Mobile Phone-Based Fall Detectors: Ready for Real-World Scenarios?

Falls are a major health problem among the elderly. The consequences of a fall can be minimized by an early detection. In this sense, there is an emerging trend towards the development of agent systems based on mobile phones for fall detection. But when a mobile phone-based fall detector is used in a real-world scenario, the specific features of the phone can affect the performance of the system. This study aims to clarify the impact of two features: the accelerometer sampling frequency and the way the mobile phone is carried. In this experimental study, 5 participants have simulated different falls and activities of daily living. Using these data, the study shows that the sampling frequency affects the performance of the detection. In the same way, when a fall detector intended to be attached at the body is carried in an external accessory, the performance of the system decreases.

[1]  Tom Fawcett,et al.  ROC Graphs: Notes and Practical Considerations for Data Mining Researchers , 2003 .

[2]  Patricia Martín-Rodilla,et al.  Multi-Agent System for Detecting Elderly People Falls through Mobile Devices , 2011, ISAmI.

[3]  G. ÓLaighin,et al.  A proposal for the classification and evaluation of fall detectors Une proposition pour la classification et l'évaluation des détecteurs de chutes , 2008 .

[4]  Gregory M. P. O'Hare,et al.  Mobile devices and intelligent agents - towards a new generation of applications and services , 2005, Inf. Sci..

[5]  L. Rubenstein,et al.  Falls and their prevention in elderly people: what does the evidence show? , 2006, The Medical clinics of North America.

[6]  Konrad Paul Kording,et al.  Fall Classification by Machine Learning Using Mobile Phones , 2012, PloS one.

[7]  Raymond Y. W. Lee,et al.  Detection of falls using accelerometers and mobile phone technology. , 2011, Age and ageing.

[8]  A. Silman,et al.  Age and sex influences on fall characteristics. , 1994, Annals of the rheumatic diseases.

[9]  Paulo Novais,et al.  Ambient Intelligence - Software and Applications - 4th International Symposium on Ambient Intelligence, ISAmI 2013, Salamanca, Spain, May 22-24, 2013 , 2013, ISAmI.

[10]  Patricia Martín-Rodilla,et al.  A New Adaptive Algorithm for Detecting Falls through Mobile Devices , 2011, PAAMS.

[11]  Joel J. P. C. Rodrigues,et al.  Towards an autonomous fall detection and alerting system on a mobile and pervasive environment , 2011, Telecommunication Systems.

[12]  Frank Sposaro,et al.  iFall: An android application for fall monitoring and response , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[13]  T. Masud,et al.  Epidemiology of falls. , 2001, Age and ageing.

[14]  Shih-Hau Fang,et al.  Developing a mobile phone-based fall detection system on Android platform , 2012, 2012 Computing, Communications and Applications Conference.

[15]  Maarit Kangas,et al.  Comparison of low-complexity fall detection algorithms for body attached accelerometers. , 2008, Gait & posture.

[16]  Emiliano Miluzzo,et al.  A survey of mobile phone sensing , 2010, IEEE Communications Magazine.

[17]  Michael Rovatsos,et al.  Towards Improving Supply Chain Coordination through Agent-Based Simulation , 2010, PAAMS.

[18]  Dong Xuan,et al.  Mobile phone-based pervasive fall detection , 2010, Personal and Ubiquitous Computing.

[19]  A K Bourke,et al.  Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm. , 2007, Gait & posture.