Angelo Loula

Artificial Cognition Systems

Emphasizing how cognitive processes can be meaningful to artificial systems, this text presents recent research efforts in artificial intelligence about building artificial systems capable of performing cognitive tasks.

Emergence of self-organized symbol-based communication in artificial creatures

In this paper, we describe a digital scenario where we simulated the emergence of self-organized symbol-based communication among artificial creatures inhabiting a virtual world of unpredictable predatory events. In our experiment, creatures are autonomous agents that learn symbolic relations in an unsupervised manner, with no explicit feedback, and are able to engage in dynamical and autonomous communicative interactions with other creatures, even simultaneously. In order to synthesize a behavioral ecology and infer the minimum organizational constraints for the design of our creatures, we examined the well-studied case of communication in vervet monkeys. Our results show that the creatures, assuming the role of sign users and learners, behave collectively as a complex adaptive system, where self-organized communicative interactions play a major role in the emergence of symbol-based communication. We also strive in this paper for a careful use of the theoretical concepts involved, including the concepts of symbol and emergence, and we make use of a multi-level model for explaining the emergence of symbols in semiotic systems as a basis for the interpretation of inter-level relationships in the semiotic processes we are studying.

Symbolic Communication in Artificial Creatures: An Experiment in Artificial Life

This is a project on Artificial Life where we simulate an ecosystem that allows cooperative interaction between agents, including intra-specific predator-warning communication in a virtual environment of predatory events. We propose, based on Peircean semiotics and informed by neuroethological constraints, an experiment to simulate the emergence of symbolic communication among artificial creatures. Here we describe the simulation environment and the creatures’ control architectures, and briefly present obtained results.

Recognition of Static Gestures Applied to Brazilian Sign Language (Libras)

This paper aims at describing an approach developed for the recognition of gestures on digital images. In this way, two shape descriptors were used: the histogram of oriented gradients (HOG) and Zernike invariant moments (ZIM). A feature vector composed by the information acquired with both descriptors was used to train and test a two stage Neural Network, which is responsible for performing the recognition. In order to evaluate the approach in a practical context, a dataset containing 9600 images representing 40 different gestures (signs) from Brazilian Sign Language (Libras) was composed. This approach showed high recognition rates (hit rates), reaching a final average of 96.77%.

On Building Meaning: A Biologically-Inspired Experiment on Symbol-Based Communication

The use of an appropriate set of empirical and theoretical constraints to guide the construction of synthetic experiments leads to a better understanding of the natural phenomena under study, and allows for a greater understanding of the experimental results. We begin this chapter with a description of a general approach for conducting experiments with artificial creatures within a synthetic ethological context. Next, we describe how this approach was used to build a computational experiment regarding the emergence of self-organized symbols. Our experiment simulated a community of artificial creatures undergoing complex intra and inter-specific interactions in which meaning evolved over time, from a tabula rasa repertoire of random alarm-calls to a specific set of optimal referential alarm-calls. To design different kinds of creatures as well as innanimate elements of the environment, we applied theoretical constraints from the Peircean philosophy of sign and empirical constraints from neuroethology. Our results suggest that the constraints chosen were both necessary and sufficient to produce symbolic communication.

The emergence of symbol-based communication in a complex system of artificial creatures

We present here a digital scenario to simulate the emergence of self-organized symbol-based communication among artificial creatures inhabiting a virtual world of predatory events. In order to design the environment and creatures, we seek theoretical and empirical constraints from C.S. Peirce Semiotics and an ethological case study of communication among animals. Our results show that the creatures, assuming the role of sign users and learners, behave collectively as a complex system, where self-organization of communicative interactions plays a major role in the emergence of symbol-based communication. We also strive for a careful use of the theoretical concepts involved, including the concepts of symbol, communication, and emergence, and we use a multi-level model as a basis for the interpretation of inter-level relationships in the semiotic processes we are studying.

Symbolic associations in neural network activations: Representations in the emergence of communication

Representation has a fundamental role in Artificial Intelligence but there is still an open debate on basic issues on this subject. Particularly, there have been various studies on the emergence of communication and language in artificial agents, where the debate on representations underlying these processes should be significant, however not much discussion and studies have been done. We propose to identify and classify possible representational processes occurring during the emergence of communication, replicating a computational experiment previously proposed and evaluating neural network activations patterns. To define representation and its classes, including icons, indexes and symbols, we rely on the semiotics of Charles Sanders Peirce. Results show that symbolic associations are established during the evolution of artificial agents and such symbolic associations benefit adaptive success.

Augmented Tattoo: Evaluation of an Augmented Reality System for Tattoo Visualization

Augmented Reality complements reality overlaying computer modeled virtual objects in real world images, allowing users to be immersed in synthetic environments. Tattoos are an ancient cultural practice, performed for centuries, with intervention in epithelial layers of the human body, and technological devices can further expand this practice. Here we describe and evaluate an Augmented Reality system for visualization of virtual tattoos on the skin, accompanying the surface of the human body. From a captured image, the system detects markers on the skin, and outputs an image without the markers with an AR tattoo inscribed to the skin. Markers detection provides high accuracy rates that allow adequate mesh and, along with skin segmentation and markers removal, the system generates suitable final images. Our system reveals robustness concerning the several possible operation conditions, dealing with different lighting conditions, background content, skin tones, drawing quality of the markers in the skin, and possible occlusions of skin and markers.

Automated Fuzzy System Based on Feature Extraction and Selection for Opinion Classification Across Different Domains

Opinions have a relevant inuence on people’s behavior. The Internet and the Web have made it possible for people to share their opinions and for other people and organizations find out more about opinions and experiences from individuals. Still, opinions involve sentiments that are vague and imprecise textual descriptions. Hence, due to the nature of the data, Fuzzy Logic can be a promising approach. This paper proposes a method to automatically build a fuzzy system, based on features extracted and selected from documents, to perform classification of sentiment in opinions across different domains. Almost 60 features were extracted from documents and multiple feature selection algorithms were applied. Over the selected features, the Wang-Mendel (WM) method was used to generate fuzzy rules and classify documents. Variations on fuzzy set modeling, on the use of weights in the rules and on fuzzy inference mechanisms were considered. The classifier fuzzy system based achieved 71,25% of accuracy in a 10-fold cross-validation, comparable to a SVM classifier.

A genetic-evolutionary model to simulate population dynamics in the Calangos game

Calangos is an under development educational game based on the fauna and flora of the desert-like field of the sand dunes in the middle São Francisco River, located within the Caatinga biome in Brazil. One of the players goals is to manage the behavior of species of lizards that inhabit this biome, with consequences to their ecology and evolution. For the development of the game a genetic-evolutionary model, embedded in a simulator, is proposed. This model will be used to simulate predator-prey dynamics based on the Evolutionary Biology and Ecology literature. The objective of this paper is to introduce the genetic-evolutionary model embedded in the simulator and present some key experimental findings. It will be shown that under certain environmental conditions lizard populations are only able to survive if allowed to evolve. The results will also show the main causes of death (malnutrition, dehydration, predation or aging), the diet preferences (vegetables or insects) of lizards and their relationship with specific environmental conditions.