Thomas R. Ioerger

JAAMAS Journal 2026 Journal Article

FLAME—Fuzzy Logic Adaptive Model of Emotions

• Magy Seif El-Nasr
• John Yen
• Thomas R. Ioerger

Abstract Emotions are an important aspect of human intelligence and have been shown to play a significant role in the human decision-making process. Researchers in areas such as cognitive science, philosophy, and artificial intelligence have proposed a variety of models of emotions. Most of the previous models focus on an agent's reactive behavior, for which they often generate emotions according to static rules or pre-determined domain knowledge. However, throughout the history of research on emotions, memory and experience have been emphasized to have a major influence on the emotional process. In this paper, we propose a new computational model of emotions that can be incorporated into intelligent agents and other complex, interactive programs. The model uses a fuzzy-logic representation to map events and observations to emotional states. The model also includes several inductive learning algorithms for learning patterns of events, associations among objects, and expectations. We demonstrate empirically through a computer simulation of a pet that the adaptive components of the model are crucial to users' assessments of the believability of the agent's interactions.

AAMAS Conference 2005 Conference Paper

Observation-Based Proactive Communication in Team Cooperation

• Yu Zhang
• Richard A. Volz
• Thomas R. Ioerger

AAAI Conference 1999 Conference Paper

Detecting Feature Interactions from Accuracies of Random Feature Subsets

• Thomas R. Ioerger
• Texas A
• M University

Interaction amongfeatures notoriously causes difficulty for machinelearning algorithms becausethe relevanceof onefeature for predicting the target class can dependon the values of other features. In this paper, weintroduce a newmethodfor detecting feature interactions byevaluating the accuracies of a learning algorithm on randomsubsets of features. Wegive an operational defufition for feature interactions basedon whena set of features allows a leamlngalgorithm to achieve higher than expectedaccuracy, assumingindependence. Then we showhowto adjust the sampling of randomsubsets in a waythat is fair andbalanced, given a limited amountof time. Finally, weshowhow decision trees built fromsets of interacting features can be converted into DNF expressions to form constructed features. Wedemonstrate theeffectiveness ofthemethod empirically byshowing that itcanimprove theaccuracy ofthe C4. 5 decision-tree algorithm onseveral benchmark databases.

AAAI Conference 1997 Conference Paper

Integrating a Spatial Reasoner with a Resolution Theorem-Prover

• Thomas R. Ioerger

Some spatial reasoning systems use images to solve problems, rather than making formal logical inferences. However, an open question is how to use these systems in contexts where some nonspatial information is also involved. We present a hybrid reasoning method in which we extend the capabilities of a spatial reasoner by integrating it with a resolution theorem-prover. We prove that the hybrid system is refutation-complete, in the sense that, if a domain theory is unsatisfiable, perhaps only because all of its models entail unrealizable images, then our algorithm will halt. We discuss how our approach differs from other hybrid reasoning algorithms in the way it manages the interaction between sub-systems.