Real-time recognition of patient intentions from sequences of pressure maps using artificial neural networks

Chica, Manuel; Campoy, Pascual; Pérez, María Ana; Rodríguez, Tomás Escobar; Rodríguez, Rubén; Valdemoros, íscar

doi:10.1016/j.compbiomed.2011.12.003

Cited by 12 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study showed that feature extraction on clients with varying somatotypes is not a trivial task. This reinforces the statement made previously by Chica et al [11] in the introduction. --------------3 310 Clients who were assigned to categories 1 and 5 had their pelvic landmark positions identified by the feature extraction algorithm with a success rate of 97.96% and 90.91%, respectively.…”

Section: Discussionsupporting

confidence: 91%

“…In a study by Chica et al [11] the aim was to create an intelligent computer system that would control the movement of a bed given a client's pressure map when laying down. The client's intentions (for example, whether they wanted to move right or left or sit up) were calculated by detecting changes in the pressure map.…”

Section: Introductionmentioning

confidence: 99%

“…Classification has been extensively carried out using pressure maps on subjects with low complexity musculoskeletal deformities or no musculoskeletal deformities [11][12][13][14]. Due to the uniformity of 'normal' body shape, it is possible to classify subjects without the design of bespoke feature extraction algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Pelvis feature extraction and classification of Cardiff body match rig base measurements for input into a knowledge-based system

Partlow

Gibson

Kulon

et al. 2012

Journal of Medical Engineering & Technology

View full text Add to dashboard Cite

The purpose of this paper is to determine whether it is possible to use an automated measurement tool to clinically classify clients who are wheelchair users with severe musculoskeletal deformities, replacing the current process which relies upon clinical engineers with advanced knowledge and skills. Clients' body shapes were captured using the Cardiff Body Match (CBM) Rig developed by the Rehabilitation Engineering Unit (REU) at Rookwood Hospital in Cardiff. A bespoke feature extraction algorithm was developed that estimates the position of external landmarks on clients' pelvises so that useful measurements can be obtained. The outputs of the feature extraction algorithms were compared to CBM measurements where the positions of the client's pelvis landmarks were known. The results show that using the extracted features facilitated classification. Qualitative analysis showed that the estimated positions of the landmark points were close enough to their actual positions to be useful to clinicians undertaking clinical assessments.

show abstract

Section: Discussionsupporting

confidence: 91%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pelvis feature extraction and classification of Cardiff body match rig base measurements for input into a knowledge-based system

Partlow

Gibson

Kulon

et al. 2012

Journal of Medical Engineering & Technology

View full text Add to dashboard Cite

show abstract

“…In rehabilitation of patients with limited or restricted mobility, the recognition of postures have been applied to avoid the appearance of bed-pressure ulcers [11], [5], [1], [7], [9], [12], [15]. Most of the systems for patient posture recognition are based on digital cameras, thermal cameras and mattress pressure sensors [6], [3], [13]. Digital and thermal cameras achieve high resolution measurements, however, they are affected by the environment illumination, temperature conditions and occlusions.…”

Section: Introductionmentioning

confidence: 99%

Posture classification of lying down human bodies based on pressure sensors array

Cruz-Santos

Beltrán-Herrera

Vazquez-Santacruz

et al. 2014

2014 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Human posture classification is an important tasks in medical applications, i.e., patient monitoring, ulcer prevention, and conduct diagnostic. We propose a system for posture recognition of lying-down human bodies using a low-resolution pressure sensor array. A support vector-machine was used to perform the classification of pressure maps. Three databases were constructed in order to represent the pressure maps: pressure raw-data, HOG and SIFT image descriptor vectors. It was found that the image descriptors have improved complexity time to build the classification models rather than using raw pressure maps. Experimental results was performed in order to control a robotic hospital bed.

show abstract

“…Numerous studies have investigated the optimal angle during HOB elevation, and these previous studies have proposed the following desirable angles: 45° [11][12][13] and between 30° and 45° [14][15][16][17][18][19][20] to prevent pressure ulcers through pressure dispersion. Moreover, previous studies have also proposed various solutions to disperse the contact pressure when the body pressure changes (force movement) during HOB elevation [5][6][7][8]21], and such analyses of the contact pressure were mainly performed for the sacrum and heels. However, other than pressure ulcers in the sacrum and heel regions, HOB elevation also generates problems such as a shearing force due to the body slipping on a mattress and dorsal or abdomen loads due to a decreasing angle.…”

Section: Introductionmentioning

confidence: 99%

1C4-1 Usability Evaluation of Electric Adjustable Bed during Back-Support Elevation Using Motion Analysis Method

Kim

Lim

Won

2015

The Japanese journal of ergonomics

View full text Add to dashboard Cite

Recently, the number of bedridden patients has increased because of the rapid growth in the aging population worldwide, and most of them have lived on an electric adjustable bed (EAB). Caring for these patients on an EAB is easier and more comfortable than on the floor or a manual adjustable bed. However, the use of an EAB has a negative effect on the slip length and the dorsal and abdomen loads on the patients. Therefore, the aim of this research was to evaluate the usability elements by elevation of the EAB's back support using a motion analysis. In this study, an experiment with 10 subjects (5 men, 5 women, 29.9 ± 2.28 years, 165.8 ± 8.26 cm, 64.2 ± 11.7 kg; mean ± SD) was carried out. The relative motions of the EAB and subjects were captured by a motion analysis system using a customized marker set (EAB: 24 markers, subject: 16 markers, U.E.T.C.). The results of this study show that the slip length and the dorsal and abdomen loads increased as the back support of the EAB was further elevated, and the slip length and dorsal load were not restored when the elevation angle was returned to 0°.A trend toward decrease in changing rate of dorsal load while increase of abdomen load were observed when the back support was elevated from Sections II-1 and II-2 (head-of-bed elevation from 30° to 60°). It would be expected that development of new care technology and care service would be possible with the results and methods of this study.

show abstract

Real-time recognition of patient intentions from sequences of pressure maps using artificial neural networks

Cited by 12 publications

References 15 publications

Pelvis feature extraction and classification of Cardiff body match rig base measurements for input into a knowledge-based system

Pelvis feature extraction and classification of Cardiff body match rig base measurements for input into a knowledge-based system

Posture classification of lying down human bodies based on pressure sensors array

1C4-1 Usability Evaluation of Electric Adjustable Bed during Back-Support Elevation Using Motion Analysis Method

Contact Info

Product

Resources

About