Marcel Kvassay

Agent-Based simulation platform evaluation in the context of human behavior modeling

In this paper we provide a brief survey of agent based simulation (ABS) platforms and evaluate two of them --- NetLogo and MASON --- by implementing an exemplary scenario in the context of human behavior modeling. We define twelve evaluation points, which we discuss for both of the evaluated systems. The purpose of our evaluation is to identify the best ABS platform for parametric studies (data farming) of human behavior, but we intend to use the system also for training purposes. That is why we also discuss one of serious game platform representatives --- VBS2.

Use of E-mail Social Networks for Enterprise Benefit

The article discusses the potential methods and benefits of the analysis of social networks hidden in the enterprise and personal email archives. A proof-of concept prototype was developed. Social network extraction and the spreading activation algorithm are discussed and evaluated.The article discusses the potential methods and benefits of the analysis of social networks hidden in the enterprise and personal email archives. A proof-of concept prototype was developed. Social network extraction and the spreading activation algorithm are discussed and evaluated.

Towards causal analysis of data from human behaviour simulations

In this article, which is a report of work in progress, we explore the principles of Bayesian causal analysis broadly along the lines formulated by Judea Pearl and other researchers. We apply these principles in the context of human behaviour modelling and aim at developing intelligent data analysis methods for large scale data sets, more specifically for logs from realistic simulations of human behaviour and data farming experiments in the context of the EDA project A-0938-RT-GC EUSAS.

Email Social Network Extraction and Search

The article discusses our email search prototype, which exploits social networks hidden in email archives and the spread of activation algorithm. The prototype offers new way of searching email archives as knowledge repository. The prototype was partially evaluated on the Enron email corpus.

Handling internal complexity in highly realistic agent-based models of human behaviour

This article describes our work in progress and deals with methods and approaches for handling internal complexity emerging in highly realistic models of human behaviour. We present a new modelling approach to human decision making along with a conceptual design of several methods targeting selected aspects of complexity, such as the combinatorial explosion of action alternatives in rich environments, or the impact of ontological reasoning on human behaviour models that need to perform in real time. We illustrate our design in the context of the EDA project A-0938-RT-GC EUSAS, where we plan to implement it.

Combining object-oriented and ontology-based approaches in human behaviour modelling

This article proposes a combination of object-oriented and ontology-based approaches for real-time interworking of human behaviour models in the context of agent-based simulation systems. We present a conceptual design of a semantic intermediation framework, including the split of the responsibilities between the intermediation ontology and software code. We illustrate our design in the context of the EDA project A-0938-RT-GC EUSAS, where it will be used for integrating various behaviour models and for virtual trainings running in real time. We also report the results of preliminary performance tests related to ontological queries, and conclude with our future plans concerning the intermediation infrastructure.

Summarizing the behaviour of complex dynamic systems

This paper outlines a general method for summarizing the behaviour of complex dynamic systems inspired by Bayesian causal analysis. The method is universally applicable and often permits to cut the backward causal loops through which the analyzed variables seem to co-determine themselves due to the nonlinearity of the equations describing complex systems.

Exploring human behaviour models through causal summaries and machine learning

This paper is a case study meant to demonstrate the relevance of causal summaries for exploratory analysis of human behaviour models. We broadly define a causal summary as a partition of the significant values of the analyzed variables (in our case the simulated motives fear and anger of human beings) into separate contributions by various “causing” factors, such as social influence or external events. We demonstrate that such causal summaries can be processed by machine learning techniques (e.g. clustering and classification) and facilitate meaningful interpretations of the emergent behaviours of complex agent-based models.

Graph-based analysis of data from human behaviour simulations

In this article, which describes our current work in progress, we demonstrate the potential and universality of graph-based methods for analysing data from computer simulations of human behaviour. The first method, MASDA algorithm, analyses action sequences through an ontology-driven process of abstraction, and aims at isolating strategic sequences and strategic action descriptions in a graphical and symbolic form. The second method, based on the spreading activation algorithm, aims at finding significant correlations between the simulation results and its various internal parameters, settings, events and entities. We illustrate our methods in the context of the EDA project A-0938-RT-GC EUSAS, where they are to be used after validation.

Towards More Realistic Human Behaviour Simulation: Modelling Concept, Deriving Ontology and Semantic Framework

This chapter argues in favour of semantic methods and approaches to human behaviour modelling. Semantic perspective can provide a seamless bridge between theoretical models and their software implementations, as well as contribute towards elegant and generic modular structure of the resulting simulation system. We describe our work in progress regarding highly realistic models of human behaviour and the impact of ontological reasoning on real-time simulations. We illustrate our approach in the context of the EDA project A-0938-RT-GC EUSAS, where we plan to implement it.