Adaptive time method for fall detection in elderly

Safa Hussein Mohammed; Yangyu Fan; Guoyun Lv; Shiya Liu

doi:10.1109/ICRAIE59459.2023.10468387

Adaptive time method for fall detection in elderly

Safa Hussein Mohammed
, Yangyu Fan
, Guoyun Lv
, Shiya Liu

School of Electronics and Information

Northwestern Polytechnical University Xian
Content Production Center of Virtual Reality

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Falls are the largest risk to the health of elderly people. Different researchers have studied threshold algorithms and machine learning for fall detection; however, these methods do not efficiently detect the possibility of falls in the elderly. Recently, sensors have been developed that can observe human joints to determine how prone a person is to fall. However, the use of a single sensor exhibits several drawbacks such as low accuracy, limited information, and a high false alarm rate. Therefore, multiple sensors at the waist, thigh, and ankle were the most comfortable positions for elderly people wearing sensors. In this paper, a hybrid approach to dimension reduction and discrete wavelet transform (DWT) is proposed to extract features from the dataset. A unique approach employing k Nearest Neighbor (KNN) and Support Vector Machine (SVM) was investigated to accurately detect if a person is prone to fall or not. The results after comparative analysis with current methods show a significant increase in accuracy of 94%.

Original language	English
Title of host publication	8th International Conference on Recent Advances and Innovations in Engineering
Subtitle of host publication	Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350315516
DOIs	https://doi.org/10.1109/ICRAIE59459.2023.10468387
State	Published - 2023
Event	8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023 - Kuala Lumpur, Malaysia Duration: 2 Dec 2023 → 3 Dec 2023

Publication series

Name	8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023

Conference

Conference	8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023
Country/Territory	Malaysia
City	Kuala Lumpur
Period	2/12/23 → 3/12/23

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

discrete wavelet transform (DWT)
IMU sensor
Principal Component Analysis (PCA)
support vector machine

Access to Document

10.1109/ICRAIE59459.2023.10468387

Cite this

Mohammed, S. H., Fan, Y., Lv, G., & Liu, S. (2023). Adaptive time method for fall detection in elderly. In 8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023 (8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICRAIE59459.2023.10468387

Mohammed, Safa Hussein ; Fan, Yangyu ; Lv, Guoyun et al. / Adaptive time method for fall detection in elderly. 8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023).

@inproceedings{aeb139598ce941318f327da916d3a00b,

title = "Adaptive time method for fall detection in elderly",

abstract = "Falls are the largest risk to the health of elderly people. Different researchers have studied threshold algorithms and machine learning for fall detection; however, these methods do not efficiently detect the possibility of falls in the elderly. Recently, sensors have been developed that can observe human joints to determine how prone a person is to fall. However, the use of a single sensor exhibits several drawbacks such as low accuracy, limited information, and a high false alarm rate. Therefore, multiple sensors at the waist, thigh, and ankle were the most comfortable positions for elderly people wearing sensors. In this paper, a hybrid approach to dimension reduction and discrete wavelet transform (DWT) is proposed to extract features from the dataset. A unique approach employing k Nearest Neighbor (KNN) and Support Vector Machine (SVM) was investigated to accurately detect if a person is prone to fall or not. The results after comparative analysis with current methods show a significant increase in accuracy of 94\%.",

keywords = "discrete wavelet transform (DWT), IMU sensor, Principal Component Analysis (PCA), support vector machine",

author = "Mohammed, \{Safa Hussein\} and Yangyu Fan and Guoyun Lv and Shiya Liu",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023 ; Conference date: 02-12-2023 Through 03-12-2023",

year = "2023",

doi = "10.1109/ICRAIE59459.2023.10468387",

language = "英语",

series = "8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "8th International Conference on Recent Advances and Innovations in Engineering",

}

Mohammed, SH, Fan, Y, Lv, G & Liu, S 2023, Adaptive time method for fall detection in elderly. in 8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023. 8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023, Institute of Electrical and Electronics Engineers Inc., 8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023, Kuala Lumpur, Malaysia, 2/12/23. https://doi.org/10.1109/ICRAIE59459.2023.10468387

Adaptive time method for fall detection in elderly. / Mohammed, Safa Hussein; Fan, Yangyu; Lv, Guoyun et al.
8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Adaptive time method for fall detection in elderly

AU - Mohammed, Safa Hussein

AU - Fan, Yangyu

AU - Lv, Guoyun

AU - Liu, Shiya

PY - 2023

Y1 - 2023

N2 - Falls are the largest risk to the health of elderly people. Different researchers have studied threshold algorithms and machine learning for fall detection; however, these methods do not efficiently detect the possibility of falls in the elderly. Recently, sensors have been developed that can observe human joints to determine how prone a person is to fall. However, the use of a single sensor exhibits several drawbacks such as low accuracy, limited information, and a high false alarm rate. Therefore, multiple sensors at the waist, thigh, and ankle were the most comfortable positions for elderly people wearing sensors. In this paper, a hybrid approach to dimension reduction and discrete wavelet transform (DWT) is proposed to extract features from the dataset. A unique approach employing k Nearest Neighbor (KNN) and Support Vector Machine (SVM) was investigated to accurately detect if a person is prone to fall or not. The results after comparative analysis with current methods show a significant increase in accuracy of 94%.

AB - Falls are the largest risk to the health of elderly people. Different researchers have studied threshold algorithms and machine learning for fall detection; however, these methods do not efficiently detect the possibility of falls in the elderly. Recently, sensors have been developed that can observe human joints to determine how prone a person is to fall. However, the use of a single sensor exhibits several drawbacks such as low accuracy, limited information, and a high false alarm rate. Therefore, multiple sensors at the waist, thigh, and ankle were the most comfortable positions for elderly people wearing sensors. In this paper, a hybrid approach to dimension reduction and discrete wavelet transform (DWT) is proposed to extract features from the dataset. A unique approach employing k Nearest Neighbor (KNN) and Support Vector Machine (SVM) was investigated to accurately detect if a person is prone to fall or not. The results after comparative analysis with current methods show a significant increase in accuracy of 94%.

KW - discrete wavelet transform (DWT)

KW - IMU sensor

KW - Principal Component Analysis (PCA)

KW - support vector machine

UR - https://www.scopus.com/pages/publications/85189944254

U2 - 10.1109/ICRAIE59459.2023.10468387

DO - 10.1109/ICRAIE59459.2023.10468387

M3 - 会议稿件

AN - SCOPUS:85189944254

T3 - 8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023

BT - 8th International Conference on Recent Advances and Innovations in Engineering

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2023

Y2 - 2 December 2023 through 3 December 2023

ER -

Mohammed SH, Fan Y, Lv G, Liu S. Adaptive time method for fall detection in elderly. In 8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (8th International Conference on Recent Advances and Innovations in Engineering: Empowering Computing, Analytics, and Engineering Through Digital Innovation, ICRAIE 2023). doi: 10.1109/ICRAIE59459.2023.10468387

Adaptive time method for fall detection in elderly

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this