A ZigBee-Based Location-Aware Fall Detection System for Improving Elderly Telecare

Abstract

Falls are the primary cause of accidents among the elderly and frequently cause fatal and non-fatal injuries associated with a large amount of medical costs. Fall detection using wearable wireless sensor nodes has the potential of improving elderly telecare. This investigation proposes a ZigBee-based location-aware fall detection system for elderly telecare that provides an unobstructed communication between the elderly and caregivers when falls happen. The system is based on ZigBee-based sensor networks, and the sensor node consists of a motherboard with a tri-axial accelerometer and a ZigBee module. A wireless sensor node worn on the waist continuously detects fall events and starts an indoor positioning engine as soon as a fall happens. In the fall detection scheme, this study proposes a three-phase threshold-based fall detection algorithm to detect critical and normal falls. The fall alarm can be canceled by pressing and holding the emergency fall button only when a normal fall is detected. On the other hand, there are three phases in the indoor positioning engine: path loss survey phase, Received Signal Strength Indicator (RSSI) collection phase and location calculation phase. Finally, the location of the faller will be calculated by a k-nearest neighbor algorithm with weighted RSSI. The experimental results demonstrate that the fall detection algorithm achieves 95.63% sensitivity, 73.5% specificity, 88.62% accuracy and 88.6% precision. Furthermore, the average error distance for indoor positioning is 1.15 ± 0.54 m. The proposed system successfully delivers critical information to remote telecare providers who can then immediately help a fallen person.

Feasibility Evaluation of Wearable Sensors for Homecare Systems

“…For walking speed estimation, method presented in [10] has been implemented according to (1), where v is walking velocity estimate, h is effective length of a leg, g = 9,81 m/s 2 and axmin is minimal vertical acceleration of a hip. (1) . 1…”

“…Wearable sensors are emerging over last decade and they presents important innovation tool for healthcare and associated services. There are various typical applications of wearable devices such as monitoring of fall detection [1,2], indoor positioning and distance walked [3,4] or physiologic parameters such as ECG [5]. According to EU demographical projections, all members' countries will experience prolongation of life expectancy and effects of ageing the population [6] and thus, there are research activities aimed on development of solutions that would enable good and economically feasible health and social care using diverse technical aids.…”

An Open and Modular Hardware Node for Wireless Sensor and Body Area Networks

“…where is the number of acceleration samples in the window and ‖ ( )‖ is the magnitude of the th acceleration vector [59].…”

“…Acceleration features are defined similarly to the ones proposed by Huang and Chan [59], but our approach does not require any particular sensor placement or alignment, since it takes into account the magnitude of acceleration vector rather than its components.…”

Lynx: Automatic Elderly Behavior Prediction in Home Telecare

“…The critical task of the system is the automatic profiling of user behaviors. Several systems were introduced in recent years to address elder-care issues, principally fall detection systems [ 5 – 9 ]. However, most of these systems either are too expensive for mass use or are of low quality.…”