StraightenUp+: Monitoring of Posture during Daily Activities for Older Persons Using Wearable Sensors

Abstract

Monitoring the posture of older persons using portable sensors while they carry out daily activities can facilitate the process of generating indicators with which to evaluate their health and quality of life. The majority of current research into such sensors focuses primarily on their functionality and accuracy, and minimal effort is dedicated to understanding the experience of older persons who interact with the devices. This study proposes a wearable device to identify the bodily postures of older persons, while also looking into the perceptions of the users. For the purposes of this study, thirty independent and semi-independent older persons undertook eight different types of physical activity, including: walking, raising arms, lowering arms, leaning forward, sitting, sitting upright, transitioning from standing to sitting, and transitioning from sitting to standing. The data was classified offline, achieving an accuracy of 93.5%, while overall device user perception was positive. Participants rated the usability of the device, in addition to their overall user experience, highly.

Sensors and Systems for Physical Rehabilitation and Health Monitoring—A Review

“…In [45], the monitoring of the posture of older persons using wearable sensors based on three inertial sensors was demonstrated. At the same time as they carried out daily activities, they generated indicators to assess their health and quality of life.…”

The Use of Inertial Measurement Units for the Study of Free Living Environment Activity Assessment: A Literature Review

“…The first main category gathers articles that intend to test a new activity classification method by developing an algorithm and/or a measurement device specific to their work [ 60 , 61 ]. Authors of these studies set up algorithms that allow, from previous annotated observations of participants performing activities (labeled training data), to determine which type of activity is performed during an analysis of a signal section (see Section 5 for more details on machine learning procedures for activity classification).…”

“…Of all studies using more than one sensor, 67% use four or less sensors. [ 27 , 28 , 54 , 61 , 65 , 74 , 86 ]). Moreover, only three studies use more than ten IMUs—these studies use the IGS-180 suit consisting of seventeen IMUs [ 18 , 63 , 70 ].…”

“…It appears that the majority of the studies have an interesting average rate of classification precision (31 analyses obtain a precision or sensitivity higher than 85 percent [ 77 , 78 , 88 , 94 ]). It should also be noted that certain types of classifiers are recurrent, notably Random Forest (RF) (11 studies [ 83 , 85 , 100 ]) and Decision Trees (DT) (eight studies [ 38 , 61 ]), Support Vector Machine (SVM) (12 studies [ 43 , 76 , 84 , 94 ]), Bayesian approaches (Naive Bayes (NB)) (three studies [ 64 , 76 , 94 ]), K-Nearest Neighbor (KNN) (four studies [ 83 , 84 , 93 , 94 ]) and Neural Network (NN) (four studies [ 15 , 43 , 76 , 108 ] with notably Multi-Layer Perceptron (MLP)). Other classifiers (K-Means (K-M), Linear Regression (LR)) are also put in place in some studies but in less frequent manners and other methods and ancillary methods can also be implemented (Hidden Markov Model (HMM), Receiving Operating Characteristics (ROC), and Adaptation Detection Chain (ADC)).…”

Monitoring Older Adults’ Health Information Using Mobile Technology: A Systematic Literature Review

“…A recent literature review identified that the most commonly used technologies in cardiovascular disease monitoring are mobile apps, and that these applications are mostly used for blood pressure monitoring, cardiac rehabilitation, arrhythmia monitoring, medication management and social support [14]. Recently, several mobile health technologies (mHealth) have emerged with the aim of providing innovative and efficient ways to help older adults in their daily lives and to reduce the cost of health care [15,16], e.g., monitoring vital functions and disease patterns [17], detecting falls or changes in motion patterns or routines [18,19] or informing health care professionals of patients' health status [20]. Digital health information can be used to evaluate health anomalies and for early detection of certain chronic diseases such as Parkinson's or spinal pain [21].…”