Projects

There has been a recent surge of success in utilizing Deep Learning (DL) in imaging and speech applications for its relatively automatic feature generation and, in particular for convolutional neural networks (CNNs), high accuracy classification abilities. While these models learn their parameters through data-driven methods, model selection (as architecture construction) through hyper-parameter choices remains a tedious and highly intuition driven task. To address this, Multi-node Evolutionary Neural Networks for Deep Learning (MENNDL) is proposed as a method for automating network selection on computational clusters through hyper-parameter optimization performed via genetic algorithms.

EDEN is a visual analytics tool for exploratory analysis of multivariate data sets. Based on an interactive variant of parallel coordinates, EDEN includes statistical analytics that guide the user to significant associations in complex data sets without information loss.

While the term ‘innovation ecosystem’ is often utilized, the concept is rarely quantified. Oak Ridge National Lab conducted a ground-breaking application of natural language processing, link analysis and other computational techniques to transform text and numerical data into metrics on clean energy innovation activity and geography for the U.S. Department of Energy. The project demonstrates that a machine-assisted methodology gives the user a replicable method to rapidly identify, quantify and characterize clean energy innovation ecosystems.

The Beholder system is a software client / server system that detects intrusion by monitoring the real-world execution time of critical kernel-level operations. Beholder was designed for use with critical infrastructure systems, especially in the power grid.

Hyperion is a software system for static analysis of compiled software, enabling the detection of undesirable behavior or the demonstration of correct behavior.

An effective tool for managing and sharing documents and data is needed to effectively support spent fuel activities.

ORNL is developing quantum information tools to help secure the electric grid. Researchers are working to extend the range and reduce the cost of quantum key distribution.

This project will improve our understanding of the dynamic interactions between social and physical networks that make up cities. It uses household level energy consumption and infrastructure records, neighborhood level communication records, digital trace data, and a range of remotely sensed data to quantify relationships between urban infrastructure systems and social structures within that urban environment. This empirical research is necessary to support the next generation of models exploring climate change impacts and resource supply security of cities now and in the future.