Laptop

HI I’M VANESSA

Ph.D. Candidate at Institute of Neuroinformatics, University of Zurich and ETH Zurich

 

ACADEMIC LIFE

IMG-20200214-WA0039.jpg

During my undergraduate studies at the Federal University of Maranhao (UFMA), I worked with medical images and 3D models visualization. I attended programming contests and participated in the ACM-ICPC Brazilian Finals in  2007.

During my second undergraduate year, I started to work at the Image Processing and Analysis Lab. At this point, I worked on developing software to help medical doctors with lung and breast cancer diagnosis. As part of this project, I studied pattern recognition and machine learning techniques. Near the end of my undergraduate studies, I  attended Computer Graphics classes and moved to another lab: Interactive Media Lab, where I did my final course project in 3D urban model visualization using spatial databases.

I completed my undergraduate studies with good knowledge in Computer Science, having studied in depth the above-mentioned areas, and I achieved a grade of 7.9/10. After that, I received a full scholarship to attend a master's course at Pontifical Catholic University of Rio de Janeiro (PUC-Rio). PUC-Rio is one of Brazil's best Computer Science departments, as assessed by both governmental and non-governmental ranks. During my master’s studies, I deepened my experience with Computer Graphics, Computer Vision, and Machine Learning. In a first project, I worked on a way to improve the communication between deaf and hearing people by using Computer Vision to translate Brazilian sign language.

At the same time, I have started to work at the Technical ­Scientific Software Development Institute (Tecgraf/PUC­-Rio) and changed my focus to the geophysics applications. Following this path, my Master Thesis was related to the lithologies classification based on well logs. To do that, I worked with Machine Learning techniques such as SVM, MLP, and Ensemble Methods. In my master’s course, I achieved a grade of 8.9/10.

When I finished my master’s degree, I was invited to work as a full-time developer and researcher in TecGraf.

There, I was part of a team that develops software for visualization and interpretation of seismic data named ‘v3o2’. The software we developed is used by Petrobras, the largest oil company in Brazil. As a senior developer, I was responsible for designing new features, refactoring activities, and training new members. I have contributed to the development of tools for 3D visualization of well and well logs; drilling well monitoring in real-time; cross plot of seismic volumes, etc.

Nowadays, I’m a Ph.D. candidate at the Institute of Neuroinformatics (INI)University of Zurich and ETH Zurich in which I am a member of The Cortical Computational Group and Neuromorphic Cognitive Systems.

 
img_view.jpeg

PROFESSIONAL HISTORY

THE CORTICAL COMPUTATION GROUP - INSTITUTE OF NEUROINFORMATICS (ETH/UZH)

October 2016 – September 2018

At the Cortical Computation Group, I worked with vision algorithms to automatically extract wiring diagrams of the nervous system at synaptic resolution. In a first project, I focused on reducing the time spent by proofreaders in fixing errors of the results of existent automatic computer-based techniques. In a second project, I worked on a way to analyze correlated Electron and Light Microscopy data. The goal was the identification of projecting areas together with local connectivity, to be able, for instance, to quantify relations between neurons projecting to different areas.
Supervisor: Matthew Cook
Ph.D. Supervisor: Richard Hanhloser

RESEARCHER AND SENIOR DEVELOPER, TECGRAF / PUC-RIO

August 2010 – August 2016

Computational Geophysics Group: Working on the development of an application for visualization and interpretation of 3D/2D seismic data for Petrobras (Brazil’s biggest oil company) called V3O2. This software has been developed for more than 14 years and the current team has about 45 developers. Started on the project as a software developer and, after two years, I took on the role of Researcher and Senior Developer, I was responsible for the design of new features, for major refactoring activities and training of new members. Contributions involved the development of tools for visualization of wells, well logs and lithologies in a 3D interface, real-time drilling monitoring, visualization of 2D and 3D pre-stack and post-stack seismic data, time-depth conversions, among others. Some technologies used in this project were C++, OpenGL, Scrum, Continuous Integration, Unit Tests and Cross-Platform development. http://www.tecgraf.puc-rio.br/en/og/og-geophysic.html

SCRUMMASTER (CSM), TECGRAF / PUC-RIO

December 2012 – June 2015

Computational Geophysics Group: As ScrumMaster, my main responsibility was to help the team (developers and the Product Owner - PO) to achieve their goals and help the organization to be more agile. Other responsibilities include (but aren’t limited for):helping everyone understand Scrum, facilitating meetings (even outside Scrum meetings), collaborating with the team in order to make the retrospective a moment of improvement, assisting the PO with the organization of the Product Backlog and work directly with the clients to coordinate the communication between them and the PO.

 
IMG_20201210_120050.jpg

EDUCATIONAL HISTORY

Learning and Living

 

January 2010 - July 2012

MASTER OF SCIENCE IN INFORMATICS, PUC-RIO, BRAZIL

Pontifical Catholic University of Rio de Janeiro (PUC-Rio), RJ, Brazil.
Computer Science Department (www.inf.puc-rio.br)
Master of Science in Informatics-Computer Graphics, 2012. GPA: 8.9/10.0
Courses include Physics Simulation, Image/Video Processing, Computer Vision and Game AI.

Note: The Pontifical Catholic University of Rio de Janeiro (PUC-Rio) has one of the best Computer Science department in Brazil, by governmental and non-governmental ranks.

March 2005 - January 2010

COMPUTER SCIENCE BACHELOR, UFMA, BRAZIL

Bachelor in Computer Science from Federal University of Maranhao (UFMA), MA, Brazil.
Computer Science Department (www.deinf.ufma.br)
Computer Science, 2009. GPA: 7.9/10.0
Most relevant courses include Computer Graphics, 3D computer graphics, OO, Numerical analysis, Linear algebra, Calculus, Physics, Probability, Networks, Databases, Distributed systems.

Organized Desk

PUBLICATIONS

 
fnins-14-00551-g001.jpg

AN ON-CHIP SPIKING NEURAL NETWORK FOR ESTIMATION OF THE HEAD POSE OF THE ICUB ROBOT

Frontiers in Neuroscience, 14: 551, 2020

In this work, we present a neuromorphic architecture for head pose estimation and scene representation for the humanoid iCub robot. The spiking neuronal network is fully realized in Intel's neuromorphic research chip, Loihi, and precisely integrates the issued motor commands to estimate the iCub's head pose in a neuronal path-integration process. The neuromorphic vision system of the iCub is used to correct for drift in the pose estimation. Positions of objects in front of the robot are memorized using on-chip synaptic plasticity. We present real-time robotic experiments using 2 degrees of freedom (DoF) of the robot's head and show precise path integration, visual reset, and object position learning on-chip. We discuss the requirements for integrating the robotic system and neuromorphic hardware with current technologies.

APPLICATION ON REINFORCEMENT LEARNING FOR DIAGNOSIS BASED ON MEDICAL IMAGE

Jan 2008 – Reinforcement Learning: Theory and Applications, Book edited by Cornelius Weber, Mark Elshaw and Norbert Michael Mayer ISBN 978-3-902613-14-1, pp.424, January 2008, I-Tech Education and Publishing, Vienna, Austria

This work presents an overview of current work applying reinforcement learning in medical image applications, presenting a detailed illustration of a particular use for lung nodules classification. The addressed application of reinforcement learning to solve the problem of lung nodules classification used the 3D geometric nodules characteristics to guide the classification. Even though the results are preliminary we may see that the obtained results are very encouraging, demonstrating that the reinforcement learning classifier using characteristics of the nodules’ geometry can effectively classify benign from malignant lung nodules based on CT images. On the other side, we may observe that this is a machine learning that is not commonly applied to medical images and this is an opportunity for more intensive investment in the research for this area. But some problems are well known in this application and must be more studied. We should research how to find out a way to shorten the training phase while maintaining the learning quality. And also must be improved the tests to generate more definitive results and to make possible the comparison with other classifiers.

Laptop Writing
wellLocations.png

ANALYSIS OF ENSEMBLE METHODS APPLIED TO LITHOLOGY CLASSIFICATION FROM WELL LOGS

Aug 2013 – 13th International Congress of The Brazilian Geophysical Society (SBGf)

This paper analyzes ensemble methods applied to automatic lithology classification. For this, we performed a comparison between single classifiers (Support Vector Machine and Multilayer Perceptron) and these classifiers with ensemble methods (Bagging and Boost).

CONTACT

+41767495242

  • Twitter
  • Instagram
  • LinkedIn
IMG_20181107_131410.jpg