Fusing Machine Learning and Analytics with Optimization
New wearables and low-cost sensors allow for the collection of a plethora of health data. This data can be leveraged in medical diagnostics and health monitoring allowing for early detection of changes in health condition.
The Laboratory for Interactive Optimization and Learning (IOL) is an experimental setup exploring, both, the fusion of advanced optimization, machine learning, and analytics into data-driven decision support systems, as well as their deployment in various real-world application contexts.
Ever-increasing competitive pressures require constant improvements to global supply chains. The coherent integration of real-time data and decision making is the next step in tomorrow's logistics landscape.
Big Data is one of the key enablers for businesses. The efficient extraction of information from large-scale data requires machine learning and optimization approaches.
Cyber-physical systems combine sensors, computing, and machines to form intelligent machines. Specific frameworks include industry 4.0, the industrial internet, and internet of things.
Key application areas include:
News and Updates.
> March/April 2017. Jeff Pavelka, Aurko Roy, and Daniel Zink successfully defended their theses.
> March 2017. NSF EAGER funding for "EAGER: SC2: PHY-Layer-Integrated Collaborative Collaborative Learning" (CNS-1737842)
> June 2016. Official launch of Machine Learning @ GT Interdisciplinary Research Center