Search results for "Problem domain"
showing 10 items of 12 documents
Using Inverse Reinforcement Learning with Real Trajectories to Get More Trustworthy Pedestrian Simulations
2020
Reinforcement learning is one of the most promising machine learning techniques to get intelligent behaviors for embodied agents in simulations. The output of the classic Temporal Difference family of Reinforcement Learning algorithms adopts the form of a value function expressed as a numeric table or a function approximator. The learned behavior is then derived using a greedy policy with respect to this value function. Nevertheless, sometimes the learned policy does not meet expectations, and the task of authoring is difficult and unsafe because the modification of one value or parameter in the learned value function has unpredictable consequences in the space of the policies it represents…
Improving the Competency of Classifiers through Data Generation
2001
This paper describes a hybrid approach in which sub-symbolic neural networks and symbolic machine learning algorithms are grouped into an ensemble of classifiers. Initially each classifier determines which portion of the data it is most competent in. The competency information is used to generated new data that are used for further training and prediction. The application of this approach in a difficult to learn domain shows an increase in the predictive power, in terms of the accuracy and level of competency of both the ensemble and the component classifiers.
Decoding Children's Social Behavior
2013
We introduce a new problem domain for activity recognition: the analysis of children's social and communicative behaviors based on video and audio data. We specifically target interactions between children aged 1-2 years and an adult. Such interactions arise naturally in the diagnosis and treatment of developmental disorders such as autism. We introduce a new publicly-available dataset containing over 160 sessions of a 3-5 minute child-adult interaction. In each session, the adult examiner followed a semi-structured play interaction protocol which was designed to elicit a broad range of social behaviors. We identify the key technical challenges in analyzing these behaviors, and describe met…
Enforcing Conceptual Modeling to improve the understanding of human genome
2010
It is widely accepted that the use of Conceptual Modeling techniques in modern Software Engineering leads to a more accurate description of the problem domain. The application of these techniques in the context of challenging domains as the human genome is a fascinating task. The relevant biological concepts should be properly addressed through the creation of the corresponding conceptual schema. This schema will improve the description of the global process followed from a DNA sequence to a fully functional protein. Once the conceptual model is established, the corresponding database is created. The database is intended to act as a unified repository of integrated information that will all…
Emergent vulnerabilities in Integrated Operations: A proactive simulation study of economic risk
2009
Abstract The protection of critical infrastructure requires an understanding of the effects of change on current and future safety and operations. Vulnerabilities may emerge during the rollout of updated techniques and integration of new technology with existing work practices. Managers need to understand how their decisions, often focused on economic priorities, affect the dynamics of vulnerability over time. Such understanding is difficult to obtain, as the historical data typically used for decision support, prediction and forecasting may not be available. We report on the use of group model building and simulation to consider proactively the effects of a 10-year, multi-billion dollar mo…
A heuristic for problem formalization in agent based simulation studies
2015
Agent Based Modeling and Simulation (ABMS) is considered an effective approach for conducting simulation studies in many fields. In order to develop high quality simulation models, methodological approaches are demanded. In such direction we are moving by proposing a heuristic for the formalization of agent based simulation problems. The proposed heuristic is based on some guidelines developed for identifying the main elements of the problem domain description by analysing verbs and their common taxonomy in grammar.
Numerical Investigations of an Implicit Leapfrog Time-Domain Meshless Method
2014
Numerical solution of partial differential equations governing time domain simulations in computational electromagnetics, is usually based on grid methods in space and on explicit schemes in time. A predefined grid in the problem domain and a stability step size restriction need. Recently, the authors have reformulated the meshless framework based on smoothed particle hydrodynamics, in order to be applied for time domain electromagnetic simulation. Despite the good spatial properties, the numerical explicit time integration introduces, also in a meshless context, a severe constraint. In this paper, at first, the stability condition is addressed in a general way by allowing the time step inc…
Unconditionally stable meshless integration of time-domain Maxwell’s curl equations
2015
Grid based methods coupled with an explicit approach for the evolution in time are traditionally adopted in solving PDEs in computational electromagnetics. The discretization in space with a grid covering the problem domain and a stability step size restriction, must be accepted. Evidence is given that efforts need for overcoming these heavy constraints. The connectivity laws among the points scattered in the problem domain can be avoided by using meshless methods. Among these, the smoothed particle electromagnetics, gives an interesting answer to the problem, overcoming the limit of the grid generation. In the original formulation an explicit integration scheme is used providing, spatial a…
Exploiting Numerical Behaviors in SPH.
2010
Smoothed Particle Hydrodynamics is a meshless particle method able to evaluate unknown field functions and relative differential operators. This evaluation is done by performing an integral representation based on a suitable smoothing kernel function which, in the discrete formulation, involves a set of particles scattered in the problem domain. Two fundamental aspects strongly characterizing the development of the method are the smoothing kernel function and the particle distribution. Their choice could lead to the so-called particle inconsistency problem causing a loose of accuracy in the approximation; several corrective strategies can be adopted to overcome this problem. This paper focu…
Some Numerical Remarks on a Meshless Approximation Method
2016
In this paper we consider sources of enhancement for the Smoothed Particle Hydrodynamics method in approximating a function and its derivatives. It is well known that the standard formulation is usually poor when scattered data distribution is considered or when the approximation near the boundary occurs. In this paper studies on the accuracy are provided and assessed with gridded and scattered data distribution in the problem domain. The improvements of the method are addressed and supporting numerical experiments are included.