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

Realizing the significance of precise detection hemoglobin concentrations towards early diagnosis several diseases, present work addresses design and analysis sensor based on defective 1D photonic crystal (PhC). The alternating layers Si SiO2 are used to proposed PhC with a central defect layer infiltrated concentrations. well-established transfer matrix method (TMM) is manipulated study transmission spectrum structure. strong dependence mode characteristics refractive index forms backbone this work. Numerous geometrical parameters such as thickness layer, angle incidence meticulously optimized realize high sensitivity. Additionally, effect temperature thoroughly investigated sensing performance. It perceived that at an incident 300 550 nm, structure bestows maximum sensitivity 1916.77 nm/RIU. Finally, we developed machine learning model predict different in blood, where found output closely matched obtained through TMM. Moreover, it can accuracy linearity.