![]() The objective of this study is to devise and implement a system for monitoring the sleep health of the elderly people living in hospice. ![]() It is being extensively deployed in the domain of object recognition as well as image segmentation. Recently, researchers proposed a deep learning model named convolutional neural network (CNN), reduces the complexity of the network and number of weights because of its shared-weight network structure. However, these traditional approaches require considerable features extraction from the preprocessed signals and are susceptible to local optimization. The data can be acquired remotely using IoT enabled sensors and several methods are in place for sleep posture classification, including means clustering, artificial neural network, dual-tree, and support vector machine (SVM). The recognition of sleep posture requires the data related to positioning of the subject and some algorithm to classify this information. This will not only result in reduction in health cost but also enhance the availability and quality of care. This capability of remote connectivity offered by IoT technology can be used remote monitoring of patients lacking access to effective health care. The Internet of Things (IoT) is the network of smart electronics device that are connected through internet equipping them with the capability of data exchange. The challenges, rising costs of care and effects of sleep-related issues on the elderly motivate the need for a system that could assist medical practitioners and caregivers in residential-care in monitoring patients more efficiently. Finally, falling out of bed during sleep is another major risk to the elderly, resulting in injuries and even death in extreme cases. Similarly, sleeping on the right-side poses a greater risk of development of transient lower esophageal sphincter relaxation, which is the main reason of nocturnal gastroesophageal reflux. Elderly sleeping in the decubitus position have a higher risk of developing sub-acromial impingement syndrome and those sleeping in a supine position are more likely to develop the symptoms of sleep paralysis. ![]() Furthermore, certain sleep positions and postures are considered to be the major causes of certain diseases. Studies have found that sleep issues are more prevalent within the residential care population. PI may result in constant pain, loss of mobility, depression, and even death. In addition to sleep quality, sleep posture is another prevalent issue among elderly and may cause pressure injuries (PI) if they have prolonged sleep in a single posture without moving, as shown in Figure 1. Sleep analysis is vital for the detection and diagnosis of sleep related complications. The quality of sleep seems to be a common problem among the elderly and needs attention. Therefore adequate and restful sleep is important as it allows the body and brain to undergo necessary restorative activities. They tend to suffer from poor sleep quality which leads to myriad problems and affects their physical health, cognitive function, and overall quality of life. The population of elderly people is on the rise and the number is expected to reach 20% of the total world population by 2050. Finally, we conducted experiments to evaluate the accuracy of the prototype, and the proposed system achieved a classification accuracy of around 90%. It also produces synopses of postures and activities over a given duration of time. A real-time feedback mechanism is also provided through an accompanying smartphone application for keeping a diary of the posture and send alert to the user in case there is a danger of falling from bed. The system is capable of recognizing the four major postures-face-up, face-down, right lateral, and left lateral. The sensors detect the distribution of the body pressure on the mat during sleep and we use convolution neural network (CNN) to analyze collected data and recognize different sleeping postures. The system uses a pressure sensing mat constructed using piezo-resistive material to be placed on a mattress. We propose an unobtrusive and affordable smart system based on an electronic mat called Sleep Mat-e for monitoring the sleep activity and sleep posture of individuals living in residential care facilities. Prevailing systems are designed based on electrocardiograms, cameras, and pressure sensors, which are not only expensive but also intrusive in nature, and uncomfortable to use. Autonomous and constant monitoring of sleep postures provides useful information for reducing the health risk. Sleep pattern and posture recognition have become of great interest for a diverse range of clinical applications.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |