Pervasive Lying Posture Tracking

Abstract

Automated lying-posture tracking is important in preventing bed-related disorders, such as pressure injuries, sleep apnea, and lower-back pain. Prior research studied in-bed lying posture tracking using sensors of different modalities (e.g., accelerometer and pressure sensors). However, there remain significant gaps in research regarding how to design efficient in-bed lying posture tracking systems. These gaps can be articulated through several research questions, as follows. First, can we design a single-sensor, pervasive, and inexpensive system that can accurately detect lying postures? Second, what computational models are most effective in the accurate detection of lying postures? Finally, what physical configuration of the sensor system is most effective for lying posture tracking? To answer these important research questions, in this article we propose a comprehensive approach for designing a sensor system that uses a single accelerometer along with machine learning algorithms for in-bed lying posture classification. We design two categories of machine learning algorithms based on deep learning and traditional classification with handcrafted features to detect lying postures. We also investigate what wearing sites are the most effective in the accurate detection of lying postures. We extensively evaluate the performance of the proposed algorithms on nine different body locations and four human lying postures using two datasets. Our results show that a system with a single accelerometer can be used with either deep learning or traditional classifiers to accurately detect lying postures. The best models in our approach achieve an F1 score that ranges from 95.2% to 97.8% with a coefficient of variation from 0.03 to 0.05. The results also identify the thighs and chest as the most salient body sites for lying posture tracking. Our findings in this article suggest that, because accelerometers are ubiquitous and inexpensive sensors, they can be a viable source of information for pervasive monitoring of in-bed postures.

A Smart IoT System for Detecting the Position of a Lying Person Using a Novel Textile Pressure Sensor

“…They used six different postures for classification, where they added sitting and movement posture over our solution. The accelerometerbased solution presented in [6] also achieved a high F1 score that ranges from 95.2% to 97.8%. Overall, the accelerometer-based solution gets better classification results over the sheet-based solution, but there is a disadvantage that the subject has to wear a piece of electronic equipment.…”

“…The work presented in [1][2][3][4], and also our solution, use a non-invasive method and without electronics attached to the subject for the prevention of bedsores. In comparison, the works presented in [5,6] are also non-invasive, but they use an electronic component that needs to be attached to the subject. This can cause some level of discomfort for long-term patients.…”

“…The disadvantage of this solution is that the lying person has to wear the same piece of electronic equipment. Authors in [6] propose a similar solution. They used a comprehensive approach for designing a sensor system that uses a single accelerometer along with machine learning algorithms for in-bed lying posture classification.…”

“…HTTP request-response block sends the data for evaluation in JSON format as a parameter in the HTTP request to the Jetson module. Data looks like: payload: { timestamp: 1605683032, subjectID: "subjet12", notes: "", data: [ [7,8,12,12,20,123,0,0], [8,10,27,21,28,26,0,0], [2,9,6,8,12,8,0, 0], [6,11,11,16,22,13,3,0], [19,32,39,95,103,66,8,0], [13,16,16,28,51,24,1,0], [18,20,24,47,82,40,6, 0], [0, 0, 4, 10, 12, 6, 0, 0], ...…”

A Review of Intelligent Sensor-Based Systems for Pressure Ulcer Prevention

“…Article [11] presents the use of a single tri-axial accelerometer sensor to detect lying postures. The work identifies the amplitude, mean, minimum and maximum values of the lateral and vertical axes as the optimal set of time-domain features to use with a traditional ML scheme, ensemble trees, in this task.…”