Bed position classification using bed sensor panel for preventing falls and prolonged bed rest

The rapid growth of the elderly population promotes the need for geriatric care. Due to the shortage of care workers, elderlies have to spend most of their time alone. This leads them to face potential risks around the bed without any assistance. Falls are major problems in nursing home care. These mishaps are related to seriously injured issues such as bruises, soreness, and bone fractures. Falling from a bed often occurs immediately after getting out of bed or coming close to the edge of a bed. Moreover, a lack of repositioning of the body of a bedridden elderly person may cause bedsores.In order to avoid such a risk, a continuous activity monitoring system is needed for taking care of the elderly. Therefore, bed fall has become an active area of research, particularly bed fall detection. Wearable devices and vision sensors have some constraints on the comfort and privacy of a subject. As a result, a non-constraint sensing device, which is embedded in the environment, is a suitable approach for continuously monitoring elderly activity. For fall prevention, the system needs to detect the position of lying with respect to the edge of the bed. Moreover, for bedsore prevention, the duration of a person lying in exactly the same position for a long time can be monitored.In this study, we proposed a bed position classification based on feature exploration and deep learning methods on signals from the panel. It is installed on the bed under the mattress. The panel sensor is embedded with the four sensors, composed of two piezoelectric sensors and two pressure sensors. The bed positions are classified into five classes, i.e., off-bed, sitting, lying center, lying left, and lying right. The off-bed and sitting positions are highly significant for detecting the bed exit activity because they are normally the positions just before or after the bed exit. The in-bed positions are important to prevent falls when the elderly patient moves toward the edge of the bed. The system will also alert the caregiver to turn the elderly patient’s body when staying in the same position for more or less two hours to prevent bedsores. The findings of our study contribute to bed falls and bedsore prevention in the elderly.