We propose a system of Interactive Differential Evolution (IDE) based on paired comparisons for reducing user fatigue and evaluate its convergence speed in comparison with Genetic Algorithms (IGA) tournament IGA. User interface performance are central to Evolutionary Computation (IEC) fatigue. Unlike IGA conventional IDE, users the proposed IDE do not need compare whole individuals each other but rather only pairs individuals, which largely decreases In this paper, we design pseudo-IEC...

In a collaborative computer-supported engineering environment, the interoperation of various applications will need representation that goes beyond current geometry-based representation, which is inadequate for capturing semantic information. The primary purpose this study to discuss semantically based information exchange protocol facilitate seamless interoperability among and next generation computer-aided design systems (CAD) between CAD other use product data. An ontological approach...

In this paper, we describe a new algorithm that consists in combining an eye-tracker for minimizing the fatigue of user during evaluation process Interactive Evolutionary Computation. The approach is then applied to One-Max optimization problem.

The aim of our research is to find an efficient solution the services QoS optimization problem. This NP-hard problem well known in service-oriented computing field: given a business workflow that includes set abstract and concrete service implementations for each service, goal optimal combination services. majority recent proposals indicate Genetic Algorithms (GA) as best approach complex workflows. But this usually needs be solved at runtime, task which GA may too slow. We propose new...

Abstract MicroRNAs, small non-coding elements implied in gene regulation, are very interesting biomarkers for various diseases such as cancers. They represent potential prodigious biotechnologies early diagnosis and therapies. However, experimental verification of microRNA-disease associations time-consuming costly, so that computational modeling is a proper solution. Previously, we designed MiRAI, predictive method based on distributional semantics, to identify new between microRNA...

In this paper, we propose a new framework hybridizing Support Vector Machine (SVM), Multi-Objective Genetic Algorithm (MOGA) and Locality Sensitive Hashing (LSH). The goal is to tackle fine-grained classification challenges which means classifying many classes with high similarities between poor inside one class. SVM used for its ability of learning multi-class problem from very few training data. MOGA optimizing samples by so as improve rate. As data define discrete set instances not...

Interactive Evolutionary Computation (IEC) community aims at reducing user's fatigue during an optimization task involving subjective criteria: a set of graphic potential solutions are simultaneously shown to user which is identify most interesting the problem he had solve. operators applied choices expecting produce better solutions. As traditional IEC ask give mark each solution or explicitly choose bests with mouse, we propose new framework that uses in real time gaze information predict...

Computer aided design now aims to provide designers with a support during the early stages of design. The purpose is translate client's specifications into shape as automatically possible. However, processing text in natural language still out reach. We then assume that are manually translated intermediate composed constraints upon physical parameters. Our efforts concern transformation these shape, precisely way complete whether satisfies or not. first study case which single primitive...

We propose a data-driven evolutionary approach to the modeling of marine currents in Bay Monaco. The CMA (Covariance Matrix Adaptation) evolution strategy is used optimize parameters predictive model that may be as surrogate expensive and time-consuming finite-element simulations. models obtained are reasonably accurate easy interpret.

Abstract The identification of condition-specific gene sets from transcriptomic experiments is important to reveal regulatory and signaling mechanisms associated with a given cellular response. Statistical approaches using only expression data allow the genes whose most altered between different conditions. However, phenotype rarely direct consequence activity single gene, but rather reflects interplay several carry out certain molecular processes. Many methods have been proposed analyze in...

The identification of condition specific gene sets from transcriptomic experiments has important biological applications, ranging the discovery altered pathways between different phenotypes to selection disease-related biomarkers. Statistical approaches using only expression data are based on an overly simplistic assumption that genes with most expressions in process under study. However, a phenotype is rarely direct consequence activity single gene, but rather reflects interplay several...