Search

A Deep Learning Multi-output regression model is employed to correctly model the relationships between optical design parameters of an asymmetric Twin Elliptical Core Photonic Crystal Fiber (TEC-PCF) and its sensing performances. TEC-PCF acts as a biosensor to detect the blood glucose level taking hemoglobin components into account. Since asymmetric TEC-PCF uses a dual elliptical core, four super modes have to be evaluated to analyze the sensing performance in terms of effective index difference, transmission spectrum, coupling length, and sensor sensitivity. The dataset used in this work is of the optical design parameters of the sensor and Finite Element Method (FEM) results with effective indices of four super modes obtained from the COMSOL Multiphysics by varying hemoglobin concentration to 120 g/L, 140 g/L, and 160 g/L. Gretel.ai's free open-source synthetic data library is used to augment the dataset to make the training more efficient. Explainable AI (XAI) feature analysis using Shapley Additive Explanations (SHAP) framework is used for two purposes: feature selection and to know the feature's effect on prediction. The former led to the development of an optimal model with much fewer computational demands and the latter made the model interpretable. The proposed model can predict the accurate super modes when given input specifications with wavelength ranging from 1.27- [Formula: see text] and for various glucose concentrations under the influence of hemoglobin much faster compared to the other numerical simulations which are computationally expensive. Computation time taken by the proposed Artificial Neural Network (ANN) model, the proposed model with XAI and FEM is also being compared.

Discovering the relevant web services for specific applications in the dynamically changing business world becomes very critical. Researchers have used many ontology based approaches to address the heterogeneity prevailing in many business problems. Our work focuses on Mishmash technique with rich semantics representation focusing on word segmentation and segregation to reduce load on the server side. We also propose a tokenized, stemmed feature weighted RDF data producing SPARQL result set for generating relevant web services. A deep learning model to learn the retrieved web services using adaptive learning approach was also used, so that a composition of relevant service domain is framed for reducing the time taken for future queries. The model classifier is dynamically built based on the new information's at every iteration, and once an acceptable range defined is achieved, the training accuracy is calculated. The trial results show that the relevant web services are grouped together by the weights in the deep learning model with a training accuracy of 94% by the Mishmash method when compared to Hyperclique method. The testing accuracy of Mishmash method was found to be 95.5% when compared to Hyperclique, which was found to be 92%. Thus the proposed Mishmash method along with Deep learning model can be used as a dynamic decision making model in the Service oriented architecture space. [ABSTRACT FROM AUTHOR]