RegMAS (Regional Multi Agent Simulator) is a spatially explicit multi-agent model framework, designed for long-term simulations of effects of government policies over agricultural systems (e.g. farm sizes, incomes, land use). RegMAS uses a profit-maximization algorithm to derive farmers' behaviors. Using RegMAS, researchers can write regional-specific models, adapting the pool of activities and resources to their specific region.
Breeze a multiple class model neural network development system. The architecture is based on the standard three-tier model/view/controller, in addition to a multi-threaded circuit switch command structure, with full application logging and internal trace routines. Network models include Online Backpropagation and Radial Basis Function Networks, for time series prediction.
Asimulator is a simulator for intelligent agents, useful to practice search algorithms, in AI courses, or for fun. The agent's goal is to understand precepts and respond with actions in a virtual world (consisting of a grid up to 129x129) to maximize a score. The simulator opens a socket, so any language can be used for agents. (Samples in Ada are included.) Agent debug output can be shown. Both text in a log window and symbols on the map can be used to visualize thoughts.
Twibright Casanova is a commandline program to partially automate conversation on dating services. Casanova stores conversation in pairs into a database. It gathers conversation statistics and suggests how to respond like an average dating service user. Such answers are likely to be familiar to others and are thus designed to increase your popularity through the psychological exposure effect. It is meant to be helpful to people with social difficulties.
Beneath A Binary Sky is an engine that simulates a world in which robots controlled by programs can live, work, fight, and even bear new children. The long-term goal of the project is to create a fully configurable engine that can simulates any kind of world, from simple to complex ones with many rules and events.
The ATRACO Project is a prototype implementation of a trusted ambient ecology system that runs and manages activity spheres in an Ambient Intelligence Space. Activity spheres are realized by automatically discovering, selecting, and adapting smart devices (artefacts) existing in the space, according to user's preferences, customs, and activities. OWL ontologies are used for modeling user profile, devices, activities, and goal descriptions. Abstract plans are bound to specific devices, methods, and values through semantic matching.
Wintermute is an intelligent framework of applications and libraries that uses neural networking to learn about its host. A pseudo-langauge engine that permits translations and grammar rulesets of any language to be incorporated into the system, and database downloads of different sets of data combine to provide a virtual self-thinking assistant that can be used to perform tasks like dictation to a text editor, and more complex tasks such as sorting of documents depending on the time of day, or automation of other routine tasks. It should be noted that Wintermute itself is a meta-project. It encompasses a large array of currently existing and potential produced projects.
pyuds is a Python library for measuring uncertainty in the Dempster-Shafer theory of evidence. The functionals supported are the Generalized Hartley (GH) uncertainty functional, Generalized Shannon (GS) uncertainty functional, and Aggregate Uncertainty (AU) functional. The library can be utilized either through its API, or through a user-friendly Web interface.
Wandora is a general purpose data extraction, management, and publishing application based on Topic Maps and Java. Wandora has a graphical user interface, layered presentation of knowledge, several data storage options, rich data extraction, import and export capabilities, and an embedded HTTP server that enables dynamic publication of Topic Maps. Wandora is well suited for rapid ontology construction and knowledge mashups.