Data Analytics
Learning from data for optimal decisions.
Our data analytics work addresses predictive modeling techniques, including system identification, anomaly detection, feature selection, and time series analysis, as well as methods to solve various decision optimization problems including continuous optimization, combinatorial optimization, and sequential decision making.
Quick Links
-
Researchers
-
Awards
-
AWARD MERL Researcher Devesh Jha Wins the Rudolf Kalman Best Paper Award 2019 Date: October 10, 2019
Awarded to: Devesh Jha, Nurali Virani, Zhenyuan Yuan, Ishana Shekhawat and Asok Ray
MERL Contact: Devesh Jha
Research Areas: Artificial Intelligence, Control, Data Analytics, Machine Learning, RoboticsBrief- MERL researcher Devesh Jha has won the Rudolf Kalman Best Paper Award 2019 for the paper entitled "Imitation of Demonstrations Using Bayesian Filtering With Nonparametric Data-Driven Models". This paper, published in a Special Commemorative Issue for Rudolf E. Kalman in the ASME JDSMC in March 2018, uses Bayesian filtering for imitation learning in Hidden Mode Hybrid Systems. This award is given annually by the Dynamic Systems and Control Division of ASME to the authors of the best paper published in the ASME Journal of Dynamic Systems Measurement and Control during the preceding year.
-
AWARD Best Student Paper Award at the International Conference on Data Mining Date: November 30, 2017
Awarded to: Yan Zhu, Makoto Imamura, Daniel Nikovski, Eamonn Keogh
MERL Contact: Daniel Nikovski
Research Area: Data AnalyticsBrief- Yan Zhu, a former MERL intern from the University of California at Riverside has won the Best Student Paper Award at the International Conference on Data Mining in 2017, for her work on time series chains, a novel primitive for time series analysis. The work was done in collaboration with Makoto Imamura, formerly at Information Technology Center/AI Department, and currently a professor at Tokai University in Tokyo, Japan, Daniel Nikovski from MERL, and Yan's advisor, Prof. Eamonn Keogh from UC Riverside, whose lab has had a long and fruitful collaboration with MERL and Mitsubishi Electric.
-
AWARD DEIM 2010 Best Paper Award Date: February 1, 2010
Awarded to: Hideya Shibata, Mamoru Kato, Mitsunori Kori and William Yerazunis
Awarded for: "An Automatic Training Data Collection Method for Confidential E-mail Detection"
Awarded by: The Forum on Data Engineering and Information Management (DEIM)
MERL Contact: William Yerazunis
Research Area: Data Analytics
See All Awards for Data Analytics -
-
News & Events
-
NEWS MERL researcher Diego Romeres gave an invited talk at University of Connecticut on Reinforcement Learning for Robotics Date: November 20, 2019
MERL Contact: Diego Romeres
Research Areas: Artificial Intelligence, Data Analytics, Machine Learning, RoboticsBrief- Diego Romeres, a Research Scientist in MERL's Data Analytics group, gave a seminar lecture at the Electrical and Computer Engineering Colloquium of the University of Connecticut. The talk described novel reinforcement algorithms based on combining physical models with non-parametric models of robotic systems derived from data.
-
NEWS Mouhacine Benosman to deliver keynote at the mini-symposium 'Data assimilation in Model Order Techniques for Computational Mechanics' Date & Time: July 29, 2019; 10 AM
Where: US National Congress on Computational Mechanics 2019, in Austin Texas
MERL Contact: Mouhacine Benosman
Research Areas: Control, Data Analytics, Dynamical SystemsBrief- MERL researcher Mouhacine Benosman will present his work on 'Learning-based Robust Stabilization for Reduced-Order Models of 3D Boussinesq Equations' as a keynote speaker at the mini-symposium 'Data assimilation in Model Order Techniques for Computational Mechanics', during the next US National Congress on Computational Mechanics 2019, in Austin Texas.
See All News & Events for Data Analytics -
-
Internships
-
DA1396: Machine learning for Contact-rich Robotic Manipulation
MERL is looking for a highly motivated individual to work on contact-rich robotic manipulation applications. The ideal candidate is expected to have expertise both in machine learning techniques, such as Gaussian Process Regression and Deep Neural Networks, as well as in reinforcement learning algorithms. In addition, having experience with robotic systems would be considered a significant plus. The candidate will be expected to develop novel algorithms and possibly implement them on robotic systems. Proficiency in Python programming is necessary, and experience with ROS would be a plus. The candidate will collaborate closely with MERL researchers. Start date for this internship is flexible, and the duration is expected to be 3-6 months.
-
DA1380: Machine Learning and Optimization
MERL is looking for a self-motivated intern to develop predictive machine learning and optimization algorithms. Applications include time series prediction, anomaly detection, scheduling, and transportation. The ideal candidate would be a senior PhD student with experience in one or more of the following areas: machine learning, mathematical optimization, discrete-event systems modeling. Strong programming skills using C++/Python are expected. Experience with libraries such as scikit-learn, Pytorch is a plus. The intern is expected to work with MERL researchers to develop algorithms and prepare manuscripts for scientific publications. The duration of the internship is expected to be 3 months. Start date is flexible.
-
DA1389: Time Series Algorithms using Generative Models or Reinforcement Learning
The Data Analytics Group is looking for a self-motivated intern to develop algorithms with applications in industrial time series data. The ideal candidate is a senior PhD student with one of the following profiles: 1) a candidate with experience in deep generative models (VAE, GAN, Boltzmann Machines, etc.), classical generative models, or in applying modern methods of machine learning to time series data; 2) a candidate with experience in reinforcement learning algorithms using time series data. Preferred candidates will have a background working with data outside computer vision. The candidate should have strong programming skills using Python and/or C++. The outcome of a successful internship will be an intern-driven algorithm development that leads to a scientific publication. Typical internship length is 3 months with a flexible start date.
See All Internships for Data Analytics -
-
Recent Publications
- , "Introducing Time Series Chains: A New Primitive for Time Series Data Mining", Knowledge and Information Systems, DOI: 10.1007/s10115-018-1224-8, Vol. 60, No. 2, pp. 1135-1161, August 2019.BibTeX Download PDFAbout TR2019-077
- @article{Zhu2019aug,
- author = {Zhu, Yan and Imamura, Makoto and Nikovski, Daniel N. and Keogh, Eamonn},
- title = {Introducing Time Series Chains: A New Primitive for Time Series Data Mining},
- journal = {Knowledge and Information Systems},
- year = 2019,
- volume = 60,
- number = 2,
- pages = {1135--1161},
- month = aug,
- doi = {10.1007/s10115-018-1224-8},
- url = {https://www.merl.com/publications/TR2019-077}
- }
- , "Anomaly Detection for Insertion Tasks in Robotic Assembly Using Gaussian Process Models", European Control Conference (ECC), June 2019.BibTeX Download PDFAbout TR2019-055
- @inproceedings{Romeres2019jun,
- author = {Romeres, Diego and Jha, Devesh and Dau, Hoang and Yerazunis, William S. and Nikovski, Daniel N.},
- title = {Anomaly Detection for Insertion Tasks in Robotic Assembly Using Gaussian Process Models},
- booktitle = {European Control Conference (ECC)},
- year = 2019,
- month = jun,
- url = {https://www.merl.com/publications/TR2019-055}
- }
- , "Fault Detection and Classification of Time Series Using Localized Matrix Profiles", IEEE International Conference on Prognostics and Health Management, June 2019.BibTeX Download PDFAbout TR2019-057
- @inproceedings{Zhang2019jun,
- author = {Zhang, Jing and Nikovski, Daniel N. and Lee, Teng-Yok and Fujino, Tomoya},
- title = {Fault Detection and Classification of Time Series Using Localized Matrix Profiles},
- booktitle = {IEEE International Conference on Prognostics and Health Management},
- year = 2019,
- month = jun,
- url = {https://www.merl.com/publications/TR2019-057}
- }
- , "Space-Time Slicing: Visualizing Object Detector Performance in Driving Video Sequences", IEEE Pacific Visualization Symposium (PacificVis), June 2019.BibTeX Download PDFAbout TR2019-024
- @inproceedings{Lee2019jun,
- author = {Lee, Teng-Yok and Wittenburg, Kent B.},
- title = {Space-Time Slicing: Visualizing Object Detector Performance in Driving Video Sequences},
- booktitle = {IEEE Pacific Visualization Symposium (PacificVis)},
- year = 2019,
- month = jun,
- url = {https://www.merl.com/publications/TR2019-024}
- }
- , "Heat Exchanger Circuitry Design by Decision Diagrams", International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, DOI: 10.1007/978-3-030-19212-9_30, June 2019, vol. 11494, pp. 467-471.BibTeX Download PDFAbout TR2019-038
- @inproceedings{Ploskas2019jun,
- author = {Ploskas, Nikolaos and Laughman, Christopher R. and Raghunathan, Arvind and Sahinidis, Nikolaos V.},
- title = {Heat Exchanger Circuitry Design by Decision Diagrams},
- booktitle = {International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research},
- year = 2019,
- volume = 11494,
- pages = {467--471},
- month = jun,
- doi = {10.1007/978-3-030-19212-9_30},
- url = {https://www.merl.com/publications/TR2019-038}
- }
- , "Last-Mile Scheduling Under Uncertainty", International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research, DOI: 10.1007/978-3-030-19212-9_34, June 2019, vol. 11494, pp. 519-528.BibTeX Download PDFAbout TR2019-040
- @inproceedings{Serra2019jun,
- author = {Serra, Thiago and Raghunathan, Arvind and Bergman, David and Hooker, John and Kobori, Shingo},
- title = {Last-Mile Scheduling Under Uncertainty},
- booktitle = {International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research},
- year = 2019,
- volume = 11494,
- pages = {519--528},
- month = jun,
- doi = {10.1007/978-3-030-19212-9_34},
- url = {https://www.merl.com/publications/TR2019-040}
- }
- , "Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze", IEEE International Conference on Robotics and Automation (ICRA), May 2019.BibTeX Download PDFAbout TR2019-028
- @inproceedings{Romeres2019may,
- author = {Romeres, Diego and Jha, Devesh and Dalla Libera, Alberto and Yerazunis, William S. and Nikovski, Daniel N.},
- title = {Semiparametrical Gaussian Processes Learning of Forward Dynamical Models for Navigating in a Circular Maze},
- booktitle = {IEEE International Conference on Robotics and Automation (ICRA)},
- year = 2019,
- month = may,
- url = {https://www.merl.com/publications/TR2019-028}
- }
- , "On the Minimum Chordal Completion Polytope", Operations Research, DOI: 10.1287/opre.2018.1783, Vol. 67, No. 2, pp. 295-597, March 2019.BibTeX Download PDFAbout TR2018-095
- @article{Bergman2019mar,
- author = {Bergman, David and Cardonha, Carlos and Cire, Andre and Raghunathan, Arvind},
- title = {On the Minimum Chordal Completion Polytope},
- journal = {Operations Research},
- year = 2019,
- volume = 67,
- number = 2,
- pages = {295--597},
- month = mar,
- doi = {10.1287/opre.2018.1783},
- url = {https://www.merl.com/publications/TR2018-095}
- }
- , "Introducing Time Series Chains: A New Primitive for Time Series Data Mining", Knowledge and Information Systems, DOI: 10.1007/s10115-018-1224-8, Vol. 60, No. 2, pp. 1135-1161, August 2019.
-
Videos
-
Free Downloads
