Real time fall detection in fog computing scenario
- PDF / 1,207,054 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 103 Downloads / 178 Views
(0123456789().,-volV)(0123456789().,-volV)
Real time fall detection in fog computing scenario Rashmi Shrivastava1 • Manju Pandey1 Received: 21 December 2019 / Revised: 21 December 2019 / Accepted: 7 January 2020 Ó Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Ambient assisted living is a concept which uses information and communication technology to assist the daily living of people. Human fall detection is an important sub-area of ambient assisted living. Human fall has been seen as a critical problem for elderly people. Fall detection is an approach which analyzes sensor data (wearable sensors/ambient sensors or vision-based sensor) to detect human fall using various learning algorithms. This paper presents a fall detection method that detects and notifies fall activity in real-time using fog computing. Support Vector Machine based one class classification is used here to build fall detection model. Five features have been calculated from Smartphone accelerometer data to build fall detection model. To implement one class classification, a new method for kernel matrix calculation is proposed here. This fall detection model exploited the concept of fog computing to send real-time notification to the caregiver and it is also able to notify caregiver in absence of fog node to cloud connection. In the proposed method we have got 100% sensitivity and 98.77% specificity for human fall detection. This fall detection method is also tested on real fall data and it is found that this method is able to detect 100% fall activities. Use of fog computing concept drastically reduces amount of data transferred to the cloud from 900 values (10,799 bytes) to 5 values (59 bytes) per 6 s. Keywords Fall detection Fog computing One-class classification SVM
1 Introduction Human fall detection is one of the major sectors of healthcare system. Human fall detection is an approach that automatically detects human fall using various types of sensors and sends notification to the caretaker to take necessary action. Risk of accidental fall is increasing in life of elderly people day by day. Repeated falls and instability are very common causes of death [1]. According to the world health organization report of aging and health 2018, ‘‘proportion of the world’s population over 60 years, will nearly double from 12 to 22% between 2015 and 2050’’ [2]. According to the new market research report ‘‘Fall Detection System Market by Component (Accelerometer& Gyroscope, Unimodal/Bimodal, Multimodal Sensors), Algorithm (Simple Threshold, Machine Learning), System (In-Home Landline, In-Home Cellular, Wearable), End
& Rashmi Shrivastava [email protected] 1
Department of MCA, National Institute of Technology, Raipur, C.G., India
User, and Region—Global Forecast to 2022’’, published by MarketsandMarketsTM , the fall detection market is expected to be worth USD 497.3 Million by 2022, growing at a CAGR of 5.58% between 2017 and 2022’’. For fall detection various types of sensors have been used in various research wor
Data Loading...
