works prove that the sensitivity is correlated to the type of detection features. But generating personalized optimal detection features is difficult due to its high computation complexity. In this paper, we propose a somatotype-based feature selection method which can give user's optimal features without extra cost. Based on the finding that user's optimal detection features can be determined by their somatotype features (i.e., height and body mass index), we partition all users into different clusters according to their somatotype features and calculate the optimal features for each cluster. Several experiments prove that feature selection carried on somatotype based group can increase the detection accuracy effectively.

Original languageEnglish
Title of host publication2017 Fifth International Conference on Advanced Cloud and Big Data (CBD)
PublisherIEEE
Pages402-407
Number of pages6
ISBN (Electronic)9781538610725
DOIs
Publication statusPublished - 7 Sep 2017
Event5th International Conference on Advanced Cloud and Big Data - Shanghai, China
Duration: 13 Aug 201716 Aug 2017

Conference

Conference5th International Conference on Advanced Cloud and Big Data
Abbreviated titleCBD 2017
CountryChina
CityShanghai
Period13/08/1716/08/17

Fingerprint

Feature extraction
Costs
Experiments
Feature selection

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Information Systems and Management

Cite this

Fu, X., Tan, Z., Yan, C., Li, Z., Wang, C., & Wang, C-X. (2017). Your Body Defines Your Fall Detection System: A Somatotype-Based Feature Selection Method. In 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD) (pp. 402-407). IEEE. https://doi.org/10.1109/CBD.2017.76
Fu, Xiaoling ; Tan, Zheng ; Yan, Chungang ; Li, Zhong ; Wang, Cheng ; Wang, Cheng-Xiang. / Your Body Defines Your Fall Detection System : A Somatotype-Based Feature Selection Method. 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD). IEEE, 2017. pp. 402-407
@inproceedings{e73781a3da4041d4b0b1c4d2ab1e740b,
title = "Your Body Defines Your Fall Detection System: A Somatotype-Based Feature Selection Method",
abstract = "Fall detection for the elderly is in great demand in order to mitigate the effect of falls. As fall detection system is a safety shield on which people's lives depend, high detection sensitivity is always the pursuit of fall detection system. Previous works prove that the sensitivity is correlated to the type of detection features. But generating personalized optimal detection features is difficult due to its high computation complexity. In this paper, we propose a somatotype-based feature selection method which can give user's optimal features without extra cost. Based on the finding that user's optimal detection features can be determined by their somatotype features (i.e., height and body mass index), we partition all users into different clusters according to their somatotype features and calculate the optimal features for each cluster. Several experiments prove that feature selection carried on somatotype based group can increase the detection accuracy effectively.",
author = "Xiaoling Fu and Zheng Tan and Chungang Yan and Zhong Li and Cheng Wang and Cheng-Xiang Wang",
year = "2017",
month = "9",
day = "7",
doi = "10.1109/CBD.2017.76",
language = "English",
pages = "402--407",
booktitle = "2017 Fifth International Conference on Advanced Cloud and Big Data (CBD)",
publisher = "IEEE",
address = "United States",

}

Fu, X, Tan, Z, Yan, C, Li, Z, Wang, C & Wang, C-X 2017, Your Body Defines Your Fall Detection System: A Somatotype-Based Feature Selection Method. in 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD). IEEE, pp. 402-407, 5th International Conference on Advanced Cloud and Big Data, Shanghai, China, 13/08/17. https://doi.org/10.1109/CBD.2017.76

Your Body Defines Your Fall Detection System : A Somatotype-Based Feature Selection Method. / Fu, Xiaoling; Tan, Zheng; Yan, Chungang; Li, Zhong; Wang, Cheng; Wang, Cheng-Xiang.

2017 Fifth International Conference on Advanced Cloud and Big Data (CBD). IEEE, 2017. p. 402-407.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Your Body Defines Your Fall Detection System

T2 - A Somatotype-Based Feature Selection Method

AU - Fu, Xiaoling

AU - Tan, Zheng

AU - Yan, Chungang

AU - Li, Zhong

AU - Wang, Cheng

AU - Wang, Cheng-Xiang

PY - 2017/9/7

Y1 - 2017/9/7

N2 - Fall detection for the elderly is in great demand in order to mitigate the effect of falls. As fall detection system is a safety shield on which people's lives depend, high detection sensitivity is always the pursuit of fall detection system. Previous works prove that the sensitivity is correlated to the type of detection features. But generating personalized optimal detection features is difficult due to its high computation complexity. In this paper, we propose a somatotype-based feature selection method which can give user's optimal features without extra cost. Based on the finding that user's optimal detection features can be determined by their somatotype features (i.e., height and body mass index), we partition all users into different clusters according to their somatotype features and calculate the optimal features for each cluster. Several experiments prove that feature selection carried on somatotype based group can increase the detection accuracy effectively.

AB - Fall detection for the elderly is in great demand in order to mitigate the effect of falls. As fall detection system is a safety shield on which people's lives depend, high detection sensitivity is always the pursuit of fall detection system. Previous works prove that the sensitivity is correlated to the type of detection features. But generating personalized optimal detection features is difficult due to its high computation complexity. In this paper, we propose a somatotype-based feature selection method which can give user's optimal features without extra cost. Based on the finding that user's optimal detection features can be determined by their somatotype features (i.e., height and body mass index), we partition all users into different clusters according to their somatotype features and calculate the optimal features for each cluster. Several experiments prove that feature selection carried on somatotype based group can increase the detection accuracy effectively.

UR - http://www.scopus.com/inward/record.url?scp=85031729252&partnerID=8YFLogxK

U2 - 10.1109/CBD.2017.76

DO - 10.1109/CBD.2017.76

M3 - Conference contribution

SP - 402

EP - 407

BT - 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD)

PB - IEEE

ER -

Fu X, Tan Z, Yan C, Li Z, Wang C, Wang C-X. Your Body Defines Your Fall Detection System: A Somatotype-Based Feature Selection Method. In 2017 Fifth International Conference on Advanced Cloud and Big Data (CBD). IEEE. 2017. p. 402-407 https://doi.org/10.1109/CBD.2017.76