ReasonSmart™is a data-driven, knowledge-centered framework that enables fast processing and analysis of large datasets.
It provides a comprehensive menu of tools for simulating what-if scenarios. Users can pull in their onw data in real real time to model and develop a system for solving real-world problems.
The ReasonSmart™ toolkit offers these tools for analyzing complex datasets:
- Agent-Based Modeling — computational modeling of phenomena as dynamic systems of autonomous and interacting agents
- Complex Pattern Recognition — Associative memory and machine learning techniques to determine patterns and associations in large-scale complex data
- Cluster Analysis — Non-parametric and parametric clustering methods to identify like entities and provide a similarity metric
- Intelligent Decision Support — Learning-based decision support tools that make recommendations based on the similarity of the current context to previous contexts and outcomes
- Intelligent Web Crawler — Agent-based technology that uses an intelligent extraction rule to create personalized Web searches for data, which is then stored in a database for research purposes
- Knowledge Discovery — A range of traditional and non-traditional tool for uncovering patterns and hidden relationships in complex data
- Logic Programming — Using mathematical logic in a computer program that represents knowledge in a declarative way to enable reasoning, planning, diagnosing and extracting information from it
- Matlab — A numerical computing environment providing a range of techniques in data analysis, visualization, application development and simulation
- Neural Networks — Modeling of multi-dimensional mathematical relationships for simulating and learning interactions between inputs and outputs
Contact Monica Nogueira at the Center for Logistics and Digital Strategy's Intelligent Systems Lab, 919.843.4740 or , to learn how to access the tools and resources ReasonSmart offers.