Monitoring and alerting the physicians related to trauma cases using behavioural DL models

Abstract

Presently Every nation places a high value on healthcare due to the rise in trauma instances. The ideal approach in this case is thought to be an Internet of Things (IoT) based health monitoring system. A novel approach in internet technology, the Internet of Things (IoT) is an increasing study area, mainly in the field of healthcare. The rising use of wearable sensors and cellphones has allowed these remote health care monitoring systems to grow at such a rapid rate. IoT health monitoring helps patients receive the appropriate care for their present level of health even when a physician is far away. The notion of the IoT and deep learning are combined in this study to present a systematic method to identify trauma instances more effectively. By utilizing some of the biological information from the patient's body, such as temperature, heart rate, and other factors, this approach presents an overview of the IoT and is also used to monitor health status and identify symptoms in the human body. For fall detection using sensor nodes, the Deep Convolutional Neural Network (DCNN) analyses individuals' motion and architecture. The suggested method may be put in place for less money but has significant potential to identify symptoms by giving patients and suspected cases the care they need and reacting to life-or-death circumstances. Metrics such as precision, recall, F-measure, and accuracy are utilized to evaluate the results when applying classification algorithms. When compared to techniques like the Decision Tree (DT), Support Vector Machine (SVM), and K Nearest Neighbour (k-NN), the findings show that it has been very successful.

Keywords

• Internet of things (IoT)
• Machine learning
• Deep convolutional neural network (DCNN)
• Healthcare
• Monitoring system
• Altering system