Ulisses de Mendonça Braga-Neto, Ph.D.
Our Germany 2018 Study Abroad program for Engineering undergraduate
students is accepting applications. The official program brochure is located here. For additional information on the program, please access our program presentation slides.
Our project "Minimum Mean Square Error Estimation and Control of Partially Observed Boolean Dynamical Systems with Applications in Metagenomics"
has been funded by a 3-year NSF CIF Award (starting August 2017). The project aims to develop and apply innovative signal processing techniques to uncover the complex interactions among microbes, human cells and their metabolic products in the gut. The main tools to be used and developed are the optimal MMSE Boolean Kalman Filter and Smoother algorithms for Partially-Observed Boolean Dynamical Systems (POBDS), along with maximum-likelihood and Bayesian parameter estimation methods, and stochastic control techniques for optimal sequential intervention design. This project is supported at Texas A&M by an interdisciplinary team consisting of Dr. Robert S. Chapkin (Nutrition and Food Science), Dr. Arul Jayaraman (Department of Chemical Engineering), Dr. Xiaoning Qian (Electrical and Computer Engineering) and Dr. Ivan Ivanov (Veterinary Physiology and Pharmacology). Dr. Johanna W. Lampe (Fred Hutchinson Cancer Research Center, Seattle, WA) is an external collaborator. More information here.
Our R Package BoolFilter,
co-authored by L.D. McClenny, M. Imani and U.M. Braga-Neto, has been
published by CRAN. BoolFilter implements algorithms for
Partially-Observed Boolean Dynamical Systems (POBDS), a Hidden Markov
Model that extends the Boolean Network model to include noisy indirect
observations, with applications in Genomic Signal
Processing. BoolFilter allows the user to estimate the hidden
Boolean states using the Boolean Kalman Filter and Smoother, as well
as infer network topology and noise parameters, from time series
transcriptomic data using exact or approximate (particle) filters, as
well as simulate time series transcriptomic data for a given Boolean
network model. (Jan 2017)
Dr. Braga-Neto has been elected to the Machine Learning for Signal
Processing Technical Committee (MLSP TC) of the Institute of
Electrical and Electronics Engineers (IEEE) Signal Processing Society
for the 2017-2019 term. The committee is at the interface between
theory and application, developing novel theoretically inspired
methodologies targeting both longstanding and emergent signal
processing applications. Central to MLSP is online/adaptive nonlinear
signal processing and data-driven learning methodologies. The IEEE
MLSP TC is expected to play a central role in the next few years in
shaping the IEEE policies and approaches to Big Data. (Oct 2016)
Link to News Item
Our book "Error Estimation for Pattern
Recognition", co-authored with Ed Dougherty, has been published by
This book is the first one dedicated exclusively to the topic of error
estimation for pattern recognition. It covers both classical and
recent results on the performance of error estimators for nonparametric and parametric classifiers.
For a sample, including table of contents and subject index, please access the publisher's website or Google Books.
The book is also available from amazon.com and barnesandnoble.com. (July 2015)
The 2-year project "In silico modeling of microbiota-gut epithelial cell interactions for predicting dietary supplement impact on gut health" has been selected for funding by the
Seed Grants for Strategic Initiatives program of Texas A&M Engineering in partnership with The Texas A&M University Division of Research (starting in Fall 2014). The PI for
this interdisciplinary project is Dr. Braga-Neto, and the Co-PIs are
Dr. Xiaoning Qian from the College of Engineering, Dr. Ivan Ivanov
from Texas A&M Veterinary School, and Dr. Robert S. Chapkin from
Texas A&M AgriLife, in collaboration with Dr. Johanna W. Lampe from
the Fred Hutchinson Cancer Research Center and Dr. Cheryl L. Walker from the Texas A&M Health Science Center.
The project "Identification of Drought Tolerance Genes and
Networks by Expression Profiling in Banana" has been funded by the
Texas A&M Center for Bioinformatics and Genomics
Systems Engineering, a partnership between Texas A&M Engineering and
Texas A&M AgriLife. The project is conducted in collaboration with
Dr. Martin Dickman from Texas A&M AgriLife and is renewable annually
for a maximum of five years.
Dr. Braga-Neto was elected to Texas A&M Council of Principal
Inverstigators as a College of Engineering representative for
the 2014-2017 term. The CPI voices the concerns of the Texas A&M PI
community to the high levels of administration. If you are a PI in the CoE and have questions or concerns that you want to be brought to the CPI please contact me.
The project "Optimal
Estimation and Network Inference for Boolean Dynamical Systems"
has been funded by a 3-year NSF CIF Award (starting in July 2013).
Dr. Braga-Neto's IEEE membership was elevated to the degree of Senior
Member (September 2011).
The project "Theory
and Application of Small-Sample Error Estimation in Genomic Signal
Processing" was funded by a 5-year NSF CAREER Award (Spring
The following conference paper is retracted:
T.T. Vu, U.M. Braga-Neto and E.R. Dougherty,
"Bagging Degrades the Performance of Linear Discriminant Classifiers,"
Proceedings of VII IEEE International Workshop on
Genomic Signal Processing and Statistics (GENSIPS'2009), Minneapolis, MN,
Please consult the journal paper instead:
T.T. Vu and U.M. Braga-Neto, "Is Bagging Effective in the
Classification of Small-Sample Genomic and Proteomic Data?" EURASIP
Journal on Bioinformatics and Systems Biology, Special Issue on
Applications of Signal Processing Techniques to Bioinformatics,
Genomics, and Proteomics,
Volume 2009, Article ID 158368, 10 pages, 2009. doi:10.1155/2009/158368
[Hindawi Open Access]
The book chapter
U.M. Braga-Neto and E. Dougherty,
In Genomic Signal Processing and Statistics,
Edited by E. Dougherty, I. Shmulevich, J. Chen and Z. J. Wang,
EURASIP Book Series on Signal Processing and Communication,
Hindawi Publishing Corporation, 2005.
has problems in Figures 3.8 and 3.9. However, none of the
conclusions in the chapter changes due to these errors.
preprint PDF linked above already contains the correct Figures 3.8 and 3.9.
[my first name]@ece.tamu.edu
Texas A&M University
Department of Electrical and Computer Engineering
College Station, TX
(979) 862-6441 (Office)
(979) 845-6259 (FAX)