Search results for "ML"
showing 10 items of 1465 documents
Sensory analysis with consumers using Free-Comment : analyses, performances and extensions
2021
Free-Comment (FC) consists in panelists describing the products using their own terms. Despite its benefits, notably the circumvention of limitations inherent to pre-established lists of sensory descriptors, FC remains rarely used because its performances are not well documented and its analyses and range of application remain limited. This thesis aims to overpass these limitations, highlighting the benefits and the potency of FC and thus put it in the spotlight for sensory analysis with consumers.For the pretreatment of FC data, a semi-automatized procedure is proposed. It enables the practitioners to extract an a posteriori list of sensory descriptors with a compromise between minimizing …
A network model for the short-term prediction of the evolution of cocaine consumption in Spain
2010
Cocaine consumption is a social problem with acute consequences and its dependency can be regarded as a health concern of social transmission. This fact leads us to develop the idea that its transmission dynamics can be studied using epidemiological mathematical models. Under this point of view, in this paper we propose a network model to study the short-term evolution of the cocaine consumer subpopulations. The model parameters are obtained from data source and from an analogue continuous model. Sensitivity of the model parameters is studied. The parameters are associated with prevention and treatment policies and the sensitivity study gives us information about which parameters have more …
Perceived-Value-driven Optimization of Energy Consumption in Smart Homes
2020
Residential energy consumption has been rising rapidly during the last few decades. Several research efforts have been made to reduce residential energy consumption, including demand response and smart residential environments. However, recent research has shown that these approaches may actually cause an increase in the overall consumption, due to the complex psychological processes that occur when human users interact with these energy management systems. In this article, using an interdisciplinary approach, we introduce a perceived-value driven framework for energy management in smart residential environments that considers how users perceive values of different appliances and how the us…
Deep CNN-ELM Hybrid Models for Fire Detection in Images
2018
In this paper, we propose a hybrid model consisting of a Deep Convolutional feature extractor followed by a fast and accurate classifier, the Extreme Learning Machine, for the purpose of fire detection in images. The reason behind using such a model is that Deep CNNs used for image classification take a very long time to train. Even with pre-trained models, the fully connected layers need to be trained with backpropagation, which can be very slow. In contrast, we propose to employ the Extreme Learning Machine (ELM) as the final classifier trained on pre-trained Deep CNN feature extractor. We apply this hybrid model on the problem of fire detection in images. We use state of the art Deep CNN…
Classification based on Iterative Object Symmetry Transform
2004
The paper shows an application of a new operator named the iterated object transform (IOT) for cell classification. The IOT has the ability to grasp the internal structure of a digital object and this feature can be usefully applied to discriminate structured images. This is the case of cells representing chondrocytes in bone tissue, giarda protozoan, and myeloid leukaemia. A tree classifier allows us to discriminate the three classes with a good accuracy.
Finding essential features for tracking starfish in a video sequence
2004
The paper introduces a software system for detecting and tracking starfish in an underwater video sequence. The target of such a system is to help biologists in giving an estimate of the number of starfish present in a particular area of the sea-bottom. The nature of the input images is characterised by a low signal/noise ratio and by the presence of noisy background represented by pebbles; this makes the detection a non-trivial task. The procedure we use is a chain of several steps that starts from the extraction of the area of interest and ends with a classifier and a tracker providing the necessary information for counting the starfish present in the scene. © 2003 IEEE.
Graph matching for efficient classifiers adaptation
2011
In this work we present an adaptation algorithm focused on the description of the measurement changes under different acquisition conditions. The adaptation is carried out by transforming the manifold in the first observation conditions into the corresponding manifold in the second. The eventually non-linear transform is based on vector quantization and graph matching. The transfer learning mapping is defined in an unsupervised manner. Once this mapping has been defined, the labeled samples in the first are projected into the second domain, thus allowing the application of any classifier in the transformed domain. Experiments on VHR series of images show the validity of the proposed method …
The functional-psychological continuum in the cognitive image of a destination: A confirmatory analysis
2009
Abstract This paper analyses the cognitive component of the image of a destination from a dual perspective. Firstly, we study its composition by positing three positions on a continuum: functional, mixed and psychological, which are analysed using confirmatory factor analysis. Secondly, we study the influence of these components on tourists' overall image of the destination and on their future behaviour intentions, using structural equation analysis. The results show that the psychological and functional components exercise the greatest influence on the overall image of the destination. Overall image was found to influence future behaviour intentions consistently, while the functional compo…
Model Based Design Optimization of Operational Reliability in Offshore Boom Cranes
2013
AbstractThis paper presents a model based approach for design of reliable electro-hydraulic motion control systems for offshore material handling cranes. The approach targets the system engineer and is based on steady-state computations, dynamic time domain simulation and numerical optimization.In general, the modelling takes into account the limited access to component data normally encountered by engineers working with system design. A system model is presented which includes the most important characteristics of both mechanical system and hydraulic components such as the directional control valve and the counterbalance valve.The model is used to optimize the performance of an initial des…
Simple kinematic models for the environmental interaction of tropical cyclones in vertical wind shear
2011
A major impediment to the intensity forecast of tropical cyclones (TCs) is believed to be associated with the interaction of TCs with dry environmental air. However, the conditions under which pronounced TC-environment interaction takes place are not well understood. As a step towards improving our understanding of this problem, we analyze here the flow topology of a TC immersed in an environment of vertical wind shear in an idealized, three-dimensional, convection-permitting numerical experiment. A set of distinct streamlines, the so-called manifolds, can be identified under the assumptions of steady and layer-wise horizontal flow. The manifolds are shown to divide the flow around the TC i…