Optimal Image Characterization for In-Bed Posture Classification by Using SVM Algorithm
Identifying patient posture while they are lying in bed is an important task in medical applications such as monitoring a patient after a surgical intervention, sleep supervision to identify behavioral and physiological markers, or for bedsore prevention. An acceptable strategy to identify the patie...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Big Data and Cognitive Computing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-2289/8/2/13 |
| _version_ | 1797298904035753984 |
|---|---|
| author | Claudia Angelica Rivera-Romero Jorge Ulises Munoz-Minjares Carlos Lastre-Dominguez Misael Lopez-Ramirez |
| author_facet | Claudia Angelica Rivera-Romero Jorge Ulises Munoz-Minjares Carlos Lastre-Dominguez Misael Lopez-Ramirez |
| author_sort | Claudia Angelica Rivera-Romero |
| collection | DOAJ |
| description | Identifying patient posture while they are lying in bed is an important task in medical applications such as monitoring a patient after a surgical intervention, sleep supervision to identify behavioral and physiological markers, or for bedsore prevention. An acceptable strategy to identify the patient’s position is the classification of images created from a grid of pressure sensors located in the bed. These samples can be arranged based on supervised learning methods. Usually, image conditioning is required before images are loaded into a learning method to increase classification accuracy. However, continuous monitoring of a person requires large amounts of time and computational resources if complex pre-processing algorithms are used. So, the problem is to classify the image posture of patients with different weights, heights, and positions by using minimal sample conditioning for a specific supervised learning method. In this work, it is proposed to identify the patient posture from pressure sensor images by using well-known and simple conditioning techniques and selecting the optimal texture descriptors for the Support Vector Machine (SVM) method. This is in order to obtain the best classification and to avoid image over-processing in the conditioning stage for the SVM. The experimental stages are performed with the color models Red, Green, and Blue (RGB) and Hue, Saturation, and Value (HSV). The results show an increase in accuracy from 86.9% to 92.9% and in <i>kappa</i> value from 0.825 to 0.904 using image conditioning with histogram equalization and a median filter, respectively. |
| first_indexed | 2024-03-07T22:42:49Z |
| format | Article |
| id | doaj.art-9e26d75f286042c88a78b7c1145fe6d3 |
| institution | Directory Open Access Journal |
| issn | 2504-2289 |
| language | English |
| last_indexed | 2024-03-07T22:42:49Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Big Data and Cognitive Computing |
| spelling | doaj.art-9e26d75f286042c88a78b7c1145fe6d32024-02-23T15:07:37ZengMDPI AGBig Data and Cognitive Computing2504-22892024-01-01821310.3390/bdcc8020013Optimal Image Characterization for In-Bed Posture Classification by Using SVM AlgorithmClaudia Angelica Rivera-Romero0Jorge Ulises Munoz-Minjares1Carlos Lastre-Dominguez2Misael Lopez-Ramirez3Unidad Académica de Ingeniería Eléctrica Plantel Jalpa, Universidad Autónoma de Zacatecas, Libramiento Jalpa Km 156+380, Fraccionamiento Solidaridad, Jalpa 99601, Zacatecas, MexicoUnidad Académica de Ingeniería Eléctrica Plantel Jalpa, Universidad Autónoma de Zacatecas, Libramiento Jalpa Km 156+380, Fraccionamiento Solidaridad, Jalpa 99601, Zacatecas, MexicoDepartamento de Ingeniería Electrónica, Tecnológico Nacional de México, Instituto Tecnológico de Oaxaca, Av. Ing. Víctor Bravo Ahuja No. 125 Esquina Calzada Tecnológico, Oaxaca de Juárez 68030, Oaxaca, MexicoMultidisciplinary Studies Department, Engineering Division, Campus Irapuato-Salamanca, University of Guanajuato, Yuriria 38954, Guanajuato, MexicoIdentifying patient posture while they are lying in bed is an important task in medical applications such as monitoring a patient after a surgical intervention, sleep supervision to identify behavioral and physiological markers, or for bedsore prevention. An acceptable strategy to identify the patient’s position is the classification of images created from a grid of pressure sensors located in the bed. These samples can be arranged based on supervised learning methods. Usually, image conditioning is required before images are loaded into a learning method to increase classification accuracy. However, continuous monitoring of a person requires large amounts of time and computational resources if complex pre-processing algorithms are used. So, the problem is to classify the image posture of patients with different weights, heights, and positions by using minimal sample conditioning for a specific supervised learning method. In this work, it is proposed to identify the patient posture from pressure sensor images by using well-known and simple conditioning techniques and selecting the optimal texture descriptors for the Support Vector Machine (SVM) method. This is in order to obtain the best classification and to avoid image over-processing in the conditioning stage for the SVM. The experimental stages are performed with the color models Red, Green, and Blue (RGB) and Hue, Saturation, and Value (HSV). The results show an increase in accuracy from 86.9% to 92.9% and in <i>kappa</i> value from 0.825 to 0.904 using image conditioning with histogram equalization and a median filter, respectively.https://www.mdpi.com/2504-2289/8/2/13patient posturegray-level co-occurrence matrixfeature extractiontexture descriptorssupport vector machinecolor components |
| spellingShingle | Claudia Angelica Rivera-Romero Jorge Ulises Munoz-Minjares Carlos Lastre-Dominguez Misael Lopez-Ramirez Optimal Image Characterization for In-Bed Posture Classification by Using SVM Algorithm Big Data and Cognitive Computing patient posture gray-level co-occurrence matrix feature extraction texture descriptors support vector machine color components |
| title | Optimal Image Characterization for In-Bed Posture Classification by Using SVM Algorithm |
| title_full | Optimal Image Characterization for In-Bed Posture Classification by Using SVM Algorithm |
| title_fullStr | Optimal Image Characterization for In-Bed Posture Classification by Using SVM Algorithm |
| title_full_unstemmed | Optimal Image Characterization for In-Bed Posture Classification by Using SVM Algorithm |
| title_short | Optimal Image Characterization for In-Bed Posture Classification by Using SVM Algorithm |
| title_sort | optimal image characterization for in bed posture classification by using svm algorithm |
| topic | patient posture gray-level co-occurrence matrix feature extraction texture descriptors support vector machine color components |
| url | https://www.mdpi.com/2504-2289/8/2/13 |
| work_keys_str_mv | AT claudiaangelicariveraromero optimalimagecharacterizationforinbedpostureclassificationbyusingsvmalgorithm AT jorgeulisesmunozminjares optimalimagecharacterizationforinbedpostureclassificationbyusingsvmalgorithm AT carloslastredominguez optimalimagecharacterizationforinbedpostureclassificationbyusingsvmalgorithm AT misaellopezramirez optimalimagecharacterizationforinbedpostureclassificationbyusingsvmalgorithm |