Search results for "Machine"
showing 10 items of 2592 documents
Preoperative Planning for Guidewires Employing Shape-Regularized Segmentation and Optimized Trajectories
2019
Upcoming robotic interventions for endovascular procedures can significantly reduce the high radiation exposure currently endured by surgeons. Robotically driven guidewires replace manual insertion and leave the surgeon the task of planning optimal trajectories based on segmentation of associated risk structures. However, such a pipeline brings new challenges. While Deep learning based segmentation such as U-Net can achieve outstanding Dice scores, it fails to provide suitable results for trajectory planning in annotation scarce environments. We propose a preoperative pipeline featuring a shape regularized U-Net that extracts coherent anatomies from pixelwise predictions. It uses Rapidly-ex…
An enhanced, near-term HCPB design as driver blanket for the EU DEMO
2019
The Helium Cooled Pebble Bed (HCPB) breeding blanket is a candidate as driver blanket for the EU DEMO. The reference design of the HCPB is based on a cooling plate “sandwich” arrangement built in Multi-Module Segments. This architecture significantly improved the tritium breeding performance (TBR = 1.15) and the plant circulating power (≈130 MW) compared to the former ITER-like “beer-box”-like design (TBR<1.10, plant circulating power>200 MW). However, several issues remain with this design, in which (1) the still large power required per He circulator (beyond the state-of-the-art for these components) and (2) the large tritium inventory foreseen in Be have been identified as the most…
Does the mastery of center-embedded linguistic structures distinguish humans from nonhuman primates?
2005
In a recentScience article, Fitch and Hauser (2004; hereafter, F&H) claimed to have demonstrated that cotton-top tamarins fail to learn an artificial language produced by a phrase structure grammar (Chomsky, 1957) generating center-embedded sentences, whereas adult humans easily learn such a language. We report an experiment replicating the results of F&H in humans but also showing that subjects learned the language without exploiting in any way the center-embedded structure. When the procedure was modified to make the processing of this structure mandatory, the subjects no longer showed evidence of learning. We propose a simple interpretation for the difference in performance observed in F…
Comparison between different surface treatment methods on shear bond strength of zirconia (in vitro study)
2020
Background To compare the effect of Er:YAG Laser and Air particle abrasion (APA) surface treatments on shear bond strength of Y-TZP to composite resin cuboids in the presence and absence of primer application and salivary contamination. Material and methods Seventy-two cuboidal shaped specimens 7x7x3 were prepared from Y-TZP using CADCAM, cleaned and sintered. Specimens were divided into 2 main groups (n=36) according to surface treatment method; Air particle abrasion (A) and laser (L). Each group was subdivided into 2 subgroups (N = 18) according to surface modification using primer; each subgroup was further divided into 2 subdivisions (N=9) according to the presence of salivary contamina…
Minimal learning machine in hyperspectral imaging classification
2020
A hyperspectral (HS) image is typically a stack of frames, where each frame represents the intensity of a different wavelength of light. Each spatial pixel has a spectrum. In the classification of the HS image, each spectrum is classified pixel-by-pixel. In some of the real-time applications, the amount of the HS image data causes performance challenges. Those issues relate to the platforms (e.g. drones) payload restrictions, the issues of the available energy and to the complexity of the machine learning models. In this study, we introduce the minimal learning machine (MLM) as a computationally cheap training and classification machine learning method for the hyperspectral imaging classificatio…
Structural Knowledge Extraction from Mobility Data
2016
Knowledge extraction has traditionally represented one of the most interesting challenges in AI; in recent years, however, the availability of large collections of data has increased the awareness that “measuring” does not seamlessly translate into “understanding”, and that more data does not entail more knowledge. We propose here a formulation of knowledge extraction in terms of Grammatical Inference (GI), an inductive process able to select the best grammar consistent with the samples. The aim is to let models emerge from data themselves, while inference is turned into a search problem in the space of consistent grammars, induced by samples, given proper generalization operators. We will …
Modeling and 'smart' prototyping human-in-the-loop interactions for AmI environments
2021
[EN] Autonomous capabilities are required in AmI environments in order to adapt systems to new environmental conditions and situations. However, keeping the human in the loop and in control of such systems is still necessary because of the diversity of systems, domains, environments, context situations, and social and legal constraints, which makes full autonomy a utopia within the short or medium term. Human-system integration introduces an important number of challenges and problems that have to be solved. On the one hand, humans should interact with systems even in those situations where their attentional, cognitive, and physical resources are limited in order to perform the interaction.…
Stochastic model predicts evolving preferences in the Iowa gambling task
2014
Learning under uncertainty is a common task that people face in their daily life. This process relies on the cognitive ability to adjust behavior to environmental demands. Although the biological underpinnings of those cognitive processes have been extensively studied, there has been little work in formal models seeking to capture the fundamental dynamic of learning under uncertainty. In the present work, we aimed to understand the basic cognitive mechanisms of outcome processing involved in decisions under uncertainty and to evaluate the relevance of previous experiences in enhancing learning processes within such uncertain context. We propose a formal model that emulates the behavior of p…
Learning Behavioral Rules from Multi-Agent Simulations for Optimizing Hospital Processes
2021
Hospital processes are getting more and more complex, starting from the creation of therapy plans over intra-hospital transportation up to the coordination of patients and staff members. In this paper, multi-agent simulations will be used to optimize the coordination of different kinds of individuals (like patients and doctors) in a hospital process. But instead of providing results in form of optimized schedules, here, behavioral rules for the different individuals will be learned from the simulations, that can be exploited by the individuals to optimize the overall process. As a proof-of-concept, the approach will be demonstrated in different variants of a hospital optimization scenario, …
Intelligent learning environment for better student’s academic performance
2021
In this paper, the authors aim to develop an intelligent learning environment model designed to improve students’ academic performance. Methodology: Referring to the litarature, the authors identified and analyzed a number of relevant issues that influence the specific components of an intelligent learning environment. These aspects were quantified using performance indicators defined on the basis of the specific objectives of each aspect chosen. Results: Following the analysis, the authors developed a model of intelligent learning space, and for its representation, we used conceptual modeling. Conclusions: Finally, the authors propose the prevalidation of the model using the dynamic modeli…