Braga-Neto and Dougherty publish book on topic of Error Estimation in Pattern Recognition

Dougherty Braga Neto Book CoverDr. Ulisses Braga-Neto and Dr. Edward Dougherty, professors in the Department of Electrical and Computer Engineering at Texas A&M University, published a book titled Error Estimation for Pattern Recognition.

The book is the first book devoted entirely to the topic of classifier error estimation in pattern recognition. Error estimation is the process of predicting the error rate of a classifier applied to future unlabeled data, and is critical for the validation of models developed in pattern recognition, machine learning and data analytics applications.

Their book contains the result of more than 10 years of joint research on this topic by the authors, in addition to a survey of the classical results in the field. Most of the new results presented in the book were obtained with funding from Braga-Neto’s National Science Foundation’s (NSF) CAREER Award.

Dougherty is considered a pioneer in the study of translational genomics via the use of engineering techniques such as signal processing, pattern recognition and control theory. He is the director of the Genomic Signal Processing Lab at Texas A&M. His honors include being named a Distinguished Lecturer and being named a Texas Engineering Experiment Station (TEES) Fellow. He has authored 17 books and more than 325 journal publications.

Braga-Neto joined the Biomedical Imaging and Genomic Signal Processing group of the department in 2007. Prior to that he was an assistant researcher with FIOCRUZ from 2004 to 2006, and from 2002 to 2004 he was a post-doctoral researcher with the Section of Clinical Cancer Genetics at the University of Texas M.D. Anderson Cancer Center.

Braga-Neto received his Ph.D. in electrical and computer engineering from The Johns Hopkins University in 2002, and master’s degrees in electrical and computer engineering and mathematical sciences, also from The Johns Hopkins University, in 1998. He received  master’s degree from the State University of Campinas, Brazil, in 1994 and his bachelor’s degree from the Federal University of Pernambuco, Brazil, in 1992.

His honors include receiving the NSF CAREER Award in 2009. Braga-Neto’s research interests include statistical signal processing and statistical pattern recognition, with applications in the study of cancer and infectious diseases. He is particularly interested in the design and analysis of statistical methods of small-sample classification and error estimation for genomics and proteomics applications.