James Whiteside, a fourth year electrical engineering student at the University of Waterloo, has just completed a co-op term at Pierre and Marie Curie University (UPMC) as part of the exchange program between Waterloo and Sorbonne Universities. During his time at UPMC, James worked in UPMC’s L2E Electronics and Electromagnetism Laboratory overseen by Professor Julien Sarrazin to create an indoor localization system to detect falls.
Falls are a serious issue in public health, and are a major cause of morbidity and mortality amongst older persons. Falls can lead to serious injuries, recurrent hospitalizations, and, even if an injury doesn’t occur, can cause a fear of falling leading to impairments in mobility, regular functioning, as well as a loss of personal autonomy1.
To prevent such issues, the goal of the lab was to create an indoor localization system capable of both detecting falls and working in real time. Real time detection of falls would allow for immediate communication of such adversities to medical professionals to supply assistance, both promoting a sense of security and reducing the negative impact of falls (1). The current system in development was unable to detect falls in real-time and could only recognize the presence of a person. In the lab, James worked on the software side of the research project with the use of MATLAB, a vector network analyzer, and an oscilloscope, in order to develop a system that could detect a person’s movement at a radio frequency of 60 GHz. James was able to develop algorithms that could detect persons at the desired frequency, with only a small delay in data interpretation through the oscilloscope.
With regard to current indoor localization systems, James comments that the research done in the lab could provide a proactive solution to fall prevention amongst the elderly through the creation of “hands free” technologies. James refers to current wearable technologies for fall detection systems, which can be effective, but can also have the crucial problem of people forgetting to wear their sensors in the first place2. With a hands free indoor localization system to detect falls, no additional effort from the user would be necessary.
In the future, Professor Sarrazin and James’ work can be applied to further advance indoor localization systems for fall detection through the creation of a system that can operate in real time.
References
-
Bagalà F, Becker C, Cappello A, Chiari L, Aminian K, Hausdorff JM, Zijlstra W, Klenk J. Evaluation of accelerometer-based fall detection algorithms on real-world falls. PloS one. 2012 May 16;7(5):e37062.
-
Zhang T, Wang J, Liu P, Hou J. Fall detection by embedding an accelerometer in cellphone and using KFD algorithm. International Journal of Computer Science and Network Security. 2006 Oct;6(10):277-84.