Application of Machine Learning for Accurate Detection of Hemoglobin Concentrations Employing Defected 1D Photonic Crystal

Abstract

Realizing the significance of precise detection of hemoglobin concentrations towards early diagnosis of several diseases, the present work addresses design and analysis of hemoglobin sensor based on the defective 1D photonic crystal (PhC). The alternating layers of Si and SiO 2 are used to design the proposed PhC with a central defect layer infiltrated with hemoglobin concentrations. The well-established transfer matrix method (TMM) is manipulated to study the transmission spectrum of the structure. The strong dependence of defect mode characteristics on the refractive index of the hemoglobin concentrations forms the backbone of this work. Numerous geometrical parameters such as thickness of defect layer, angle of incidence are meticulously optimized to realize high sensitivity. Additionally, the effect of temperature is thoroughly investigated on the sensing performance. It is perceived that at an incident angle of 30 0 and the defect layer thickness of 550 nm, the proposed structure bestows a maximum sensitivity of 1916.77 nm/RIU. Finally, we developed a machine learning model to predict different concentrations of hemoglobin in blood, where we found that the model output is closely matched with the output obtained through the TMM. Moreover, it is perceived that the developed machine learning model can predict hemoglobin concentrations with high accuracy and linearity.

A high-performance biosensor design for waterborne bacteria detection based on one-dimensional photonic crystal

“…In 2022, A H Aly et al [12] used a 1D PhC of sensitivity 335.73 nm RIU to detect wide range of pathogens. A Panda et al [22] investigated the sensitivity of a defected 1D PhC to detect Hemoglobin Concentrations and found a sensitivity of 1916.77 nm RIU −1 using Si/SiO 2 materials. M G Daher et al [41] also studied 1D PhC to detect waterborne bacteria and achieved a high sensitivity of 3639.53 nm RIU −1 .…”

“…A H Aly et al demonstrated a blood sugar concentration sensor employing a 1D defect-based PhC structure where transfer matrix method (TMM) is used to tune a number of geometrical parameters in order to achieve a high sensitivity of 1100 nm RIU [21]. A Panda et al [22] constructed a 1D defective PhC for measuring concentrations of hemoglobin and employed TMM to analyze the positional shift in the transmission spectrum to achieve a sensitivity of 1916.77 nm RIU and computed a data set using machine learning techniques. Omar et al [23] used the TMM to develop a protein sensor to identify a change in the PBG properties of a defect-based 1D PhC.…”

Data analysis on the three defect wavelengths of a MoS2-based defective photonic crystal using machine learning

“…Although increasing the number of defects in a DPC modifies the absorption value, wavelength, and Full Width at Half Maximum (FWHM) of defect modes, it complicates the design because of structural parameters’ abundance that leads researchers to use machine learning techniques. In the field of PCs, machine learning is being used to design and optimize a wide range of devices and structures, such as optical waveguides, resonant cavities, and optical sensors 41 – 43 . To design DPC structures and predict their properties, various machine learning methods such as linear, polynomial, and (KNN) regression are implemented through training a model on a training subset and evaluating its validity on a test subset to improve its generalization ability 44 – 47 .…”