Noninvasive Blood Glucose Measurement Based on NIR Spectrums and Double ANN Analysis

Guo, Dongmin; Shang, Y. Z.; Peng, Rongshuo; Yong, Shanshan; Wang, X. A.

doi:10.4236/jbm.2015.36007

Cited by 11 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experiments showed that the RMSE of the prediction is between 0.97 and 6.69 mg/dL and the average of RMSE is 3.80 mg/dL. [ 24 ] Tamilselvi and Ramkumar in 2015 proposed a framework for noninvasive blood glucose measurement using NIR spectroscopy with 940-nm wavelength. At the start of experiment, the Global Positioning System module sends the user's position coordinates with the message to the physician.…”

Section: Literature Reviewmentioning

confidence: 99%

Noninvasive optical diagnostic techniques for mobile blood glucose and bilirubin monitoring

2018

View full text Add to dashboard Cite

Background:People with diabetes need to monitor their blood sugar levels constantly and attend health centers regularly for checkups. The aim of this study is to provide a healthcare system for mobile blood glucose and bilirubin monitoring.Methods:It includes a sensor for noninvasive blood glucose and bilirubin measurement using near-infrared spectroscopy and optical method, respectively, communicating with a smartphone.Results:It was observed that by increasing the glucose concentration, the output voltage of the sensor increases in transmittance mode and decreases in reflectance mode. Moreover, it was observed that by increasing the bilirubin concentration, the output voltage of sensor decreases in transmittance mode and increases in reflectance mode. In the collected data there was good correlations between voltage and concentration and their relationship were approximately linear. Therefore, it is possible to use noninvasive methods to predict the glucose or bilirubin concentration. In vivo experiments for glucose were carried out with 19 persons in training phase, and five persons were used for testing the model. The glucose behavior model was built into the mobile application. The average glucose concentrations from the transmittance and reflectance mode were obtained. The average percentage error was 8.27 and root mean square error was 18.52 mg/dL.Conclusions:From this research, it can be inferred that the noninvasive optical methods implemented on wireless sensors and smartphones could form a system that can be used at any time and any place in the future as an alternative to traditional invasive blood glucose and bilirubin measurement methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Noninvasive optical diagnostic techniques for mobile blood glucose and bilirubin monitoring

2018

View full text Add to dashboard Cite

show abstract

“…Due to the ineffectiveness of invasive techniques, non-invasive techniques for detecting blood sugar have emerged, this non-invasive technique is already quite widely used by implementing various types of calculation techniques. [2][3] [4] and the most widely used technique is linear regression techniques [5] [6]. Detection results produced through non-invasive devices do not have a high degree of accuracy and the level of error margins of noninvasive devices is still quite large.…”

Section: Introductionmentioning

confidence: 99%

Performance Improvement of Non Invasive Blood Glucose Measuring System With Near Infra Red Using Artificial Neural Networks

Pamungkas

Putrada

Abdurohman

2019

KINETIK

View full text Add to dashboard Cite

Measurement of body blood sugar levels is one of the important things to do to reduce the number of people with diabetes mellitus. Non-invasive measurement techniques become a blood sugar measurement technique that is more practical when compared to invasive techniques, but this technique has not shown too high levels of accuracy, specificity and sensitivity. For this reason, the non-invasive measurement model using NIR and ANN is proposed to improve the performance of non-invasive gauges. Non-invasive blood sugar measuring devices will be built using a nodemcu board with photodiaodes and NIR transmitters whose data is then processed using ANN models compared to invasive blood sugar data obtained from 40 data. 40 data obtained then used as raw data to build ANN models which 75% percent of it use as training data and 25% od it will be use as testing data to validate accuration of the model been built, the split of data doing randomly without any interference from programmer or model designer. All the data gathered are data collected from all volunteers which willingly to test their blood glucose using invasive glucose meter and non invasive glucose meter which been built. The invasive glucose meter used to gather raw data of blood glucose is SafeAccu-2 with 95% level of accuracy so the accuracy and error parameter calculated in this research are based on that 95% level accurcy of the invasive device.

show abstract

Design and Implementation of a Wearable System for Non-Invasive Glucose Level Monitoring

Islam

Maniur

2019

2019 IEEE International Conference on Biomedical Engineering, Computer and Information Technology for Health (BECITHCON)

View full text Add to dashboard Cite

Noninvasive Blood Glucose Measurement Based on NIR Spectrums and Double ANN Analysis

Cited by 11 publications

References 18 publications

Noninvasive optical diagnostic techniques for mobile blood glucose and bilirubin monitoring

Noninvasive optical diagnostic techniques for mobile blood glucose and bilirubin monitoring

Performance Improvement of Non Invasive Blood Glucose Measuring System With Near Infra Red Using Artificial Neural Networks

Design and Implementation of a Wearable System for Non-Invasive Glucose Level Monitoring

Contact Info

Product

Resources

About