Fitting analysis and research of measured data of SAW micro-pressure sensor based on BP neural network

Research has been carried out on a heart rate and body temperature monitoring system based on the Internet of Medical Things (IoMT). This study aims to create a system for monitoring heart rate and body temperature remotely in real-time with measurement results displayed on a web server. This research includes several methods such as developing research concepts based on literature studies, system design consisting of hardware and software design, sensor calibration, web server creation, system testing, and direct data retrieval. The hardware manufacturing stage uses several components such as a pulse heart sensor to detect heart rate, DS18B20 sensor to detect body temperature, Arduino Uno microcontroller, Xbee end device, Xbee coordinator, and raspberry pi as a server computer. Then for the use of software on this system, it consists of Arduino Integrated Development Environment (IDE) to run Arduino Uno hardware, XCTU to provide configuration on Xbee, Python to run Raspberry Pi and Django as a framework for building web servers and MySQL as data storage center measurement results. Heart rate monitoring is done by placing a sensor on one of the fingers, and body temperature is done by placing the sensor in the axilla. The output from the sensor in the form of analog data is converted by the Arduino Uno microcontroller into digital data and then sent to the Raspberry Pi module via Xbee. The raspberry pi has processed data is then stored in the database and then displayed on the webserver. The sensor calibration results show that the pulse heart sensor's error rate is 0.41%, and the DS18B20 temperature sensor is 1.09%. After calibration of the sensor, data was collected on the three respondents' heart rate and body temperature. The measurement results show that the system can store each respondent's heart rate and body temperature data in the database and display the measurement results on the webserver in real-time. Based on these results indicate that the system that has been made can work well.

show abstract

“…The test compares the sensor measurement results with a comparison tool. The error value for each sensor is obtained by using equation (1) [23]:…”

Section: Sensor Calibration Resultsmentioning

confidence: 99%

INTERNET OF MEDICAL THINGS (IoMT)-BASED HEART RATE AND BODY TEMPERATURE MONITORING SYSTEM

Laila

Arifin

Armynah

2022

IPR

View full text Add to dashboard Cite

show abstract

“…It aims to learn the parameters that can minimize the mean square error, and the defined error function 𝐸 is expressed as [35,36]…”

Section: Neural Network (Nn)mentioning

confidence: 99%

Geometry optimization and pressure analysis of a proton exchange membrane fuel cell stack

Chen

Tsai

Chang

et al. 2021

International Journal of Hydrogen Energy

View full text Add to dashboard Cite

“…ANN loosely models the neuron functions in a human's brain for pattern recognition [20][21][22][23][24]. It can interpret data via clustering, machine perception or labeling input data.…”

Section: Artificial Neural Network (Ann)mentioning

confidence: 99%

Classification of abnormal location in medium voltage switchgears using hybrid gravitational search algorithm-artificial intelligence

et al. 2021

View full text Add to dashboard Cite

In power system networks, automatic fault diagnosis techniques of switchgears with high accuracy and less time consuming are important. In this work, classification of abnormal location in switchgears is proposed using hybrid gravitational search algorithm (GSA)-artificial intelligence (AI) techniques. The measurement data were obtained from ultrasound, transient earth voltage, temperature and sound sensors. The AI classifiers used include artificial neural network (ANN) and support vector machine (SVM). The performance of both classifiers was optimized by an optimization technique, GSA. The advantages of GSA classification on AI in classifying the abnormal location in switchgears are easy implementation, fast convergence and low computational cost. For performance comparison, several well-known metaheuristic techniques were also applied on the AI classifiers. From the comparison between ANN and SVM without optimization by GSA, SVM yields 2% higher accuracy than ANN. However, ANN yields slightly higher accuracy than SVM after combining with GSA, which is in the range of 97%-99% compared to 95%-97% for SVM. On the other hand, GSA-SVM converges faster than GSA-ANN. Overall, it was found that combination of both AI classifiers with GSA yields better results than several well-known metaheuristic techniques.

show abstract

Fitting analysis and research of measured data of SAW micro-pressure sensor based on BP neural network

Cited by 41 publications

References 19 publications

INTERNET OF MEDICAL THINGS (IoMT)-BASED HEART RATE AND BODY TEMPERATURE MONITORING SYSTEM

INTERNET OF MEDICAL THINGS (IoMT)-BASED HEART RATE AND BODY TEMPERATURE MONITORING SYSTEM

Geometry optimization and pressure analysis of a proton exchange membrane fuel cell stack

Classification of abnormal location in medium voltage switchgears using hybrid gravitational search algorithm-artificial intelligence

Contact Info

Product

Resources

About