Robotics Institute
5000 Forbes Ave
Pittsburgh, PA 15213
Research Interests
My name is Mathieu Guillame-Bert, and I am working at CMU (Carnegie Mellon University) since 2013 as a Postdoctoral Fellow for the Auton-Lab (Robotic Institute). I defended my PhD in France in 2012 at the INRIA Research Lab in the PRIMA team under the supervision of James L. Crowley. I graduate from the Master of Advance Computing of the Imperial College of London, and from the "French Grande Ecole" ENSIMAG (Ecole Nationale Supérieure d'Informatique et de Mathématiques Appliquées) in 2009.
I am studying the automated extraction of patterns from large temporal datasets, as well as the use of those models for automated prediction, user interpretation and automated reasoning. Application domains I have worked on include Medical Diagnostics, Medical Forecastion, Human Activity Recognition and Forecasting, Banking Activity Patterns, Fault Detection and Prediction on complex systems, automatic Foreign exchange market trading, and a bit of Robotics.
Publications
2016
Journals/Conference Proceedings
Tutorial
]]Article
]2015
Presentation
]]2014
Workshop
]Presentation
2013
Presentation
]Tutorial
]2012
Journals/Conference Proceedings
]]Presentation
Report
Committee: Pr. Malik Gha llab, Pr. Paul Lukowicz, Dr. Artur Dubrawski, Pr. Augustin Lux
]2011
Journals/Conference Proceedings
]]2010
Journals/Conference Proceedings
]Prior to 2010
Report
Distinguished MSc project [page]
]Curriculum vitae
Softwares & Datasets
Softwares
Since the 28 Nov. 2015, all the softwares except the Machine Learning Lab (along with their documentation) are hosted on the MGBFramework website. All softwares are publicly available and free to use.
-
TITARL (Temporal Interval Tree Association Rule Learner) is a Temporal Data Mining algorithm able to extract temporal rules from symbolic time series and time sequences (SSTS). The rules can be interpreted, used for predictions, or used for further analysis.
-
Event Viewer is a powerful visualizing tool for time series, time sequences and other symbol or scalar temporal datasets. Event Viewer has a lot of unique features which allow a powerful understanding of data. Event Viewer can be used to study static data and real time data flows. Event Viewer can interact seemingly with Honey.
-
Honey is a compact and high level flow-oriented programming language designed to facilitate the pre/post processing and the analysis of symbolic and numerical time series and sequences datasets. Honey can seemingly be applied on static dataset and real time data streams.
-
Machine Learning Lab is a small exploratory tool designed to test and experiment easily with several Machine Learning algorithms on several real work and sythetic datasets.
Public datasets
- SSTS Classification
- Synthetic
Small synthetic dataset containing containing 1, 2 and 3 elements GTC patterns [screen-shot]. - Internal Bleeding
Medical dataset about detection of internal bleeding from small snapshots of high frequency vital sign records [screen-shot]. - Internal Bleeding + Events
Similar to the Interval Bleeding dataset, but contains, in addition, two event-base features extracted with the help of the Honey programming language [screen-shot]. - URC Plots
Plotting (picture only) of the URC datasets [screen-shot]. - Rare events forecasting in SSTS
- The computer generated Database
A syntetic data-set create to test symbolic time sequence data-mining algorithms. - The Home Data Set
The "Home activities dataset" of Tim van Kasteren et al. converted to be imported in TITARL and Event Viewer. - Forex Dataset: Automated Trading Experiment
A three years record of the USD/EUR Forrex market converted to be imported in TITARL and Event Viewer.
Gallery
This sections shows some of the nice pictures that I have generated through my research work. You can click on the picture to get the full size versions.
Evolution of GSMap over time (video)
You can see more of those pictures at the gallery page.
▲ Come back to indexPersonal area
I enjoy skiing and salsa dancing.
The core of a robot made of legos
when I was a kid.
Apart from that, I enjoy DIY as well as making video games (which are related). You can find some old video games and old DIY projects that I made in my youth on my old personal website at http://hokage.no.jutsu.free.fr/Achoum/.
In-game screen-shot of Build & Defend
I created a game called Build & Defend. This is a multi-player survival cooperative game in a randomly generated and destructible world. This game is an experiment of some game-play concepts that I wanted to try for a long time. Also, I rely of lot on player feed backs as a direction to help developing the game. You can try this game at http://buildanddefend.com/. You can see the Indie DB web-page of this game at http://www.indiedb.com/games/build-defend. You can also follow me on twitter at @Achoum_GameDev.
Definition of the "for" function in SMALL.
I also enjoy hacking a bit with computer. I have created this little blog where I talk about some of my hacks.
The logo of Nac-sitter.com
I am also co-creator of the website http://nac-sitter.com/. Nac-sitter.com helps people to find somebody to keep their pets during holidays. This web-site focus mainly on NACs (Nouveau animaux de compagnie - "New pets" in english) such as rats, hamsters, rabbits, fishs, pogonas, etc.
▲ Come back to index
