Article Preview
Top1. Introduction
A fall is defined as a sudden, uncontrolled and unintentional downward displacement of the body to the ground. It is evident that falls affect millions of people (especially the elderly) and may result in significant injuries (Kannus, Sievänen, Palvanen, Järvinen, & Parkkari, 2005). Moreover, injury is a leading cause of death among elderly people (Stevens, Corso, Finkelstein, & Miller, 2006). Automatic fall detection systems rely on a set of threshold values for predetermined parameters, as well as classification rules, in order to continuously process motion data, obtained from an accelerometer and/or a gyroscope, or other sensors, and to determine in near real-time if a fall event has occurred.
Automatic fall detection is one of the hottest topics in the field of preventive health care since the last decade. Numerous papers report approaches to automatic fall detection based on the analysis of images, video, audio, as well as inertial sensor data from sensors that are either discrete (stand-alone) or integrated inside a mobile phone (Abbate, Avvenuti, Bonatesta, Cola, Corsini, & Vecchio, 2012 ; Bagalà et al., 2012; Bourke, O’Brien, & Lyons, 2007; Fudickar, Karth, Mahr, & Schnor, 2012; Rougier, Meunier, St-Arnaud & Rousseau, 2011; Sposaro & Tyson, 2009; Vaidehi, Ganapathy, Mohan, Aldrin, & Nirmal, 2011; Zhang, Wang, Liu, & Hou, 2006).
The utilization of mobile phones or smartphones for the provision of pervasive health care services (Hristoskova, Sakkalis, Zacharioudakis, Tsiknakis, & De Turck, 2014) provides a cost-effective and powerful solution to the well-known issue of increasing health-care needs and costs due to the growing population of elderly (Spanakis, Lelis, Chiarugi, & Chronaki, 2005 ; Spanakis et al. 2012). Various such fall detection systems already exist (Table 1) and each one of these uses a specific phone with different embedded sensors. Moreover each method is evaluated within its own testing environment and with its own data. Thus it is very difficult, if not impossible, to compare different existing approaches on their validity and effectiveness.
Table 1. Overview of fall detection and classification methods
| Method Type | Article | No. of Subjects | Types of Motions | Phone/Sensor Position | Performance |
| Falls | ADLS |
| Threshold Based | Dai et al. (2010) | 15 | 3 | 3 | Waist | Forward fall: FN 2.6%
Lateral fall: FN 3.3%
Backward fall: FN 2.1%
ADLS: FP 8.7% |
| Lee et al. (2011) | 18 | 4 | 8 | Waist | SP: 81%, SE: 77% |
| Tolkiehn et al. (2011) | 12 | 13 | 12 | Waist | SP: 85.24%, SE: 87.77% |
| Fang et al. (2012) | 4 | Performed but not defined | 4 | Chest, waist, thigh | SP: 72.22%, SE: 73.78% |
| Cao et al. (2012) | 20 | Performed but not defined | 3 | Shirt pocket | SP: 92.75%, SE: 86.75% |
| Viet et al. (2012) | 5 | 3 | 6 | Shirt pocket, pants pocket, hand, ear | SP: 96%, SE: 80% |
| Machine Learning | Zhang et al. (2006) | 32 | Low risk fall
High risk fall | Normal/ High-intensity, Special movements, Critical movements | Clothes pocket
Hanged on neck | Mean ratio of correctness 93.3% |
| Luštrek et al. (2009) | 3 | Performed but not defined | 6 | 12 body tags attached to: shoulders, elbows, wrists, hips, knees and ankles. | SVM Accuracy:
97.7% on clear data
96.5% on noisy data |
| Abbate et al. ( 2012) | 7 | 3 | 6 | Waist | Accuracy: 100% |
| Albert et al. (2012) | 15 | 4 | Fall-like events extracted while 9 subjects wearing device for 10 days | Standardized position& orientation: Belt | RLR Accuracy:
Detection: 98 %
Classification: 99.6% |
| Zhao et al. (2012) | 10 | 4 | 3 | Waist | Accuracy: 98.4% |
| Fahmi et al. (2012) | Unclear | 4 | 4 | 5 postures:
Holding phone, Phone in ear, chest/pants pockets, on sidewise lying, on supine lying | SE: 85.3%
SP: 90.5% |
| Kansiz et al. (2013) | 8 | 4 | 6 | Pocket | Average recall value: 0.88 |