Exploring a Fuzzy Rule Inferred ConvLSTM for Discovering and Adjusting the Optimal Posture of Patients with a Smart Medical Bed

Abstract

Several countries nowadays are facing a tough social challenge caused by the aging population. This public health issue continues to impose strain on clinical healthcare, such as the need to prevent terminal patients’ pressure ulcers. Provocative approaches to resolve this issue include health information technology (HIT). In this regard, this paper explores one technological solution based on a smart medical bed (SMB). By integrating a convolutional neural network (CNN) and long-short term memory (LSTM) model, we found this model enhanced performance compared to prior solutions. Further, we provide a fuzzy inferred solution that can control our proposed proprietary automated SMB layout to optimize patients’ posture and mitigate pressure ulcers. Therefore, our proposed SMB can allow autonomous care to be given, helping prevent medical complications when lying down for a long time. Our proposed SMB also helps reduce the burden on primary caregivers in fighting against staff shortages due to public health issues such as the increasing aging population.

DMGM: deformable-mechanism based cervical cancer staging via MRI multi-sequence *

“…The specific structure construction inside the module is shown in figure 2. The design of module structure is as follows: firstly, the main data flow passes through a ConvLSTM layer (Shi et al 2015, Costello et al 2021. Secondly, the tensors are input into 3D convolutional layer (Ji et al 2010, Xu and Liu 2019, Chen et al 2020), 3D average-pooling layer, and map clipping layer successively to obtain three bias maps for every dimension and a spatial attention map.…”

Untitled

“…Due to the advantage of feature learning, recent solutions have widely utilized various CNN models to increase the accuracy of the classifier. Indeed, several CNN-based studies have been proposed, such as the works of [2][3][4]. In [2], the researchers introduced a self-supervised learning model which consists of an upstream self-supervised pre-training task and a downstream recognition task.…”

“…Both these approaches provide impressive results with over 99% accuracy in the 3-class dataset. In the work of Costello et al, the authors combined a fuzzy rule inference with a mixture of CNN and LSTM models to achieve the accuracy of 98.8% in terms of 10 sleeping postures classification [4].…”

Nurses' Perceptions About Smart Beds in Hospitals

“…In the advent of the coronavirus disease (COVID-19) pandemic, interest in mattresses equipped with smart features has continued to increase 12–14 . Thus, improving the quality and features of medical beds has become important in enhancing the safety and well-being of both patients and nurses 15–19 …”

“…[12][13][14] Thus, improving the quality and features of medical beds has become important in enhancing the safety and well-being of both patients and nurses. [15][16][17][18][19] Although nurses are one of the key stakeholders who ensure the safe use of medical equipment and devices, little is known about nurses' perceptions, concerns, and suggestions regarding a smart mattress for patient care. According to the technology acceptance model, 20 an individual's behavioral intention in the use of technology is affected by perceived usefulness and ease of use.…”