FMCW radar and inertial sensing synergy for assisted living
| Autor: | Haobo Li, Aman Shrestha, Francesco Fioranelli, Julien Le Kernec, Hadi Heidari |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2019 |
| Předmět: |
cw radar
cognition gyroscopes accelerometers support vector machines fm radar statistical analysis image classification tested subjects suitable sensor combinations unknown subjects random cross-validation improved statistical approach quadratic-kernel support vector machine classifier individual sensor unnecessary computation classification accuracy inertial measurement unit cw cognitive chronic health conditions physical health conditions older people fall detection indoor daily activities multisensory recognition assisted living inertial sensing synergy fmcw radar Engineering (General). Civil engineering (General) TA1-2040 |
| Zdroj: | The Journal of Engineering (2019) |
| Druh dokumentu: | article |
| ISSN: | 2051-3305 |
| DOI: | 10.1049/joe.2019.0558 |
| Popis: | This study presents preliminary results about the multi-sensory recognition of indoor daily activities and fall detection, to monitor the well-being of older people at risk of physical and cognitive chronic health conditions. Five different sensors, continuous wave (CW) radar, frequency-modulated CW (FMCW) radar, and inertial measurement unit comprising an accelerometer, gyroscope, and magnetometer were used to simultaneously collect data from 20 subjects performing 10 activities. Rather than using all of the available sensors, it is more efficient and economical to select part of them to maximise the classification accuracy and avoid unnecessary computation to process information if it is not salient. Each individual sensor and several sensor combinations are trained with a quadratic-kernel support vector machine classifier. In addition, they are validated with an improved statistical approach, which uses data from unknown participants to test model rather than random cross-validation to verify if the model generalises well for unknown subjects. Furthermore, the most suitable sensor combinations are derived for each specific group of tested subjects selected (e.g. the oldest, youngest, tallest, and shortest sub-groups of participants out of the entire group). |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|
Plný text