Non-Invasive Near-Infrared-Based Optical Glucose Detection System for Accurate Prediction and Multi-Class Classification
Journal Title: International Journal of Experimental Research and Review - Year 2023, Vol 31, Issue 2
Abstract
One of the most common diseases around the world is diabetes. Intrusive methods involving blood samples via a finger prick are required to test for diabetes. These treatments are uncomfortable and prone to infection. Non-invasive testing is proposed as a solution to this concerning problem. To test the glucose levels of subjects, a shortwave near-infrared-based optical detection system with a 950 nm wavelength sensor in reflective mode is presented. The system collects the measured signal through voltage, transmittance, absorbance and reflections to estimate glucose. The relation between voltage and predicted glucose is evaluated from the absorbance, reflectance, and voltage for 575 samples. A Multiple linear regression (MLR) expression is used in the proposed method to enhance the accuracy. The proposed method achieves a coefficient of determination (R2) of 99% and a mean absolute derivative of 3.6 mg/dl in real-time data analysis with the sensor. The root mean square error (RMSE) is also calculated as 3.46 mg/dl. Three additional machine learning classifiers are employed to achieve high accuracy in multi-class classification. Adaboosting and Gaussian Naïve Bayes classifiers achieve an accuracy of 97% each. Furthermore, the system computes performance metrics such as precision, recall, and F1-score, and predicts the class on the test sample.
Authors and Affiliations
M Naresh, Samineni Peddakrishna
Keywords
Related Articles
- EP ID EP719469
- DOI https://doi.org/10.52756/10.52756/ijerr.2023.v31spl.012
- Views 56
- Downloads 0
Impact of Social Entrepreneurship on Digital Technology and Students’ Skill Set in Higher Education Institutions: A Structured Equation Model
This research paper investigates the impact of social entrepreneurial initiatives implemented by Colleges and Universities on the utilization of digital technology, examining how this utilization, in turn, affects the le...
Efficient Utilization of Energy in IoT Devices Using Machine Learning Algorithms
The expansion of the Internet of Things (IoT) has revolutionized various industries, allowing for the automation of processes, monitoring in real time, and smart decision-making. One of the most significant difficulties...
Traditional use of medicinal plants and its biodiversity in India
Population explosion in certain parts of the world, especially in the developing countries like India, has led to a continuous effort towards development. In India, the dominant health care system is based on allopathic...
Assessing the Impact of Real-Time Visual Feedback during Treadmill Training on Walking Improvement in Stroke Patients
After a stroke, most patients often suffer reduced walking ability and balance. Restoring walking ability and improving balance are major goals of stroke rehabilitation. Treadmills are often used in clinical setups to ac...
Low birth weight is associated with maternal nutrition of Indian women
Low birth weight infants are those born weighing less than 2500g. There are two division such as VLBW < 1000g. Low birth weight (birth weight 15 years old), preterm birth or premature birth (born < 37 weeks gestation and...