Dr. Emmanuel Arzuaga Profile

Dr. Emmanuel Arzuaga

Associate Professor at Univ de Puerto Rico Mayagüez

SPIE Involvement:

Author

Publications (10)

Proceedings Article | 28 September 2023 Presentation + Paper

Using Monte Carlo simulated PPGs signals to train a deep learning model to predict hemoglobin levels

Michael Alvarez, Emmanuel Arzuaga, Heidy Sierra

Proceedings Volume 12655, 1265504 (2023) https://doi.org/10.1117/12.2677499

KEYWORDS: Blood oxygen saturation, Monte Carlo methods, Simulations, Education and training, Deep learning, Tissues, Signal generators, Skin, Blood

Read Abstract +

Measuring Hemoglobin (Hb) levels is required for the assessment of different health conditions, such as anemia, a condition where there are insufficient healthy red blood cells to carry enough oxygen to the body’s tissues. Measuring Hb levels requires the extraction of a blood sample, which is then sent to a laboratory for analysis. This is an invasive procedure that may add challenges to the continuous monitoring of Hb levels. Noninvasive techniques, including imaging and photoplethysmography (PPG) signals combined with machine learning techniques, are being investigated for continuous measurements of Hb. However, the availability of real data to train the algorithms is limited to establishing a generalization and implementation of such techniques in healthcare settings. In this work, we present a computational model based on Monte Carlo simulations that can generate multispectral PPG signals that cover a broad range of Hb levels. These signals are then used to train a Deep Learning (DL) model to estimate hemoglobin levels. Through this approach, valuable insights about the relationships between PPG signals, oxygen saturation, and Hb levels are learned by the DL model. The signals were generated by propagating a source in a volume that contains the skin tissue properties and the target physiological parameters. The source consisted of plane waves using the 660 nm and 890 nm wavelengths. A range of 6 g/dL to 18 dL Hb values was used to generate 468 PPGs to train a Convolutional Neural Network (CNN). The initial results show high accuracy in detecting low levels of Hb. To the best of our knowledge, the complexity of biological interactions involved in measuring hemoglobin levels has yet to be fully modeled. The presented model offers an alternative approach to studying the effects of changes in Hb levels on the PPGs signal morphology and its interaction with other physiological parameters that are present in the optical path of the measured signals.

Proceedings Article | 19 May 2020 Presentation + Paper

Studying the effect of a decision fusion model on enhanced hyperspectral images

Carlos Theran, Michael Alvarez, Heidy Sierra, Emmanuel Arzuaga

Proceedings Volume 11392, 1139206 (2020) https://doi.org/10.1117/12.2560107

KEYWORDS: Data fusion, Image fusion, Hyperspectral imaging, Spatial resolution, Image classification, Data modeling, Fuzzy logic, Remote sensing, Neural networks, Buildings

Read Abstract +

Proceedings Article | 19 May 2020 Presentation + Paper

Analyzing the effects of pixel-scale data fusion in hyperspectral image classification performance

Michael Alvarez, Carlos Theran, Emmanuel Arzuaga, Heidy Sierra

Proceedings Volume 11392, 1139205 (2020) https://doi.org/10.1117/12.2560106

KEYWORDS: Spatial resolution, Image fusion, Data fusion, Hyperspectral imaging, Image classification, Image enhancement, Resolution enhancement technologies, Multispectral imaging, Spectral resolution

Read Abstract +

SPIE Journal Paper | 13 June 2019

Improving execution time for supervised sparse representation classification of hyperspectral images using the Moore–Penrose pseudoinverse

Fernando Arias, Heidy Sierra, Emmanuel Arzuaga

JARS, Vol. 13, Issue 02, 026512, (June 2019) https://doi.org/10.1117/12.10.1117/1.JRS.13.026512

KEYWORDS: Hyperspectral imaging, Image classification, Scene classification, Principal component analysis, Optimization (mathematics), Associative arrays, Reflectivity, Statistical methods, Classification systems, Sensors

Read Abstract +

Proceedings Article | 5 May 2017 Paper

Subsurface classification of objects under turbid waters by means of regularization techniques applied to real hyperspectral data

Emmanuel Carpena, Luis Jiménez, Emmanuel Arzuaga, Sujeily Fonseca, Ernesto Reyes, Juan Figueroa

Proceedings Volume 10198, 1019818 (2017) https://doi.org/10.1117/12.2262760

KEYWORDS: Titanium dioxide, Reflectivity, Image processing, Image classification, Hyperspectral imaging, Reconstruction algorithms, Algorithm development, Mathematical modeling, Water, Remote sensing, Pattern recognition, Animal model studies, Optical properties, Absorption, Backscatter, Associative arrays

Read Abstract +

Proceedings Article | 17 May 2016 Paper

Classification performance of a block-compressive sensing algorithm for hyperspectral data processing

Fernando Arias, Heidy Sierra, Emmanuel Arzuaga

Proceedings Volume 9840, 984005 (2016) https://doi.org/10.1117/12.2224542

KEYWORDS: Compressed sensing, Hyperspectral imaging, Sensors, Data acquisition, Data processing, Reconstruction algorithms, Image processing, Data storage, Image compression, Neural networks

Read Abstract +

Proceedings Article | 9 March 2016 Presentation + Paper

Compressive sensing in reflectance confocal microscopy of skin images: a preliminary comparative study

Fernando Arias, Heidy Sierra, Milind Rajadhyaksha, Emmanuel Arzuaga

Proceedings Volume 9713, 97130Z (2016) https://doi.org/10.1117/12.2213685

KEYWORDS: Skin, Reconstruction algorithms, Confocal microscopy, Image processing, Compressed sensing, Signal processing, Algorithm development, Image compression, Signal detection, Microscopes

Read Abstract +

Proceedings Article | 1 June 2005 Paper

An update on the MATLAB hyperspectral image analysis toolbox

Samuel Rosario-Torres, Emmanuel Arzuaga-Cruz, Miguel Velez-Reyes, Luis Jimenez-Rodriguez

Proceedings Volume 5806, (2005) https://doi.org/10.1117/12.605674

KEYWORDS: MATLAB, Algorithm development, Hyperspectral imaging, Image analysis, Image processing, Image enhancement, Image classification, Visualization, Multispectral imaging, Remote sensing

Read Abstract +

Proceedings Article | 23 September 2003 Paper

Unsupervised feature extraction and band subset selection techniques based on relative entropy criteria for hyperspectral data analysis

Emmanuel Arzuaga-Cruz, Luis Jimenez-Rodriguez, Miguel Velez-Reyes

Proceedings Volume 5093, (2003) https://doi.org/10.1117/12.485942

KEYWORDS: Principal component analysis, Feature extraction, Data analysis, Hyperspectral imaging, Remote sensing, Image processing, Data modeling, Optimization (mathematics), Image analysis, Pattern recognition

Read Abstract +

Proceedings Article | 13 March 2003 Paper

Unsupervised feature extraction techniques for hyperspectral data and its effects on unsupervised classification

Luis Jimenez-Rodriguez, Emmanuel Arzuaga-Cruz, Miguel Velez-Reyes

Proceedings Volume 4885, (2003) https://doi.org/10.1117/12.463521

KEYWORDS: Principal component analysis, Feature extraction, Landsat, Hyperspectral imaging, Remote sensing, Data analysis, Data modeling, Sensors, Data centers, Earth observing sensors

Read Abstract +

Feature extraction, implemented as a linear projection from a higher dimensional space to a lower dimensional subspace, is a very important issue in hyperspectral data analysis. The projection must be done in a matter that minimizes the redundancy, maintaining the information content. In hyperspectral data analysis, a relevant objective of feature extraction is to reduce the dimensionality of the data maintaining the capability of discriminating object of interest from the cluttered background. This paper presents a comparative study of different unsupervised feature extraction mechanisms and shows their effects on unsupervised detection and classification. The mechanisms implemented and compared are an unsupervised SVD based band subset selection mechanism, Projection Pursuit, and Principal Component Analysis. For purposes of validating the unsupervised methods, supervised mechanisms as Discriminant Analysis and a supervised band subset selection using Bhattacharyya distance were implemented and its results were compared with the unsupervised methods. Unsupervised band subset selection based on SVD chooses automatically the most independent set of bands. Projection Pursuit based feature extraction algorithm automatically searches for projections that optimize a projection index. The projection index we optimized is one that measures the information divergence between the probability density function of the projected data and the Gaussian probability density function. This produces a projection where the probability density function of the whole data set is multi-modal, instead of a Gaussian uni-modal distribution. This augments the separability of the unknown clusters in the lower dimensional space. Finally they were compared with well-known and used Principal Component Analysis. The methods were tested using synthetic as well as remotely sensed data obtained from AVIRIS and LANDSAT. They were compared using unsupervised classification methods in a known ground truth area.

Showing 5 of 10 publications

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Keywords/Phrases

Search In:

Publication Years