Dr. Roberto Rosas Romero

Profesor Roberto Rosas

Roberto Rosas-Romero is a professor in the Department of Electrical & Computer Engineering at the Universidad de las Américas-Puebla in México since 2000. He earned his Ph. D. Degree in Electrical Engineering from the University of Washington (1999) and was a Visiting Professor at Yale University's Department of Diagnostic Radiology in 2012. A two-time Fulbright Scholar, Dr. Roberto Rosas-Romero has also completed international research and lecturing stays at University College London, Durham University, Université de Montréal, and Appalachian State University.

Professor Rosas secured Mexican government funding to bridge the digital divide in the state of Puebla through the implementation of multiple wireless links and video conferencing systems.This initiative successfully brought high-quality data, voice, and video services to isolated communities, facilitating applications in distance education and telemedicine. He partnered with Appalachian State University to equip a rural health clinic with sustainable solar technology for electricity and hot water. His research network includes collaborations with groups like Yale's Image Processing and Analysis Group and the University of Washington's Vascular Imaging Lab.

His research interesta are Signal Processing, Pattern Recognition and Machine Learning, and his work bridges the gap between theoretical Computer Vision and practical applications in Medical Imaging, Bioinformatics, and Financial Forecasting. Key projects include early-stage disease detection (Parkinson’s, Cancer, Diabetic Retinopathy, Epilepsy), environmental monitoring (forest fires), and industrial quality control (food processing). His contributions are extensively documented in selected peer-reviewed publications:

Journal Papers

G. Solana-Lavalle, M. D. Cusimano, T. Steeves, R. Rosas-Romero, P. N. Tyrrell, "Causal forest machine learning analysis of Parkinson's disease in resting-state functional magnetic resonance imaging", Tomography, vol. 10, no. 6, pp. 894-911, 2024 (paper).
E. Guevara, G. Solana-Lavalle, R. Rosas-Romero, "Integrating fNIRS and machine learning: Shedding light on Parkinson's disease detection", EXCLI Journal - Experimental and Clinical Sciences, vol. 23, pp. 763-771, 2024 (paper).
Brenda Rangel-Olvera, R. Rosas-Romero, "Detection and classification of skin burns on color images using multi-resolution clustering and the classification of reduced feature subsets", Multimedia Tools and Applications, 2023 (paper).
Isabel Sarzo-Wabi, D. A. Galindo-Lazo, R. Rosas-Romero, "Feature extraction and classification of static spiral tests to assist the detection of Parkinson’s disease", Multimedia Tools and Applications, 2023 (paper).
J. C. Metri-Ojeda, G. Solana-Lavalle, R. Rosas-Romero, E. Palou, M. Ramírez-Rodrígues, D. Baigts-Allende, "Rapid screening of mayonaisse quality using computer vision and machine learning", Journal of Food Measurement and Characterization, vol. 17, no. 3, pp. 2792-2804, 2023 (paper).
D. Baigts-Allende, M. Ramírez-Rodrígues, R. Rosas-Romero, "Monitoring of the dehydration process of apple snacks with visual feature extraction and image processing techniques", Applied Sciences, vol. 12, no. 21:11269, pp. 1-13, 2022 (paper).
M. A. Jara-Maldonado, V. Alarcón-Aquino, R. Rosas-Romero, "A new machine learning model based on the broad learning system and wavelets", Journal of Engineering Applications of Artificial Intelligence, vol. 112, no. 104886, pp. 1-15, 2022 (paper).
B. Rangel-Olvera, R. Rosas-Romero, "Detection and classification of burnt skin via sparse representation of signals by over-redundant dictionaries", Computers in Biology and Medicine, vol. 132, no. 104310, pp. 1-9, 2021 (paper).
G. Solana-Lavalle, R. Rosas-Romero, "Analysis of voice as an assisting tool for detection of Parkinson's disease and its subsequent clinical interpretation", Biomedical Signal Processing and Control, vol. 66, no. 102415, pp. 1-11, 2021 (paper).
G. Solana-Lavalle, R. Rosas-Romero, "Classification of PPMI MRI scans with voxel-based morphometry and machine learning to assist in the diagnosis of Parkinson's disease", Computer Methods and Programs in Biomedicine, vol. 198, no. 105793, pp. 1-15, 2021 (paper).
M. A. Jara-Maldonado, V. Alarcón-Aquino, R. Rosas-Romero, O. Starostenko-Basarab, J. M. Ramírez-Cortés, "Transiting exoplanet discovery using machine learning techniques: A survey", Earth Science Informatics, vol. 13, no. 3, pp. 573-600, 2020 (paper).
G. Solana-Lavalle, J. C. Galán-Hernández, R. Rosas-Romero, "Automatic Parkinson disease detection at early stages as pre-diagnosis tool by using classifiers and a small set of vocal features", Biocybernetics and Biomedical Engineering, vol. 40, no. 1, pp. 505-516, 2020 (paper).
E. Guevara, J. A. Flores-Castro, K. Peng, D. K. Nguyen, F. Lesage, P. Pouliot, R. Rosas-Romero, "Prediction of epileptic seizures using fNIRS and machine learning", Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 2055-2068, 2020 (paper).
R. Rosas-Romero, E. Guevara, K. Peng, D. K. Nguyen, F. Lesage, P. Pouliot, E. W. Lima-Saad, "Prediction of epileptic seizures with convolutional neural networks and functional near-infrared spectroscopy signals", Computers in Biology and Medicine, vol. 111, no. 103355, 2019 (paper).
R. Rosas-Romero, O. López-Rincón, O. Starostenko-Basarab, "Fully automatic alpha matte extraction using artificial neural networks", Neural Computing & Applications, vol. 32, pp. 6843-6855, 2019 (paper).
O. Starostenko-Basarab, C. Pérez-Cruz, V. Alarcón-Aquino, R. Rosas-Romero, "Real-time facial expression recognition using local appearance-based descriptors", Journal of Intelligent & Fuzzy Systems, vol. 36, no. 5, pp. 5037-5049, 2019 (paper).
J. Hernández-Capistrán, J. Martínez-Carballido, R. Rosas-Romero, "False positive reduction by an annular model as a set of few features for microcalcification detection to assist early diagnosis of breast cancer", Journal of Medical Systems, vol. 42, no. 134, pp. 1-9, 2018 (paper).
L. Peralta-Malváez, O. López-Rincón, E. D. Rojas-Velázquez, L. O. Valencia-Rosado, R. Rosas-Romero, G. Etecheverry, "Newborn cry nonlinear features extraction and classification", Journal of Intelligent & Fuzzy Systems, vol. 34, no. 5, pp. 3281-3289, 2018 (paper).
R. Rosas-Romero, A. Díaz-Torres, G. Etcheverry, "Forecasting of stock return prices with sparse representation of financial time series over redundant dictionaries", Expert Systems with Applications, vol. 57, pp. 37-48, 2016 (paper).
R. Rosas-Romero, J. Martínez-Carballido, J. Hernández-Capistrán, L. J. Uribe-Valencia, "A method to assist in the diagnosis of early diabetic retinopathy: Image processing applied to detection of microaneurysms in fundus images", Computerized Medical Imaging and Graphics, vol. 44, pp. 41-53, 2015 (paper).
G. Castro-Muñoz, J. Martínez-Carballido, R. Rosas-Romero, "A human action recognition approach with a novel reduced feature set based on the natural domain knowledge of the human figure", Journal of Signal Processing: Image Communication, vol. 30, pp. 190-205, 2015 (paper).
R. Rosas-Romero, "Remote detection of forest fires from video signals with classifiers based on K-SVD learned dictionaries", Journal of Engineering Applications of Artificial Intelligence, vol. 33, pp. 1-11, 2014 (paper).
R. Rosas-Romero, H. D. Tagare, "Segmentation of endocardium in ultrasound images based on sparse representation over learned redundant dictionaries", Journal of Engineering Applications of Artificial Intelligence, vol. 29, pp. 201-210, 2014 (paper).

Book Chapters, Conference Talks & Publications

R. Rosas-Romero, P. Becerra-Vivanco, L. I. Castro-Pastrana, "A first-generation AI tool for antidepressant pharmacovigilance: Addressing data accessibility gaps in mental health care", 24th ISoP Annual Meeting "Pharmacovigilance: Back to the Future", Cairo, Egypt, 2025.
R. Rosas-Romero, "Image segmentation network based on convolutional layers, a clustering layer and cluster classification", Computer Applications in Industry and Engineering. CAINE 2024. Communications in Computer and Information Science, vol. 2242, pp. 167-175, 2025 (paper).
B. Rangel-Olvera, R. Rosas-Romero, "Detection and classification of burnt skin on images with sparse representation of image patches and dictionaries", Technology, Science and Culture: A Global Vision Volume IV, San Andrés Cholula, Puebla, México, 2023.
G. Solana-Lavalle, R. Rosas-Romero, "Analysis of voice and magnetic resonance images to assist diagnosis of Parkinson’s disease with machine learning", Technology, Science and Culture: A Global Vision Volume III, San Andrés Cholula, Puebla, México, 2020.
M. A. Jara-Maldonado, V. Alarcon-Aquino, R. Rosas-Romero, "Exoplanet research using machine learning and multiresolution analysis techniques", Technology, Science and Culture: A Global Vision Volume III, San Andrés Cholula, Puebla, México, 2020.
M. A. Jara-Maldonado, V. Alarcón-Aquino, R. Rosas-Romero, "A multiresolution machine learning technique to identify exoplanets", Mexican International Conference on Artificial Intelligence, Mexico City, Mexico, 2020.
M. A. Jara-Maldonado, V. Alarcon-Aquino, R. Rosas-Romero, "A multiresolution analysis technique to improve exoplanet identification", Exoplanets III, Heidelberg, Germany, 2020.
R. Rosas-Romero, Edgar Guevara, "Classification of functional near infra-red signals with machine learning for prediction of epilepsy", Proceedings of the 12th International Conference on Bioinformatics and Computational Biology (BICOB 2020), San Francisco, California, U. S. A., 2020.
R. Rosas-Romero, J. P. Medina-Ochoa, "Learning financial time series for prediction of the stock exchange market", Proceedings of the 34th International Conference on Computers and their Applications (CATA 2019), Honolulu, Hawaii, U. S. A., 2019.
R. Rosas-Romero, "Morphologic image processing for detection of micro-aneurysms in fundus images as pre-diagnosis of diabetic retinopathy", International Conference on Medical Imaging & Case Reports (MICR 2018), Baltimore, Maryland, U. S. A., 2018.
R. Rosas-Romero, "Detection of forest fires from video signals with sparse representation over dictionaries", Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017), San Diego, California, U. S. A., 2017.
A. Flores-Castro, K. Peng, D. K. Nguyen, F. Lesage, P. Pouliot, R. Rosas-Romero, E. Guevara, "Detecting epileptic seizures in advance using optical and electrical recordings", Proceedings of the 27th International Conference on Electronics, Communications and Computers (CONIELECOMP 2017), San Andrés Cholula, Puebla, México, 2017.
R. Rosas-Romero, O. López-Rincón, E. D. Rojas-Velázquez, N. P. Jacobo-Aispuro, "Learning matte extraction in green screen images with MLP classifiers and the back-propagation algorithm", Proceedings of the 26th International Conference on Electronics, Communications and Computers (CONIELECOMP 2016), San Andrés Cholula, Puebla, México, 2016.
R. Rosas-Romero, "Segmentation of endocardium in ultrasound images based on sparse representation over learned redundant dictionaries", 2015 Applied Imagery Pattern Recognition Workshop (AIPR 2015), Washington D. C., U. S. A., 2015.
R. Rosas-Romero, "A method to assist in the diagnosis of early diabetic retinopathy: Image processing applied to detection of microaneurysms in fundus images", 2015 Applied Imagery Pattern Recognition Workshop (AIPR 2015), Washington D. C., U. S. A., 2015.

Research

Methodology for PD detection and subsequent interpreting analysis of PD with rs-fMRI.

Causal forest machine learning analysis of Parkinson’s disease in resting-state functional magnetic resonance imaging

In recent years, Artificial Intelligence has been used to assist healthcare professionals in detecting and diagnosing neurodegenerative diseases. In this study, we propose a methodology to analyze functional Magnetic Resonance Imaging signals and perform classification between Parkinson’s disease patients and healthy participants with Machine Learning algorithms while providing information on the brain regions that are being affected. The functional Magnetic Resonance Imaging from the PPMI and 1000-FCP datasets were pre-processed, and time series from 200 regions were obtained for each participant, extracting 11600 features from the time series. Causal Forest and Wrapper Feature Subset Selection algorithms were used for dimensionality reduction, resulting in a subset of features based on their heterogeneity and association with the disease. Logistic regression and XGBoost algorithms were used to perform classification. Finally, Multiple Correspondence Analysis was used to visualize the relationships between brain regions and each group. Classification of signals as Parkinson’s Disease positive or negative was above 92% in accuracy, 92.4% in F1 score, 93.8% in precision, 92.3% in recall, and 98.6% in AUC by analyzing sets with less than 300 features. Multiple Correspondence Analysis was used to project the associations between brain regions and the groups. These associations were also obtained using the Unified Parkinson’s Disease Rating Scale questionnaire. This work proposes a methodology to (1) classify patients and controls with high accuracy using Machine Learning and Causal Forest and (2) increase the interpretability of results by visualizing associations between brain regions and groups.

Collaboration with Michael D. Cusimano, Thomas Steeves, Pascal N. Tyrrell (University of Toronto).

Publication: G. Solana-Lavalle, M. D. Cusimano, T. Steeves, R. Rosas-Romero, P. N. Tyrrell, "Causal forest machine learning analysis of Parkinson's disease in resting-state functional magnetic resonance imaging", Tomography, vol. 10, no. 6, pp. 894-911, 2024 (paper).

Methodology for PD detection by analyzing fNIRS signals from participants. The methodology consists of four states: feature extraction, feature pre-processing, feature selection and feature classification.

Integrating fNIRS and machine learning: Shedding a light on Parkinson's disease detection

The purpose of this research is to introduce an approach to assist the diagnosis of Parkinson’s disease (PD) by classifying functional near infra-red spectroscopy (fNIRS) studies as PD positive or negative. fNIRS is a non-invasive optical signal modality that conveys the brain’s hemodynamic response, specifically changes in blood oxygenation in the cerebral cortex; and its potential as a tool to assist PD detection deserves to be explored since it is non-invasive and cost-effective as apposed to other neuroimaging modalities. Besides the integration of fNIRS and machine learning, a contribution of this work is that various approaches were implemented and tested to find the implementation that achieves the highest performance. All the implementations used a logistic regression model for classification. A set of 792 temporal and spectral features were extracted from each participant’s fNIRS study. In the two best performing implementations, an ensemble of feature-ranking techniques was used to select a reduced feature subset, which was subsequently reduced with a genetic algorithm. The best detection performance achieved was accuracy of 100%, precision of 100 %, recall of 100 %, F1 score of 1, area under the curve of 1 by using 14 features.

Publication: E. Guevara, G. Solana-Lavalle, R. Rosas-Romero, "Integrating fNIRS and machine learning: Shedding light on Parkinson's disease detection", EXCLI Journal - Experimental and Clinical Sciences, vol. 23, pp. 763-771, 2024 (paper).

Stages for detection and classification of burnt skin on color images.

Detection and classification of skin burns on color images using multi-resolution clustering and the classification of reduced feature subsets

The detection of skin burns on color images and their corresponding classification to identify their intensity degree are useful tools for automatic assistance in emergencies in which clinical experience is not available. In this work, the analysis of images with skin burns starts with multiresolution processing to identify non-homogeneous regions that contain these lesions. Subsequently, segmentation within the non-homogeneous region is performed with k-means so that these regions are divided into unlabeled clusters. Finally, each unclassified cluster is assigned one of six classes; healthy skin, first-degree burn, second-degree burn, third-degree burn, shadowed skin, background. Four classification models are used; k-nearest neighbors, multi-layer perceptron, linear discriminant analysis, and support vector machine. There is a very large amount of available features that can be associated with skin analysis, but only a few of them are substantially associated with the classification of skin as being burnt or not, and with the burn degree. A contribution of this work is the selection of relevant features for each of two tasks: (1) segmentation of the regions of interest into clusters and (2) classification of each cluster to detect and classify burns. According to the selected features, the best detection and classification performance metrics are 95.65% sensitivity and 94.83% precision.

Collaboration with Edgar Guevara (Universidad Autónoma de San Luis Potosí).

Publication: B. Rangel-Olvera, R. Rosas-Romero, "Detection and classification of skin burns on color images using multi-resolution clustering and the classification of reduced feature subsets", Multimedia Tools and Applications, 2023 (paper).

Stages of the proposed approach for PD detection based on the analysis of spiral drawings.

Feature extraction and classification of static spiral tests to assist the detection of Parkinson’s disease

Analyses of spiral drawings have been carried out in clinics to study and assist the diagnosis of Parkinson’s Disease (PD), the second most common neurodegenerative disorder in people at their 60’s. The purpose of this research is to propose an approach to classify static spiral drawings, as an assisting tool for PD diagnosis using a simple data set obtained from a balanced population of patients with PD and controls. In this study, analyses were conducted on pictures of drawings, an affordable technological application, specially in small clinics where neither resources, such as tablets, nor specialists are available. The most significant contribution of this work lies on the extraction and selection of features. Five feature groups are used to characterize the natural process of tracing a spiral for both PD patients and controls. These groups convey information related to the trace movement on the plane, trace pressure, texture, frequency content, and morphology. Furthermore, the number of features is reduced by searching for the best feature subset. Three classifiers are used: k-nearest neighbors, multilayer perceptron, and support vector machine. The best detection performance achieved is 86.67% of accuracy, 80.00% of sensitivity, 100% of specificity, 100% of positive predictive value, and 82.35% of negative predictive value.

Publication: I. Sarzo-Wabi, D. A. Galindo-Lazo, R. Rosas-Romero, "Feature extraction and classification of static spiral tests to assist the detection of Parkinson’s disease", Multimedia Tools and Applications, 2023 (paper).

Image processing methodology for feature extraction: image acquisition (A), conversion of the image into a grayscale color map and segmentation (B), superimposing and color conversions (C), and feature extraction (D).

Rapid screening of mayonnaise quality using computer vision and machine learning

Implementing reliable, fast, and low-cost analysis is gaining popularity in the food industry. One alternative for this type of analysis is an artificial intelligence based on image analysis. This study aimed to use image analysis to develop classification models for discriminating the acceptability of mayonnaises. A semi-trained panel comprised of 8 evaluators classified 300 pictures of mayonnaises. Features extracted from the images include the mean, standard deviation, minimum and maximum intensity values, skewness, and kurtosis from Red–Green–Blue (RGB), Hue-Saturation-Value (HSV), and the Commission Internationale d’Eclairage L* a* b* (CIELab) color spaces. Haralick Features and the intensity differences between the region of interest and the background were calculated using gray-level intensity values. A Support Vector Machine (SVM), Gradient Boosting, and K-Nearest Neighbors (KNN) models were used and evaluated in terms of accuracy, precision, recall, and F1-measure with tenfold cross-validation. Color features revealed to be the most important data for the models; these models demonstrated 92.60–93.30% accuracy, 89.00–93.30% precision, 91.40–96.43% recall, and 91.90–92.30% F1-measure. Tested models showed similar results among them. Every tested model did not exhibit significant difference compared to the panel, which presented 88.33, 94.37, 93.54, and 93.75% of accuracy, precision, recall, and F1-measure, respectively. The models obtained herein, showed to be a possible approach for a fast, low-cost, and simple methodology to estimate the acceptability of mayonnaise in sensory analysis or shelf-life studies.

Collaboration with Diana Karina Baigts-Allende (Czech University of Life Sciences Prague) & Milena Ramírez-Rodrígues (ITESM).

Publication: J. C. Metri-Ojeda, G. Solana-Lavalle, R. Rosas-Romero, E. Palou, M. Ramírez-Rodrígues, D. Baigts-Allende, "Rapid screening of mayonaisse quality using computer vision and machine learning", Journal of Food Measurement and Characterization, vol. 17, no. 3, pp. 2792-2804, 2023 (paper).

General overview of the computer vision methodology.

Monitoring of the dehydration process of apple snacks with visual feature extraction and image processing techniques

Monitoring food processing is mandatory for controlling and ensuring product quality. Most of the used techniques are destructive, arduous, and time-consuming. Non-destructive analyses are convenient for rapid and conservative food quality assessment. Color images of apple slices during the manufacturing of healthy snacks were used for monitoring the drying processing. The implementation of the image-based analysis was straightforward, feasible, and low-cost. The parameters analyzed during image acquisition for normalizing were: contrast enhancement, binarization, and morphologic processing, varying the illumination and reference between the positions of the camera and object under analysis. Several apple features related to color, texture, and shape were extracted with computer vision techniques and also analyzed. During image analysis, the entropy was one of the most relevant computed features according to principal component analysis, and it was also relevant in terms of physical interpretation. The average percentage of entropy increase was 19.81% in the green and blue channels, while it was 16.82% in the red channel. Other relevant visual features were the skewness and kurtosis in the RGB channels; and textural information such as contrast, correlation, and variance.

Collaboration with Diana Karina Baigts-Allende (Czech University of Life Sciences Prague) & Milena Ramírez-Rodrígues (ITESM).

Publication: D. Baigts-Allende, M. Ramírez-Rodrígues, R. Rosas-Romero, "Monitoring of the dehydration process of apple snacks with visual feature extraction and image processing techniques", Applied Sciences, vol. 12, no. 21:11269, pp. 1-13, 2022 (paper).

Proposed Wavelet-Based Broad Learning System (WABBLES) architecture.

A new machine learning model based on the broad learning system and wavelets

In this work, a new neural network named WAvelet-Based Broad LEarning System (WABBLES) is presented. WABBLES is based on the flat structure of the broad learning system. Such structure offers an alternative to deep learning models, such as convolutional neural networks. The WABBLES network uses multiresolution analysis to look for subtle, yet important features from the input data for a better classification performance. WABBLES uses wavelets to map the input signal, to obtain more relevant features from it. This is achieved by autonomously learning and adjusting the dilation and translation parameters of a wavelet, which controls its shape. In this way, the resulting mapping nodes have a better representation of the most important features for the classification problem. The construction of the model is described here, along with special considerations and algorithms involved. Finally, the proposed model is tested using a database of synthetic astronomical data and a benchmark dataset called the Breast Cancer Wisconsin Dataset. The conducted experiments provide a comparison between the proposed model and several machine learning algorithms with different performance metrics applied to the context of exoplanet identification and breast cancer detection. Our results confirm that the WABBLES model obtains superior accuracy and F-score percentages than the other models.

Collaboration with Miguel Jara-Maldonado & Dr. Vicente Alarcón-Aquino (UDLAP).

Publication: M. A. Jara-Maldonado, V. Alarcón-Aquino, R. Rosas-Romero, "A new machine learning model based on the broad learning system and wavelets", Journal of Engineering Applications of Artificial Intelligence, vol. 112, no. 104886, pp. 1-15, 2022 (paper).

Video_Coloquio_2021.mp4

Detection and classification of burnt skin via sparse representation of signals by over-redundant dictionaries

Skin burns in color images must be accurately detected and classified according to burn degree in order to assist clinicians during diagnosis and early treatment. Especially in emergency cases in which clinical experience might not be available to conduct a thorough examination with high accuracy, an automated assessment may benefit patient outcomes. In this work, detection and classification of burnt areas are performed by using the sparse representation of feature vectors by over-redundant dictionaries. Feature vectors are extracted from image patches so that each patch is assigned to a class representing a burn degree. Using color and texture information as features, detection and classification achieved 95.65% sensitivity and 94.02% precision. Experiments used two methods to build dictionaries for burn severity classes to apply to observed skin regions: (1) direct collection of feature vectors from patches in various images and locations and (2) collection of feature vectors followed by dictionary learning accompanied by K-singular value decomposition.

Publications: B. Rangel-Olvera, R. Rosas-Romero, "Detection and classification of burnt skin via sparse representation of signals by over-redundant dictionaries", Computers in Biology and Medicine, vol. 132, no. 104310, pp. 1-9, 2021 (paper).

B. Rangel-Olvera, R. Rosas-Romero, "Detection and classification of burnt skin on images with sparse representation of image patches and dictionaries", Technology, Science and Culture: A Global Vision Volume IV, San Andrés Cholula, Puebla, México, 2021.

Proposed approach.

DSI Gabriel Solana Lavalle.mp4

Classification of PPMI MRI scans with voxel-based morphometry and machine learning to assist in the diagnosis of Parkinson’s disease

Qualitative and quantitative analyses of Magnetic Resonance Imaging (MRI) scans are carried out to study and understand Parkinson disease (PD), the second most common neurodegenerative disorder in people at their 60’s. Some quantitative analyses are based on the application of voxel-based morphometry (VBM) on magnetic resonance (MR) images to determine the regions of interest (ROIs), within gray matter, where there is a loss of the nerve cells that generate dopamine. This loss of dopamine is indicative of PD. The contribution of this research is the introduction of a new method to classify the 3-D MRI scans of an individual, as an assisting tool for PD diagnosis by using the largest MRI dataset (Parkinson’s Progression Markers Initiative - PPMI) from a population of PD patients and control individuals. Previous to classification, VBM is conducted on MR images to detect the regions where features are extracted by using first- and second-order statistics histograms. Furthermore, the number of features is considerably reduced by using feature selection techniques. Seven classifiers are used and we are conducting separate experiments for men and women. The best detection performance achieved in men was 99.01% of accuracy, 99.35% of sensitivity, 100% of specificity, and 100% of precision. The best detection performance achieved in women is 96.97% of accuracy, 100% of sensitivity, 96.15% of specificity, and 97.22% of precision. During classification of MR images, the corresponding computational complexity is reduced since few features are selected. While previous works have focused their analysis to the striatum region of the brain, the proposed approach is based on analysis over the whole brain by looking for decreases of tissue thickness, with the consequence of finding other regions of interest such as the cortex.

Publication: G. Solana-Lavalle, R. Rosas-Romero, "Classification of PPMI MRI scans with voxel-based morphometry and machine learning to assist in the diagnosis of Parkinson's disease", Computer Methods and Programs in Biomedicine, vol. 198, no. 105793, pp. 1-15, 2021 (paper).

Overview of the proposed approach.

Illustration of different states (pre-ictal, ictal, inter-ictal) in one single EEG channel, one HbO channel, and one HbR channel, extracted from an epileptic patient.

Prediction of epileptic seizures based on convolutional neural networks (CNN) and functional Near-Infra Red Spectroscopy (fNIRS) signals

This work presents the implementation of the learning algorithm for a Deep Learning Machine (DLM), specifically, a Convolutional Neural Network (CNN), which is effectively applied to the prediction of epileptic seizures from functional Near-Infrared Spectroscopy (fNIRS) recordings, an optical modality for recording of brain waves. A CNN is suitable for this application, instead of other learning machines, since fNIRS recordings are characterized by very high dimensionality, given that there are hundreds of fNIRS channels and that at any time position these signals are represented as two-dimensional tensors. The training of the CNN is based on the back propagation algorithm to update kernel weights in convolutional layers and synaptic weights in classification layers. This work presents the required formulations to update weights over all the layers of the network. Application of CNN to fNIRS recordings showed an accuracy ranging between 96.9% and 100%, depending on the subject. The most important aspect of obtaining these results is the combination of fNIRS signals with the particular CNN algorithm. This signal modality has not been used in epileptic seizure prediction and this work pretends to be one of the first to use this modality and deep learning to address the problem of seizure prediction.

Collaboration with Dr. Edgar Guevara (CONACYT - UASLP), Dr. Frédéric Lesage (Ecole Polytechnique de Montréal), Dr. Philippe Pouliot (Ecole Polytechnique de Montréal), Dr. Dang Khoa Nguyen (Hôpital Notre-Dame du CHUM), Dr. Ke Peng (École Polytechnique Montréal de Montréal).

Publications: E. Guevara, J. A. Flores-Castro, K. Peng, D. K. Nguyen, F. Lesage, P. Pouliot, R. Rosas-Romero, "Prediction of epileptic seizures using fNIRS and machine learning", Journal of Intelligent & Fuzzy Systems, vol. 38, no. 2, pp. 2055-2068, 2020 (paper).

R. Rosas-Romero, E. Guevara, K. Peng, D. K. Nguyen, F. Lesage, P. Pouliot, E. W. Lima-Saad, "Prediction of epileptic seizures with convolutional neural networks and functional near-infrared spectroscopy signals", Computers in Biology and Medicine, vol. 111, no. 103355, 2019 (paper).

R. Rosas-Romero, Edgar Guevara, "Classification of functional near infra-red signals with machine learning for prediction of epilepsy", Proceedings of the 12th International Conference on Bioinformatics and Computational Biology (BICOB 2020), San Francisco, California, U. S. A., 2020.

A. Flores-Castro, K. Peng, D. K. Nguyen, F. Lesage, P. Pouliot, R. Rosas-Romero, E. Guevara, "Detecting epileptic seizures in advance using optical and electrical recordings", Proceedings of the 27th International Conference on Electronics, Communications and Computers (CONIELECOMP 2017), San Andrés Cholula, Puebla, México, 2017.

Overview of the proposed method.

Automatic Parkinson’s disease detection at early stages as a pre-diagnosis tool by using classifiers and a reduced subset of relevant vocal features

Recent research on Parkinson Disease (PD) detection has shown that vocal disorders are linked to symptoms of PD patients at an early stage. Thus, there is an interest in applying vocal features to the remote diagnosis and monitoring of patients with PD at early stages. The objective of this research is to increase vocal-based PD detection performance while using the newest and largest public dataset available by selecting an optimal and very reduced set of vocal features. The number of features range from 8 to 20 after using Wrappers feature subset selection. An ensemble of four classifiers (k Nearest Neighbor, Multi-Layer Perceptron, Support Vector Machine and Random Forest) is applied to vocal-based PD detection. The proposed approach showed an accuracy of 94.7%, sensitivity of 98.4%, specificity of 92.68%, precision of 97.22%, MCC of 86.86%, and F1 score of 96.33%.

Publications: G. Solana-Lavalle, R. Rosas-Romero, "Analysis of voice as an assisting tool for detection of Parkinson's disease and its subsequent clinical interpretation", Biomedical Signal Processing and Control, vol. 66, no. 102415, pp. 1-11, 2021 (paper).

G. Solana-Lavalle, J. C. Galán-Hernández, R. Rosas-Romero, "Automatic Parkinson disease detection at early stages as pre-diagnosis tool by using classifiers and a small set of vocal features", Biocybernetics and Biomedical Engineering, vol. 40, no. 1, pp. 505-516, 2020 (paper).

Example of a light curve. As the exoplanet orbits the star, different brightness values are obtained.

DSI Miguel Angel Jara Maldonado.mp4

Transiting exo-planet identification using machine learning techniques

Spatial missions such as the Kepler mission, and the Transiting Exoplanet Survey Satellite (TESS) mission, have encouraged data scientists to analyze light curve datasets. The purpose of analyzing these data is to look for planet transits, with the aim of discovering and validating exoplanets, which are planets found outside our Solar System. Furthermore, transiting exoplanets can be better characterized when light curves and radial velocity curves are available. The manual examination of these datasets is a task that requires big quantities of time and effort, and therefore is prone to errors. As a result, the application of machine learning methods has become more common on exoplanet discovery and categorization research. This research focuses on the analysis on different exoplanet transit discovery algorithms based on machine learning, some of which even found new exoplanets. The analysis of these algorithms is organized in four steps, namely light curve preprocessing, possible exoplanet signal detection, and identification of the detected signal to decide whether it belongs to an exoplanet or not. This work concludes that multiresolution analysis in the time-frequency domain can improve exoplanet signal identification, because of the characteristics of light curves and transiting exo-planet signals.

Collaboration with Miguel Jara-Maldonado & Dr. Vicente Alarcón-Aquino (UDLAP).

Publications: M. A. Jara-Maldonado, V. Alarcón-Aquino, R. Rosas-Romero, "A new machine learning model based on the broad learning system and wavelets", Journal of Engineering Applications of Artificial Intelligence, vol. 112, no. 104886, pp. 1-15, 2022 (paper).

M. A. Jara-Maldonado, V. Alarcón-Aquino, R. Rosas-Romero, O. Starostenko-Basarab, J. M. Ramírez-Cortés, "Transiting exoplanet discovery using machine learning techniques: A survey", Earth Science Informatics, vol. 13, no. 3, pp. 573-600, 2020 (paper).

M. A. Jara-Maldonado, V. Alarcón-Aquino, R. Rosas-Romero, "A multiresolution machine learning technique to identify exoplanets", Mexican International Conference on Artificial Intelligence, 2020.

M. A. Jara-Maldonado, V. Alarcon-Aquino, R. Rosas-Romero, "A multiresolution analysis technique to improve exoplanet identification", Exoplanets III, Heidelberg, Germany, 2020.

Results of fully-automatic alpha matte extraction and compositing of extracted foreground on new background scenes.

Application for alpha matte extraction from green screen images. The application includes the training of a neural network and the extraction of alpha matte and foreground.

Fully automatic alpha matte extraction in green screen images using artificial neural networks

The alpha matte is a two-dimensional map that is used to combine two images, one containing a foreground and the other containing a background, a process known as digital compositing. Alpha matte extraction is performed on green-screen images and requires user interaction to tune parameters in different pre-processing and post-processing stages to refine an alpha matte. This work tackles the problem of fully automatic extraction of the foreground on a green screen image along with the extraction of the corresponding alpha matte, a process also known as pulling a matte. The method is based on learning machine that assigns an alpha value, from a discrete set of ten alpha values, to each patch on a green-screen image. The approach for assigning an alpha value to a patch is based on a set of features that enhance discrimination between foreground and background. Prior to alpha matte extraction, the classifier is trained to learn to separate foreground objects from green screen backgrounds as well as to generate the corresponding alpha matte map required for subsequent digital compositing. We tested the proposed method on high-definition (HD) green screen images, corresponding to two different sequence cases (TOY CAR ROTO & GODIVA MEDIUM), both cases from a public data set provided by Hollywood Camera Work LLC. HD green screen images, from each particular case, have limitations that are not good enough for film production. In addition, a data set with 64 images was generated to test how the proposed approach handles alpha matte extraction under unsuitable conditions such as short separation distance between the subject and the green screen. The project also provides, for the case of the public data set, a quantitative comparison between the alpha matte, extracted by means of the proposed approach, and that generated by the application Adobe After Effects CC, which has the disadvantage of demanding a large amount of user interaction.

Collaboration with Omar López-Rincón & Dr. Oleg Starostenko-Basarab (UDLAP).

Publications: R. Rosas-Romero, O. López-Rincón, O. Starostenko-Basarab, "Fully automatic alpha matte extraction using artificial neural networks", Neural Computing & Applications, vol. 32, pp. 6843-6855, 2019 (paper).

R. Rosas-Romero, O. López-Rincón, E. D. Rojas-Velázquez, N. P. Jacobo-Aispuro, "Learning matte extraction in green screen images with MLP classifiers and the back-propagation algorithm", Proceedings of the 26th International Conference on Electronics, Communications and Computers (CONIELECOMP 2016), San Andrés Cholula, Puebla, México, 2016.

Cumulative return gain curves obtained by following a predictive model based on an artificial predictor (orange) vs. the market (blue).

Forecasting of stock return prices with sparse representation of financial time series over redundant dictionaries

This project introduces the theory, methodology and application of a new predictive model for time series within the financial sector, specifically data from 20 companies listed on the U. S. stock exchange market. The proposed method is based on learned redundant dictionaries for sparse representation of financial time series. The methodology is conducted by finding the optimal set of atoms for the predicting model following two directions for the generation of dictionaries; by extraction of atoms from past daily return price values to build untrained dictionaries and by atom extraction followed by training of dictionaries through K-SVD (K - Singular Value Decomposition). Prediction of financial time series is a periodic process where each cycle consists of two stages: (1) training of the model to learn the dictionary that maximizes the probability of occurrence of an observation sequence of return values, (2) prediction of the return value for the next coming trading day. After prediction, the two stages are alternatively repeated by using an adjusted sequence of observations that adds the newest observed return value and drops the oldest observed return value from the sequence (window shift). The motivation for such research is the fact that a tool, which might generate confidence of the potential benefits obtained from using formal financial services, would encourage more participation in a formal system such as the stock market. Theory, issues, challenges and results related to the application of sparse representation to the prediction of financial time series, as well as the performance of the method, are presented.

Publications: R. Rosas-Romero, A. Díaz-Torres, G. Etcheverry, "Forecasting of stock return prices with sparse representation of financial time series over redundant dictionaries", Expert Systems with Applications, vol. 57, pp. 37-48, 2016 (paper).

R. Rosas-Romero, J. P. Medina-Ochoa, "Learning financial time series for prediction of the stock exchange market", Proceedings of the 34th International Conference on Computers and their Applications (CATA 2019), Honolulu, Hawaii, U. S. A., 2019.

Original image (upper panel) and result of detection of candidates to micro-aneurysms (lower panel).

A method to assist in the diagnosis of early diabetic retinopathy: Image processing applied to detection of microaneurysms in fundus images

Diabetes increases the risk of developing any deterioration in the blood vessels that supply the retina, an ailment known as Diabetic Retinopathy (DR). Since this disease is asymptomatic, it can only be diagnosed by an ophthalmologist. However, the growth of the number of ophthalmologists is lower than the growth of the population with diabetes so that preventive and early diagnosis is difficult due to the lack of opportunity in terms of time and cost. Preliminary, affordable and accessible ophthalmological diagnosis will give the opportunity to perform routine preventive examinations, indicating the need to consult an ophthalmologist during a stage of non-proliferation. During this stage, there is a lesion on the retina known as microaneurysm (MA), which is one of the first clinically observable lesions that indicate the disease. In recent years, different image processing algorithms, which allow the detection of the DR, have been developed; however, the issue is still open since acceptable levels of sensitivity and specificity have not yet been reached, preventing its use as a pre-diagnostic tool. Consequently, this work introduces a new approach for MA detection based on (1) reduction of non-uniform illumination; (2) normalization of image grayscale content to improve dependence of images from different contexts; (3) application of the bottom-hat transform to leave reddish regions intact while suppressing bright objects; (4) binarization of the image of interest with the result that objects corresponding to MAs, blood vessels, and other reddish objects (Regions of Interest - ROIs) are completely separated from the background; (5) application of the hit-or-miss Transformation on the binary image to remove blood vessels from the ROIs; (6) two features are extracted from a candidate to distinguish real MAs from FPs, where one feature discriminates round shaped candidates (MAs) from elongated shaped ones (vessels) through application of Principal Component Analysis (PCA); (7) the second feature is a count of the number of times that the radon transform of the candidate ROI, evaluated at the set of discrete angle values {0°, 1°, 2°, …, 180°}, is characterized by a valley between two peaks. The proposed approach is tested on the public databases DiaretDB1 and Retinopathy Online Challenge (ROC) competition. The proposed MA detection method achieves sensitivity, specificity and precision of 92.32%, 93.87% and 95.93% for the diaretDB1 database and 88.06%, 97.47% and 92.19% for the ROC database. Theory, results, challenges and performance related to the proposed MA detecting method are presented.

Collaboration with Dr. Jorge Martínez-Carballido (INAOE).

Publications: R. Rosas-Romero, J. Martínez-Carballido, J. Hernández-Capistrán, L. J. Uribe-Valencia, "A method to assist in the diagnosis of early diabetic retinopathy: Image processing applied to detection of microaneurysms in fundus images", Computerized Medical Imaging and Graphics, vol. 44, pp. 41-53, 2015 (paper).

R. Rosas-Romero, "Morphologic image processing for detection of micro-aneurysms in fundus images as pre-diagnosis of diabetic retinopathy", International Conference on Medical Imaging & Case Reports (MICR 2018), Baltimore, Maryland, U. S. A., 2018.

Monitoring System for Remote Detection of Forest Fires.

Smoke detection under high illumination.

Remote detection of forest fires from video signals with classifiers based on K-Singular Value Decomposition (K-SVD) learned dictionaries

In this project a method for remote detection of forest fires in video signals from surveillance cameras is introduced. The idea is based on learned redundant dictionaries for sparse representation of feature vectors extracted from image patches on three different regions; smoke, sky and ground. A testing image patch is assigned to the region for which the corresponding dictionary gives the best sparse representation during segmentation. To further reduce the presence of misclassified patches, a spatio-temporal cuboid of patches is built around a classified patch to take a majority vote in the set of classes inside the cuboid. To reduce the number of false positives there is a verification process to determine if a region of interest is growing. Theory, results, issues and challenges related to the implementation of the forest fire monitoring system, and performance of the method are presented.

Publications: R. Rosas-Romero, "Remote detection of forest fires from video signals with classifiers based on K-SVD learned dictionaries", Journal of Engineering Applications of Artificial Intelligence, vol. 33, pp. 1-11, 2014 (paper).

R. Rosas-Romero, "Detection of forest fires from video signals with sparse representation over dictionaries", Proceedings of the 30th International Conference on Computer Applications in Industry and Engineering (CAINE 2017), San Diego, California, U. S. A., 2017.

Results of segmentation based on sparse representation: Original Image (above) & Segmented Image (bellow).

Segmentation of endocardium in ultrasound images based on sparse representation over learned redundant dictionaries

This project tackles the problem of segmenting the endocardium in 2-D short-axis echocardiographic images from rats by using the sparse representation of feature vectors over learned dictionaries during classification. We highlight important aspects of the application of the theory of sparse representation and dictionary learning to the problem of ultrasound image segmentation. Experiments were conducted following two directions for the generation of dictionaries for myocardium and blood pool regions; by manual extraction of image patches to build untrained dictionaries and by patch extraction followed by training of dictionaries. The results obtained from different learned dictionaries are compared. During classification of an image patch, instead of using features of the patch alone, features of neighboring patches are combined.

Collaboration with Dr. Hemant D. Tagare (Yale University).

Publication: R. Rosas-Romero, H. D. Tagare, "Segmentation of endocardium in ultrasound images based on sparse representation over learned redundant dictionaries", Journal of Engineering Applications of Artificial Intelligence, vol. 29, pp. 201-210, 2014 (paper).

Overview of the proposed human action recognition method: extraction and tracking of regions of interest, feature extraction and classification.

Representation of a silhouette as three rectangular regions.

Outline of the bounding box tracker.

A human action recognition approach with a reduced feature set based on the natural domain knowledge of the human figure

Current video surveillance systems are not designed to raise an automatic alert in case of situations that put people lives at risk such as accidents, assaults and terrorism among others. This is due to the fact that these systems are not able to analyze huge amounts of video signals at higher processing speed where these signals come from cameras installed in the worldwide network. Faced with this situation, scientific communities are combining efforts to design algorithms and hardware to accelerate the processing of video signals. However, most of the methods proposed to date are too complex to be implemented in hardware at the place where the video camera is installed. In this paper, we report a significantly reduced feature set to design an analysis algorithm of significant less complexity which recognizes human actions from video sequences. The proposed method is based on the natural domain knowledge of the human figure such as proportions of the human body and foot positions. The analysis is characterized by working on sub-sequences of the entire video signals, processing a small fragment of the whole image, estimating the location of the region of interest, using simple operations (sum, subtraction, multiplications, divisions), extracting a reduced number of features per frame (6 features), and using a combination of four linear classifiers (one perceptron and three support vector machines) with a hierarchical structure. The method is evaluated on two of the datasets cited in the human action recognition literature, the Weizmann and the UIUC datasets. Results show that for the case of the Weizmann dataset, the correct classification rate (CCR) is 99.95% when the LOOCV Protocol is used and 98.38% for the case of Protocol 60-40, which is comparable or even higher than that of current state-of-the-art methods. Confusion matrices were also obtained for the UIUC dataset, where the obtained CCR is 100% for the case of the LOOCV Protocol and 99.35% when Protocol 60-40 is used. The experimental results are promising with much fewer features (between 85 and 113 times less features), compared with other methods, and the possibility of processing more than 200 fps.

Collaboration with Dr. Jorge Martínez-Carballido (INAOE).

Publication: G. Castro-Muñoz, J. Martínez-Carballido, R. Rosas-Romero, "A human action recognition approach with a novel reduced feature set based on the natural domain knowledge of the human figure", Journal of Signal Processing: Image Communication, vol. 30, pp. 190-205, 2015 (paper).

Stages for detection of micro-calcifications as a tool to assist in diagnosis of breast cancer: cluster identification, segmentation, binarization, feature extraction, and classification .

False positive reduction by an annular model as a set of few features for microcalcification detection to assist early diagnosis of breast cancer

Early automatic breast cancer detection from mammograms is based on the extraction of lesions, known as microcalcifications (MCs). This research proposes a new and simple system for microcalcification detection to assist in early breast cancer detection. This work uses the two most recognized public mammogram databases, MIAS and DDSM. The MC detection method is based on (1) Beucher gradient for detection of regions of interest (ROIs), (2) an annulus model for extraction of few and effective features from candidates to MCs, and (3) one classification stage with two different classifiers, k Nearest Neighbor (KNN) and Support Vector Machine (SVM). For dense mammograms in the MIAS database, the performance metrics achieved are sensitivity of 0.9835, false alarm rate of 0.0083, accuracy of 0.9835, and area under the ROC curve of 0.9980 with a KNN classifier. The proposed MC detection method, based on a KNN classifier, achieves, a sensitivity, false positive rate, accuracy and area under the ROC curve of 0.9813, 0.0224, 0.9795 and 0.9974 for the MIAS database; and 0.9035, 0.0439, 0.9298 and 0.9759 for the DDSM database. By slightly reducing the true positive rate the method achieves three instances with false positive rate of 0:2 on fatty mammograms with KNN and SVM, and one on dense with SVM. The proposed method gives better results than those from state of the art literature, when the mammograms are classified in fatty, fatty-glandular, and dense.

Collaboration with Dr. Jorge Martínez-Carballido (INAOE).

Publication: J. Hernández-Capistrán, J. Martínez-Carballido, R. Rosas-Romero, "False positive reduction by an annular model as a set of few features for microcalcification detection to assist early diagnosis of breast cancer", Journal of Medical Systems, vol. 42, no. 134, pp. 1-9, 2018 (paper).

Interests

Academy Awards

Photography Gallery 1, Photography Gallery 2, Photography Gallery 3, Photography Gallery 4

Photography Gallery 5, Photography Gallery 6, Photography Gallery 7, Photography Gallery 8

Google Sites

Report abuse