A Multisensory Approach for Remote Health Monitoring of Older People

TY - JOUR

T1 - A Multisensory Approach for Remote Health Monitoring of Older People

AU - Li, Haobo

AU - Shrestha, Aman

AU - Heidari, Hadi

AU - Kernec, Julien Le

AU - Fioranelli, Francesco

PY - 2018/6

Y1 - 2018/6

N2 - Growing life expectancy and increasing incidence of multiple chronic health conditions are significant societal challenges. Different technologies have been proposed to address these issues, detect critical events, such as stroke or falls, and monitor automatically human activities for health condition inference and anomaly detection. This paper aims to investigate two types of sensing technologies proposed for assisted living: wearable and radar sensors. First, different feature selection methods are validated and compared in terms of accuracy and computational loads. Then, information fusion is applied to enhance activity classification accuracy combining the two sensors. Improvements in classification accuracy of approximately 12% using feature level fusion are achieved with both support vector machine s (SVMs) and k-nearest neighbor (KNN) classifiers. Decision-level fusion schemes are also investigated, yielding classification accuracy in the order of 97%-98%.

AB - Growing life expectancy and increasing incidence of multiple chronic health conditions are significant societal challenges. Different technologies have been proposed to address these issues, detect critical events, such as stroke or falls, and monitor automatically human activities for health condition inference and anomaly detection. This paper aims to investigate two types of sensing technologies proposed for assisted living: wearable and radar sensors. First, different feature selection methods are validated and compared in terms of accuracy and computational loads. Then, information fusion is applied to enhance activity classification accuracy combining the two sensors. Improvements in classification accuracy of approximately 12% using feature level fusion are achieved with both support vector machine s (SVMs) and k-nearest neighbor (KNN) classifiers. Decision-level fusion schemes are also investigated, yielding classification accuracy in the order of 97%-98%.

UR - https://doi.org/10.1109/JERM.2018.2827099

U2 - 10.1109/JERM.2018.2827099

DO - 10.1109/JERM.2018.2827099

M3 - Article

VL - 2

SP - 102

EP - 108

JO - IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology

JF - IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology

IS - 2

ER -