An efficient Elman neural network classifier with cloud supported internet of things structure for health monitoring system

The technological advent in smart sensing devices and the Internet has provided practical solutions in various sectors of networking, public and private sector industries, and government organizations worldwide. This study intends to combine the Internet of Things (IoT) technology with health monitoring to make it personalized and timely through allowing the interconnection between the devices. This work is aimed at exploring various wearable health monitoring modules that people wear to monitor heart rate, blood pressure, pulse, body temperature, and physiological information. The information is acquired using the wireless sensor to create a health monitoring system. The data is integrated using the Internet of Things for processing, connecting, and computing to achieve real-time monitoring. The temperature of three people measured by the temperature thermometer is 36.4, 36.7, and 36.5 (°C), respectively, and the average acquired by the monitoring system of the three people is 36.5, 36.4, and 36.5 (°C), respectively, indicating that the system demonstrated relatively accurate and stable testability. The user’s ECG is displayed clearly and conveniently using the ECG acquisition system. The pulse rate of the three people tested by the system is 78, 78, and 79 (times/min), respectively, similar to the medical pulse meter results. The physiological information acquired using the semantic recognition, matching system, and character matching system is relatively accurate. It concludes that the human health monitoring system based on the Internet of Things can provide people with daily health management, instrumental in heightening health service quality and level.

Download Full-text

Transformer Health Monitoring System Using Internet of Things

2018 2nd IEEE International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES) ◽

10.1109/icpeices.2018.8897325 ◽

2018 ◽

Cited By ~ 1

Author(s):

Divyank Srivastava ◽

M. M. Tripathi

Keyword(s):

Internet Of Things ◽

Monitoring System ◽

Health Monitoring ◽

Health Monitoring System

Download Full-text

Monitoring of the Human Body Signal through the Internet of Things (IoT) Based LoRa Wireless Network System

Applied Sciences ◽

10.3390/app9091884 ◽

2019 ◽

Vol 9 (9) ◽

pp. 1884 ◽

Cited By ~ 9

Author(s):

Mohammad Shahidul Islam ◽

Mohammad Tariqul Islam ◽

Ali F. Almutairi ◽

Gan Kok Beng ◽

Norbahiah Misran ◽

...

Keyword(s):

Internet Of Things ◽

Oxygen Saturation ◽

Wireless Network ◽

Monitoring System ◽

Healthcare System ◽

Pulse Rate ◽

Health Monitoring ◽

Physiological Data ◽

Network System ◽

Health Monitoring System

Internet of Things (IoT) based healthcare system is now at the top peak because of its potentialities among all other IoT applications. Supporting sensors integrated with IoT healthcare can effectively analyze and gather the patients’ physical health data that has made the IoT based healthcare ubiquitously acceptable. A set of challenges including the continuous presence of the healthcare professionals and staff as well as the proper amenities in remote areas during emergency situations need to be addressed for developing a flexible IoT based healthcare system. Besides that, the human entered data are not as reliable as automated generated data. The development of the IoT based health monitoring system allows a personalized treatment in certain circumstances that helps to reduce the healthcare cost and wastage with a continuous improving outcome. We present an IoT based health monitoring system using the MySignals development shield with (Low power long range) LoRa wireless network system. Electrocardiogram (ECG) sensor, body temperature sensor, pulse rate, and oxygen saturation sensor have been used with MySignals and LoRa. Evaluating the performances and effectiveness of the sensors and wireless platform devices are also analyzed in this paper by applying physiological data analysis methodology and statistical analysis. MySignals enables the stated sensors to gather physical data. The aim is to transmit the gathered data from MySignals to a personal computer by implementing a wireless system with LoRa. The results show that MySignals is successfully interfaced with the ECG, temperature, oxygen saturation, and pulse rate sensors. The communication with the hyper-terminal program using LoRa has been implemented and an IoT based healthcare system is being developed in MySignals platform with the expected results getting from the sensors.

Download Full-text

Simplified-Boost Reinforced Model-Based Complex Wind Signal Forecasting

Advances in Civil Engineering ◽

10.1155/2020/9564287 ◽

2020 ◽

Vol 2020 ◽

pp. 1-16

Author(s):

Qiushuang Lin ◽

Chunxiang Li ◽

Chao Wu

Keyword(s):

Neural Network ◽

Structural Health Monitoring ◽

Convolutional Neural Network ◽

Monitoring System ◽

High Precision ◽

Health Monitoring ◽

Wind Engineering ◽

Stage Model ◽

Health Monitoring System ◽

Non Gaussian

Wind signal forecasting has become more and more crucial in the structural health monitoring system and wind engineering recently. It is a challenging subject owing to the complicated volatility of wind signals. The robustness and generalization of a predictor are significant as well as of high precision. In this paper, an adaptive residual convolutional neural network (CNN) is developed, aiming at achieving not only high precision but also high adaptivity for various wind signals with varying complexity. Afterwards, reinforced forecasting is adopted to enhance the robustness of the preliminary forecasting. The preliminary forecast results by adaptive residual CNN are integrated with historical observed signals as the new input to reconstruct a new forecasting mapping. Meanwhile, simplified-boost strategy is applied for more generalized results. The results of multistep forecasting for five kinds of nonstationary non-Gaussian wind signals prove the more excellent adaptivity and robustness of the developed two-stage model compared with single models.

Download Full-text