Search results for " image processing"
showing 10 items of 2323 documents
Problem Space Identification for Developing Virtual Reality Learning Environments
2021
Our study argues that the extant literature on virtual reality-based learning environments (VRLEs) currently lacks proper definitions and context descriptions for a problem space, which is fundamental for conducting design science research (DSR). Without properly conducted problem space identification, the most pivotal problems cannot be identified resulting solutions lacking validity and unreliable evaluations. This is a major challenge for the DSR in the educational field, but also for the research on VRLEs. The purpose of this paper is to introduce a novel DSR method to support rigorous problem space identification, which would allow rigorous and profound problem space analysis. The inst…
Self-Organized Linguistic Systems: From traditional AI to bottom-up generative processes
2018
Este trabajo busca explorar el potencial de los procesos generativos bottom-up en el contexto de la producción conlang, con el objetivo de describir las bases de un nuevo campo de investigación: los Sistemas Lingüísticos Autoorganizados o SOLS, específicamente bajo la perspectiva doble de sistemas autoorganizados y lenguajes construidos. El enfoque SOLS proporciona un marco para la creación de lenguajes artificiales autogenerados y puede servir como punto de partida para el desarrollo de lenguajes dependientes del contexto o específicos del dominio. Reconoce que el desarrollo de conlangs puede ocurrir en sociedades artificiales de agentes simples, como resultado de interacciones sociales en…
Distributed channel prediction for multi-agent systems
2017
Los sistemas multiagente (MAS) se comunican a través de una red inalámbrica para coordinar sus acciones e informar sobre el estado de su misión. La conectividad y el rendimiento del sistema pueden mejorarse mediante la predicción de la ganancia del canal. Presentamos un esquema basado en regresión de procesos gaussianos (GPR) distribuidos para predecir el canal inalámbrico en términos de la potencia recibida en el MAS. El esquema combina una máquina de comité bayesiano con un esquema de consenso medio, distribuyendo así no sólo la memoria sino también la carga computacional y de comunicación. A través de simulaciones de Monte Carlo, demostramos el rendimiento del GPR propuesto. RACHEL TEC20…
Fixed Points for Multivalued Convex Contractions on Nadler Sense Types in a Geodesic Metric Space
2019
In 1969, based on the concept of the Hausdorff metric, Nadler Jr. introduced the notion of multivalued contractions. He demonstrated that, in a complete metric space, a multivalued contraction possesses a fixed point. Later on, Nadler&rsquo
Combining gestures and vocalizations to imitate sounds
2015
International audience; Communicating about sounds is a difficult task without a technical language, and naïve speakers often rely on different kinds of non-linguistic vocalizations and body gestures (Lemaitre et al. 2014). Previous work has independently studied how effectively people describe sounds with gestures or vocalizations (Caramiaux, 2014, Lemaitre and Rocchesso, 2014). However, speech communication studies suggest a more intimate link between the two processes (Kendon, 2004). Our study thus focused on the combination of manual gestures and non-speech vocalizations in the communication of sounds. We first collected a large database of vocal and gestural imitations of a variety of …
Archetypal analysis: an alternative to clustering for unsupervised texture segmentation
2019
Texture segmentation is one of the main tasks in image applications, specifically in remote sensing, where the objective is to segment high-resolution images of natural landscapes into different cover types. Often the focus is on the selection of discriminant textural features, and although these are really fundamental, there is another part of the process that is also influential, partitioning different homogeneous textures into groups. A methodology based on archetype analysis (AA) of the local textural measurements is proposed. AA seeks the purest textures in the image and it can find the borders between pure textures, as those regions composed of mixtures of several archetypes. The prop…
Comparing identification of vocal imitations and computational sketches of everyday sounds
2016
International audience; Sounds are notably difficult to describe. It is thus not surprising that human speakers often use many imitative vocalizations to communicate about sounds. In practice,vocal imitations of non-speech everyday sounds (e.g. the sound of a car passing by) arevery effective: listeners identify sounds better with vocal imitations than with verbal descriptions, despite the fact that vocal imitations are often inaccurate, constrained by the human vocal apparatus. The present study investigated the semantic representations evoked by vocal imitations by experimentally quantifying how well listeners could match sounds to category labels. Itcompared two different types of sounds…
Control of irregular cardiac rhythm
2018
International audience; The aim of this work is to investigate the chaos control of the one di- mensional map which modelizes the duration of the current cardiac action potential (APD) as a function of the previous one. Using OGY control method, we obtain very satisfactory numerical results to stabilize the irregular heart rhythm into the normal rhythm.
Remote sensing image segmentation by active queries
2012
Active learning deals with developing methods that select examples that may express data characteristics in a compact way. For remote sensing image segmentation, the selected samples are the most informative pixels in the image so that classifiers trained with reduced active datasets become faster and more robust. Strategies for intelligent sampling have been proposed with model-based heuristics aiming at the search of the most informative pixels to optimize model's performance. Unlike standard methods that concentrate on model optimization, here we propose a method inspired in the cluster assumption that holds in most of the remote sensing data. Starting from a complete hierarchical descri…
Recognition of Falls and Daily Living Activities Using Machine Learning
2018
A robust fall detection system is essential to support the independent living of elderlies. In this context, we develop a machine learning framework for fall detection and daily living activity recognition. Using acceleration data from public databases, we test the performance of two algorithms to classify seven different activities including falls and activities of daily living. We extract new features from the acceleration signal and demonstrate their effect on improving the accuracy and the precision of the classifier. Our analysis reveals that the quadratic support vector machine classifier achieves an overall accuracy of 93.2% and outperforms the artificial neural network algorithm. Re…