Felix Ramos - Academia.edu (original) (raw)

Papers by Felix Ramos

Generation of virtual creatures under multidisciplinary biological premises

Artificial Life and Robotics

People are being influenced by several means to purchase different products or services, e.g., ta... more People are being influenced by several means to purchase different products or services, e.g., targeted advertisements that are generated by computer systems. Agents in these systems are known as the influencers of the environment. In this work, it is proposed an architecture based on a Multi-Agent System to show autonomous behaviors with social implications. The social behaviors observed are used to analyze the influence of suppliers and the trend of products or services in commercial markets. The study case in this paper uses the color based fashion trends.

Computational intelligence and neuroscience, 2017

Emotion regulation is a process by which human beings control emotional behaviors. From neuroscie... more Emotion regulation is a process by which human beings control emotional behaviors. From neuroscientific evidence, this mechanism is the product of conscious or unconscious processes. In particular, the mechanism generated by a conscious process needs a priori components to be computed. The behaviors generated by previous experiences are among these components. These behaviors need to be adapted to fulfill the objectives in a specific situation. The problem we address is how to endow virtual creatures with emotion regulation in order to compute an appropriate behavior in a specific emotional situation. This problem is clearly important and we have not identified ways to solve this problem in the current literature. In our proposal, we show a way to generate the appropriate behavior in an emotional situation using a learning classifier system (LCS). We illustrate the function of our proposal in unknown and known situations by means of two case studies. Our results demonstrate that it ...

Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment

A character’s appearance is crucial to communicating game mechanics to the audience. Creating a g... more A character’s appearance is crucial to communicating game mechanics to the audience. Creating a game character’s design is a time-consuming task and requires design knowledge, skills, and experience. Research on how an AI system might be able to support this design process is an underexplored area. In this work we present a prototype of a variational autoencoder-based creativity support tool that modifies game character silhouettes by using words to describe the design’s desired properties.

Artificial Intelligence Review, 2020

In the field of Artificial Intelligence (AI), efforts to achieve human-like behavior have taken v... more In the field of Artificial Intelligence (AI), efforts to achieve human-like behavior have taken very different paths through time. Cognitive Architectures (CAs) differentiate from traditional AI approaches, due to their intention to model cognitive and behavioral processes by understanding the brain’s structure and their functionalities in a natural way. However, the development of distinct CAs has not been easy, mainly because there is no consensus on the theoretical basis, assumptions or even purposes for their creation nor how well they reflect human function. In consequence, there is limited information about the methodological aspects to construct this type of models. To address this issue, some initial statements are established to contextualize about the origins and directions of cognitive architectures and their development, which help to outline perspectives, approaches and objectives of this work, supported by a brief study of methodological strategies and historical aspec...

A Human-like Strategy For Pervasive Service Composition

2020 11th IEEE International Conference on Cognitive Infocommunications (CogInfoCom)

Insecurity is a common problem that all cities face, and different solutions have been developed ... more Insecurity is a common problem that all cities face, and different solutions have been developed throughout history to prevent or eradicate this problem. Using existing technology or developing new one is a good strategy; currently there has been technological breakthroughs, both in software and hardware, that allows us to use of Artificial Intelligence (AI) algorithms. Cognitive processes are studied in order to build solutions of problems in a way similar to what humans do. In this work, we propose the interaction among cognitive processes and info-communication devices to enable an artificial cognitive system to compose pervasive services useful to solve complex problems of public safety. Specifically, to deter predatory crimes when the predator decides to perform the crime and is within the victim's vicinity.

Obligations as constrainers, descriptors, and linkers of Open System of Systems

Collaboration among independent systems to achieve a common objective, which a system alone could... more Collaboration among independent systems to achieve a common objective, which a system alone could not accomplish by itself, requires dynamic composition of the participant systems, in addition to mechanisms for leading the interaction of the resultant system of systems. Here is proposed to model system of systems using a multi-agent system approach, where agents represent stakeholders of the systems. Systems

Computational framework of the visual sensory system based on neuroscientific evidence of the ventral pathway

Cognitive Systems Research

IEEE Sensors Journal, 2011

This paper deals with distributed creation and maintaining of ad hoc networks including diverse w... more This paper deals with distributed creation and maintaining of ad hoc networks including diverse wireless devices, namely sensors, PDA, cell phones, and video games consoles. A cluster-based self-organizing strategy is proposed for building a backbone among the mobile devices, detecting segmentation, and recovery. In this approach, each mobile device is controlled by a multi-role agent, which performs these tasks efficiently based only on local interactions; role management allows the backbone reconfiguration when the nodes leave or arrive to the network yielding a complex global emergent behavior. Energy saving is achieved by adapting the time interval and power of transmission after the network formation. Simulations showed that the distributed algorithms performance is close to that obtained by an optimizing global procedure.

A Multi-agent System Architecture for Modeling Multicultural Interaction

sersc.org

Page 1. International Journal of Energy, Information and Communications Vol. 2, Issue 4, November... more Page 1. International Journal of Energy, Information and Communications Vol. 2, Issue 4, November, 2011 15 A Multi-agent System Architecture for Modeling Multicultural Interaction Omar Gonz??lez 1 , Jean-Paul Barth??s 1 , F??lix Ramos 2 ...

Bio-inspired computational object classification model for object recognition

Cognitive Systems Research, 2022

A Cognitive Architecture Based on Neuroscience for the Control of Virtual 3D Human Creatures

Lecture Notes in Computer Science, 2010

Abstract. For the creation of a virtual 3D creature it is necessary an underlying structure that ... more Abstract. For the creation of a virtual 3D creature it is necessary an underlying structure that provides to it some desired capabilities. One of our main research objectives is creating a virtual 3D creature that resem-bles human behavior in an actual environment. In this paper, we propose a ...

Proceedings of the 2005 International Symposium on Collaborative Technologies and Systems, 2005., 2005

This paper presents details of the specification, design and functionality of the Virtual UNR Cam... more This paper presents details of the specification, design and functionality of the Virtual UNR Campus software (in short, VCampus), an interactive virtual environment that allows users to explore the 3D representation of the University of Nevada, Reno. VCampus provides a realistic rendering of the university and allows users to obtain useful information such as building names and directories, university historical and statistical data, events scheduled to take place on campus, and area maps centered on specified locations. The users can navigate through the 3D representation of the campus by adopting either a first or a third person view and by selecting either a walking or a flying exploration mode. Various graphical objects can be accessed in the environment to obtain orientation data and general information, a guided tour is available, and communication and collaboration with peers is supported by a multiuser , multi-character real-time interaction facility. The paper also includes a comparison of VCampus with similar projects, a discussion of the environment's advantages and limitations, and a set of pointers to future research and development work.

In game development, designing compelling visual assets that convey gameplay-relevant features re... more In game development, designing compelling visual assets that convey gameplay-relevant features requires time and experience. Recent image generation methods that create high-quality content could reduce development costs, but these approaches do not consider game mechanics. We propose a Convolutional Variational Autoencoder (CVAE) system to modify and generate new game visuals based on their gameplay relevance. We test this approach with Pokemon sprites and Pokemon type information, since types are one of the game's core mechanics and they directly impact the game's visuals. Our experimental results indicate that adopting a transfer learning approach can help to improve visual quality and stability over unseen data.

In this paper we present a fast data parallel implementation of the radix sort on the DirectCompu... more In this paper we present a fast data parallel implementation of the radix sort on the DirectCompute software development kit (SDK). We also discuss in detail the various optimization strategies that were used to increase the performance of our radix sort, and we show how these strategies can be generalized for any video card that supports the DirectCompute model. The insights that we share in this paper should be of use to any General-Purpose Graphics Processing Unit (GPGPU) programmer regardless of the video card being used. Finally, we discuss how radix sort can be used to accelerate ray tracing and we present some results in this area as well.

One of the main characteristics of multi-agent systems is the ability to solve problems achieving... more One of the main characteristics of multi-agent systems is the ability to solve problems achieving objectives. This is possible because of the learning mechanisms that are embedded in the systems and go from neural networks up to vector support machines. Agent-based systems stand out for their autonomy and adaptation of dynamic conditions of the environment. This article presents the Hebbian theory, which is one of the learning methods from the neuroscience field. A particularity presented by the Hebbian theory from the computer since field perspective is the primary mechanism of synaptic plasticity where the value of a synaptic connection increases if neurons on both sides of a said synapse are activated repeatedly, creating a new one simultaneously. This mechanism is integrated into the Learning Classifier Systems (LCS) to validate its effectiveness in the solution task, and can be used in multi-agent systems.

Computational Intelligence and Neuroscience

Episodic memory and emotions are considered essential functions in human cognition. Both allow us... more Episodic memory and emotions are considered essential functions in human cognition. Both allow us to acquire new knowledge from the environment, ranging from the objects around us to how we feel towards them. These qualities make them crucial functions for systems trying to create human-like behaviour. In the field of cognitive architectures (CAs), there are multiple studies covering memory and emotions. However, most of them treat these subjects in an isolated manner, considering emotions only as a reward signal unrelated to a retrieved experience. To address this lack of direct interaction, we propose a computational model that covers the common processes that are related to memory and emotions. Specifically, this proposal focuses on affective evaluations of episodic memories. Neurosciences and psychology are the bases of this model. That is, the model’s components and the processes that they carry out on the information they receive are designed based on evidence from these cogni...

2015 International Conference on Computational Science and Computational Intelligence (CSCI), 2015

This article describes how to generate autonomous behavior to populate a virtual environment usin... more This article describes how to generate autonomous behavior to populate a virtual environment using Serious Games and Learning Classifier Systems. A serious game is a paradigm that simulates the real environment like a natural phenomenon. For example, people's behavior living an earthquake, fire, weather phenomenon or others. Into a serious game, the users are represented by virtual entities that have autonomous behavior taken from human's behavior. The principal interest to use serious games is that it's possible to obtain a tool with capabilities to predict, to plan and to train people involved in many natural phenomenons. The originality of this paper is that used a Learning Classifier Systems (LCS) inside in Serious games. It is possible to find a better simulation of the human's behavior into a real situation, using learning machine. The entities (agents) has autonomy and adaptability given by a genetic algorithm embedded in the LCS.

Biologically Inspired Cognitive Architectures

Emotional and motivational evaluations are part of the development of rewards within living being... more Emotional and motivational evaluations are part of the development of rewards within living beings. Particularly, during the perception of stimuli in the environment, these evaluations collaborate with one another to generate reward values automatically, without the need to involve rational processes. In this paper we propose a conceptual model of automatic reward for virtual creatures inspired by neuroscientific evidence, contemplating the processes of emotions and motivations, as well as the generation and recovery of automatic reward values. According to the evidence, the reward process is divided into two processes: liking, which is oriented toward interpreting information inputs and generating reward values, and wanting, focused on the recovery of the stored reward values and the generation of objectives in the environment. The reward process is implemented as a concurrent and parallel naturally distributed system, allowing virtual creatures to adapt to their environment and generate more credible behaviors. The results of liking and wanting are shown in this article through a case study, in which the performance of both processes is observed when the creature interacts with the environment.

Towards a model of visual recognition based on neurosciences

Procedia Computer Science