Computer Science High School

OBJECTIVE:

EDUCATION:

HONORS AND

AWARDS:

WORK

EXPERIENCE:

INTERNSHIP:

To obtain a position where I can fully leverage my knowledge on the

statistical data analysis, pattern recognition modeling and research skills

where my experience on various domains will be viewed as a clear value add

to a corporation that encourages career growth.

Ph.D. in Computer Science, GPA 3.7/4.0, University of Houston, Houston, TX,

December 2012

M.Sc. in Computer Science, CINVESTAV, Guadalajara, Mexico, November 2004

B.Sc. in Computer Systems Engineering, ITESO, Guadalajara, Mexico, June

2001

Best Content Poster in the 2012 UH Computer Science Ph.D. Research Showcase

National Scholarship (Ph.D.), CONACYT, Mexico 2009-2010

National Scholarship (M.Sc.), CONACYT, Mexico 2002-2004

Valedictorian ITESO 2001

Best G.P.A. ITESO 1997 and 1998

Research Assistant, University of Houston, August 2006-December 2012

Developed a variety of machine learning algorithms, where we exploit domain

knowledge to design solutions for different types of data using tools, such

as MATLAB, WEKA, and several machine learning libraries. Relevant projects

include:

. Data Characterization for the suitability in the use of class

decomposition (2006-2012). Research Leader for the analysis and design

of algorithms, models, and experiments to understand when the use of

class decomposition is beneficial in terms of classification

performance. Our results are reported in refereed conference

publications. See publications 1, 3, and 5.

. Automatic Geomorphic Mapping and Analysis of Land Surfaces Using

Pattern Recognition, collaboration with Lunar and Planetary Institute

(2006-2011). Project leader for the development of a system that

classifies entire topographic scenes into characteristic landscape

classes. A number of novel solutions, including semi-supervised

learning, meta-learning, and a wrapping technique coupling

classification and segmentation, were proposed to address challenges

posed by the specificity of topographic data. Our results are reported

in refereed conference publications. See publications 3 and 7.

Instructor. ITESO, January 2006 - June 2006

Compilers course where students built a compiler based on C++.

Instructor. CINVESTAV, January 2006 - June 2006

Algorithms course where students used JAVA and C++ to implement them.

Software developer. ASCI (www.asci.us), March 2005 - March 2006

Developed drivers and firmware in JAVA for different hardware manufacturers

such as CANON, RICOH, XEROX, and SHARP.

Hewlett-Packard (HP), R&D (Guadalajara, M xico), January 2003 - June 2003

Team leader for the analysis, design and development of the JetLink

Analyzer Tool. This tool was built to manage the communications among

different protocols over HP-Printers.

PUBLICATIONS:

COMPUTER SKILLS:

LANGUAGES:

COMMUNITY INVOLVEMENT:

REFERENCES:

1. Ocegueda-Hernandez F. and Vilalta R. An Empirical Study of the

Suitability of Class Decomposition for Linear Models: When Does It Work

Well? SIAM International Conference on Data Mining (SIAM-DM-2013).

2. Vilalta R., Kuchibhotla S., Hoang S., Valerio R., Ocegueda-Hernandez F.,

Pinsky L. (2012) Classification of Sources of Ionizing Radiation in

Space Missions: A Machine Learning Approach. Journal of the European

Space Agency, Acta Futura 5, pp. 111-119.

3. Vilalta R., Gorty P, Ocegueda-Hernandez F., and Stepinski T.

Classification using Graph-based Class Decomposition for the

Identification of Mars Landforms. NASA Conference on Intelligent Data

Understanding (CIDU) 2011.

4. Vilalta R., Kuchibotla S., Ocegueda-Hernandez F., Hoang S., and Pinsky

L. Machine Learning for Identification of Sources of Ionizing Radiation

during Space Missions. In proceedings of 2011 IJCAI Workshop on:

Artificial Intelligence in Space: Intelligence beyond planet. Barcelona,

Spain.

5. Vilalta R., Ocegueda-Hernandez F. and Bagaria C. (2010). A Conceptual

Study of Model Selection and Classification. Multiple Local Models vs

One Global Model. Second International conference on Agents and

Artificial Intelligence (ICAART-2010), Valencia, Spain.

6. Vilalta R., Valerio R., Ocegueda-Hernandez F., Watts G. (2009) The

Effect of the Fragmentation Problem in Decision Tree Learning Applied to

the Search for Single Top Quark Production. 17th International

Conference on Computing in High Energy and Nuclear Physics (CHEP-09),

Prague, Czech Republic. Journal of Physics: Conference Series.

7. Vilalta R., Stepinski T., Achari M., Ocegueda-Hernandez F.(2004).A

Quantification of Cluster Novelty with an Application to Martian

Topography. 8th European Conference on Principles and Practice of

Knowledge Discovery in Databases (PKDD04).

8. Francisco Ocegueda, Roberto S nchez and F lix Ramos "Tlachtli: A

Framework for Soccer Agents Based on GeDa-3D", In proceedings of the

Third International School and Symposium on Advanced Distributed

Systems, ISSADS 2004, held in Guadalajara, Mexico in January 2004.

. Machine Learning Tools: Mastery of WEKA and Statistical

Pattern Recognition Toolbox (Matlab)

. Software Development: Intermediate level of Java, C/C++,

VB

. Operating Systems: Windows (7, Vista, XP), Linux

(Ubuntu, Knoppix).

Spanish (Native), English (Advanced).

SIEMENS Foundation- 2013 Siemens Competition in Math, Science & Technology

Mentoring High School students to prepare their science project for this

event

Academic and professional references available upon request.

Contact this candidate