A Falling Detection System Using Geophone and Support Vector Machines (SVM)

Project Abstract

According to the research, approximately 7.5 million people are 65 years or older in Thailand, which is 11% of the Thai population in 2016.

The number has increased from 5% in 1995 and will be expected to represent more than a quarter of the population by 2040, with 17 million Thais projected to be 65 years or older.

[1]. As the second leading factor of accidental deaths in the world, falls cause around 646,000 cases that lead to human deaths every year, especially for individuals over 65 years of age in developing countries.

[2]. Moreover, an immediate rescue alert that asks for timely assistance could largely cut down the following consequences of injuries after a fall event occurs .

[3]. Currently, people have to hire caregivers to take care of the elders. However, hiring caregivers could increase the cost to take care of the elders. To provide an affordable and effective system to report falls, a fall detection system is introduced in this proposal. This approach uses a geophone sensor and Raspberry Pi to collect the signal generated from falling events. Then, the system will extract the featured data and apply a Support Vector Machines (SVM) algorithm to classify the falling events. The system will be deployed and verified in laboratory experiments to perform identifications on falls from environmental noises and non-fall events, such as activities of daily living (ADL) and item falls.



Reference

[1]Thailand economic monitor - June 2016: Aging Society and Economy. Bangkok:World Bank.

[2] “Falls,” World Health Organization. [Online]. Available : https://www.who.int/news-room/fact-sheets/detail/falls. [Accessed: 16-Sep-2019].

[3] Bagalà, F.; Becker, C.; Cappello, A.; Chiari, L.; Aminian, K.; Hausdorff, J.M.;Zijlstra, W.; Klenk, J. Evaluation of accelerometer-based fall detection algorithms onreal-world falls. PLoS ONE 2012, 7, e37062. [CrossRef] [PubMed]

Researcher
Yang Qi
Student
CMKL University
Advisor
Akkarit Sangpetch
Assistant Professor
CMKL University
Orathai Sangpetch
Assistant Professor
CMKL University
Siriwat Kasamwattanarote
Yarnvith Raksri
Kasikorn Business-Technology Group