Abstract: A method of transforming Monte Carlo (MC) simulations for diffuse reflectance spectroscopy (DRS) may include obtaining, by a DRS device, MC simulated DRS measurements using a pre-defined number of photons; pre-processing, by the DRS device, the MC simulated DRS measurements to obtain normalized DRS measurements; correcting, by the DRS device, non-monotonicity of the normalized DRS measurements to obtain monotonic DRS measurements; converting, by the DRS device, the monotonic DRS measurements to a logarithmic domain to obtain logarithmic DRS measurements; performing, by the DRS device, curve fitting on the logarithmic DRS measurements in the logarithmic domain to obtain curve-fitted logarithmic DRS measurements; and transforming, by the DRS device, the curve-fitted logarithmic DRS measurements to a non-logarithmic domain to obtain transformed MC simulated DRS measurements.

Abstract: A method of predicting a blood compound concentration of a target may include receiving, by a system, spectral data associated with a region of the target, using near-infrared (NIR) spectroscopy. The method may include classifying, by the system, each of the plurality of data instances of the spectral data to one of a plurality of labelled classes. The method may include obtaining, by the system, one or more best fit models from a plurality of prediction models based on the classification. The method may include determining, by the system, blood compound concentration values corresponding to each of the one or more best fit models. The method may include predicting, by the system, the blood compound concentration of the target using the blood compound concentration values predicted using the best fit models.

Abstract: Provided is a method for predicting optical properties of a sample, the method including obtaining, by a device, a plurality of diffuse reflectance values based on optical energy diffusely reflected from the sample, generating, by a multi-layered Deep Fully Connected Neural Network (DFCNN) in the device, a first set of intermediate values by non-linearly mapping the plurality of diffuse reflectance values to the first set of intermediate values, generating, by a One-Dimensional-Convolutional Neural Network (1D-CNN) in the device, a second set of intermediate values by non-linearly mapping the plurality of diffuse reflectance values to the second set of intermediate values, and predicting, by the device, values of the optical properties of the sample based on the first set of intermediate values and the second set of intermediate values.

Abstract: A method includes processing near infrared spectroscopy (NIR) spectra and pure spectra, to obtain a preprocessed NIR spectra, wherein the preprocessed NIR spectra includes any one or any combination of a training data of a plurality of subjects, a calibration data of a test subject and a validation data of the test subject, extracting a dominant feature set from the preprocessed NIR spectra, wherein the dominant feature set includes at least one preprocessed NIR spectrum corresponding to each of the training data, the calibration data and the validation data, and determining a blood glucose concentration of the test subject, using the training data of the plurality of subjects and based on the extracted dominant feature set.

Abstract: A method of predicting a blood compound concentration of a target may include receiving, by a system, spectral data associated with a region of the target, using near-infrared (NIR) spectroscopy. The method may include classifying, by the system, each of the plurality of data instances of the spectral data to one of a plurality of labelled classes. The method may include obtaining, by the system, one or more best fit models from a plurality of prediction models based on the classification. The method may include determining, by the system, blood compound concentration values corresponding to each of the one or more best fit models. The method may include predicting, by the system, the blood compound concentration of the target using the blood compound concentration values predicted using the best fit models.

Abstract: A method includes processing near infrared spectroscopy (NIR) spectra and pure spectra, to obtain a preprocessed NIR spectra, wherein the preprocessed NIR spectra includes any one or any combination of a training data of a plurality of subjects, a calibration data of a test subject and a validation data of the test subject, extracting a dominant feature set from the preprocessed NIR spectra, wherein the dominant feature set includes at least one preprocessed NIR spectrum corresponding to each of the training data, the calibration data and the validation data, and determining a blood glucose concentration of the test subject, using the training data of the plurality of subjects and based on the extracted dominant feature set.